Skip to content

Update to Vally 0.7.0#854

Open
adityamandaleeka wants to merge 4 commits into
mainfrom
adityamandaleeka/effective-journey
Open

Update to Vally 0.7.0#854
adityamandaleeka wants to merge 4 commits into
mainfrom
adityamandaleeka/effective-journey

Conversation

@adityamandaleeka

@adityamandaleeka adityamandaleeka commented Jul 2, 2026

Copy link
Copy Markdown
Member

Updates the informational skill-vs-baseline shadow harness to Vally 0.7.0:

  • Scoping via experiment run --eval-filter (deleted scope-experiment.mjs); CI honors each matrix entry's skills_path.
  • Scoring via Vally compare: adapt.mjs splits experiment output by eval file and runs compare per skill. Pass = credible improvement (mean preference > 0 with its 95% CI above 0). Dropped the old weighted-composite score + 10% threshold.
  • Eval specs: removed - type: pairwise from 89 files (0.7.0 removed that grader); the sibling prompt grader stays.

Requires Vally ≥ 0.7.0. Informational job — never gates PRs.

⚠️ Note: the experiment currently uses runs: 1, which makes the 95% CI very wide — genuinely-helpful skills often read "not credible." We should bump runs for a real signal before relying on these verdicts.

adityamandaleeka and others added 3 commits July 2, 2026 13:46
@adityamandaleeka
Migrate vally harness to single experiment run
5578e8d 
Consume Vally 0.6.0 (no ambient skill discovery; `vally experiment run`).
Replace the dual `vally eval` baseline/skilled harness with a single
declarative experiment per plugin, keeping adapt.mjs for the improvement-score
verdict.

- Add dotnet-skills.experiment.yaml: baseline (no skills) vs skilled (the one
  skill under test via environment.skills), skill path derived from the eval
  path. Excludes agent.* evals.
- Add scope-experiment.mjs: rewrites the experiment's evals/overrides blocks to
  scope a run to specific evals and pin model/judge/runs (no YAML dependency).
- adapt.mjs: add experiment-dir mode that splits per-variant results.jsonl into
  per-skill results.json; iterate the union of evals across variants and warn on
  any eval missing from a variant instead of silently dropping it.
- run-vally-evals.sh and vally-evaluation.yml: drive `vally experiment run`,
  then adapt. Select the run dir created by this invocation, clear and verify
  the expected per-skill outputs, and report produced-vs-expected shortfalls.
- Normalize compound-duration eval timeouts (2m40s/17m30s) to single-unit
  seconds; 0.6.0 validates specs that the old --skip-validate flow bypassed.
- Remove .vally.yaml (only configured ambient discovery, now gone).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@adityamandaleeka
Rework vally harness for 0.7.0: compare-based scoring + --eval-filter
8097ef8 
Consume vally 0.7.0: use `vally experiment run --eval-filter` for scoping
(deleting scope-experiment.mjs), and `vally compare` per eval as the scoring
engine. adapt.mjs now splits experiment output by evalFile and maps each
comparison to a per-skill verdict; a skill passes only on a credible
improvement (mean preference > 0 with its 95% CI above 0). Model/judge/runs
come from the experiment file's overrides block.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
@adityamandaleeka
Migrate eval specs off the removed pairwise grader
204d231 
vally 0.7.0 removed the `pairwise` grader type (the validator now hard-errors
on it); comparison moved into `vally compare`. Remove the `- type: pairwise`
grader entries; the sibling `prompt` grader retains per-trajectory LLM grading.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
@adityamandaleeka

adityamandaleeka commented Jul 2, 2026

Copy link
Copy Markdown
Member Author

@AbhitejJohn

@github-actions

github-actions Bot commented Jul 2, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor

Skill Coverage Report

Plugin Skill Covered Coverage
⚠️ dotnet-advanced csharp-scripts 13/22 59.1%
❌ dotnet-advanced dotnet-pinvoke 6/28 21.4%
⚠️ dotnet-ai mcp-csharp-create 18/25 72%
✅ dotnet-ai mcp-csharp-debug 16/18 88.9%
⚠️ dotnet-ai mcp-csharp-publish 10/15 66.7%
⚠️ dotnet-ai mcp-csharp-test 11/18 61.1%
✅ dotnet-ai technology-selection 20/24 83.3%
⚠️ dotnet-aspnetcore configuring-opentelemetry-dotnet 13/21 61.9%
⚠️ dotnet-aspnetcore minimal-api-file-upload 4/8 50%
❌ dotnet-blazor author-component 0/1 0%
❌ dotnet-blazor collect-user-input 0/4 0%
❌ dotnet-blazor configure-auth 0/3 0%
❌ dotnet-blazor coordinate-components 0/2 0%
❌ dotnet-blazor fetch-and-send-data 1/5 20%
❌ dotnet-blazor plan-ui-change 0/1 0%
❌ dotnet-blazor support-prerendering 0/3 0%
❌ dotnet-blazor use-js-interop 0/2 0%
❌ dotnet-data optimizing-ef-core-queries 4/17 23.5%
⚠️ dotnet-diag analyzing-dotnet-performance 12/21 57.1%
✅ dotnet-diag android-tombstone-symbolication 5/5 100%
✅ dotnet-diag apple-crash-symbolication 5/5 100%
✅ dotnet-diag clr-activation-debugging 16/19 84.2%
✅ dotnet-diag dotnet-trace-collect 15/17 88.2%
✅ dotnet-diag microbenchmarking 3/3 100%
✅ dotnet-experimental exp-mock-usage-analysis 12/13 92.3%
⚠️ dotnet-experimental exp-test-maintainability 10/18 55.6%
⚠️ dotnet-maui maui-collectionview 7/9 77.8%
⚠️ dotnet-maui maui-data-binding 6/10 60%
❌ dotnet-maui maui-dependency-injection 0/1 0%
❌ dotnet-maui maui-safe-area 0/2 0%
❌ dotnet-maui maui-theming 0/1 0%
❔ dotnet-msbuild agent.msbuild — error
⚠️ dotnet-msbuild check-bin-obj-clash 9/13 69.2%
❌ dotnet-msbuild directory-build-organization 0/1 0%
✅ dotnet-msbuild msbuild-modernization 6/7 85.7%
⚠️ dotnet-msbuild msbuild-server 7/9 77.8%
✅ dotnet-msbuild resolve-project-references 5/6 83.3%
✅ dotnet-nuget convert-to-cpm 16/16 100%
❌ dotnet-template-engine template-authoring 5/16 31.2%
✅ dotnet-template-engine template-comparison 8/10 80%
✅ dotnet-template-engine template-discovery 10/12 83.3%
⚠️ dotnet-template-engine template-instantiation 11/16 68.8%
⚠️ dotnet-template-engine template-smart-defaults 6/8 75%
⚠️ dotnet-template-engine template-validation 5/10 50%
❔ dotnet-test-migration agent.test-migration — error
✅ dotnet-test-migration migrate-mstest-v1v2-to-v3 13/16 81.2%
✅ dotnet-test-migration migrate-mstest-v3-to-v4 38/41 92.7%
✅ dotnet-test-migration migrate-vstest-to-mtp 21/25 84%
⚠️ dotnet-test-migration migrate-xunit-to-mstest 31/46 67.4%
✅ dotnet-test-migration migrate-xunit-to-xunit-v3 14/16 87.5%
❔ dotnet-test agent.test-quality-auditor — error
❔ dotnet-test agent.testability-migration — error
✅ dotnet-test assertion-quality 22/22 100%
✅ dotnet-test code-testing-agent 5/5 100%
✅ dotnet-test crap-score 6/6 100%
✅ dotnet-test detect-static-dependencies 15/15 100%
✅ dotnet-test generate-testability-wrappers 22/22 100%
✅ dotnet-test migrate-static-to-wrapper 21/21 100%
✅ dotnet-test mtp-hot-reload 16/16 100%
✅ dotnet-test run-tests 16/16 100%
✅ dotnet-test test-anti-patterns 21/21 100%
✅ dotnet-test test-gap-analysis 24/24 100%
✅ dotnet-test test-smell-detection 26/26 100%
✅ dotnet-test test-tagging 28/28 100%
✅ dotnet-test writing-mstest-tests 45/45 100%
⚠️ dotnet-upgrade dotnet-aot-compat 6/10 60%
✅ dotnet-upgrade migrate-dotnet10-to-dotnet11 6/6 100%
✅ dotnet-upgrade migrate-dotnet8-to-dotnet9 6/6 100%
✅ dotnet-upgrade migrate-dotnet9-to-dotnet10 6/6 100%
⚠️ dotnet-upgrade migrate-nullable-references 20/27 74.1%
✅ dotnet-upgrade thread-abort-migration 21/22 95.5%
Uncovered: dotnet-advanced/csharp-scripts
  • [Validation] dotnet --version reports 10.0 or later (or fallback path is used) (line 274)
  • [Validation] The app compiles without errors (can be checked explicitly with dotnet build <file>.cs) (line 276)
  • [Validation] App files and cached artifacts are cleaned up after the session (line 279)
  • [Pitfall] #:package without a version (line 286)
  • [Pitfall] #:property with wrong syntax (line 287)
  • [Pitfall] Directives placed after C# code (line 288)
  • [Pitfall] Reflection-based JSON serialization fails (line 293)
  • [WorkflowStep] Step 5: Clean up (line 199)
  • [CodePattern] [MSBuild] (line 93)
Uncovered: dotnet-advanced/dotnet-pinvoke
  • [Validation] Calling convention specified if targeting Windows x86; omitted otherwise (line 424)
  • [Validation] String encoding is explicit — no reliance on defaults or CharSet.Auto (line 425)
  • [Validation] Memory ownership is documented and matched (who allocates, who frees, with what) (line 426)
  • [Validation] SafeHandle used for all native handles (no raw IntPtr escaping the interop layer) (line 427)
  • [Validation] Delegates passed as callbacks are rooted to prevent GC collection (line 428)
  • [Validation] SetLastError/SetLastPInvokeError set for APIs that use OS error codes (line 429)
  • [Validation] Struct layout matches native (packing, alignment, field order) (line 430)
  • [Validation] CLong/CULong used for C long/unsigned long in cross-platform code (line 431)
  • [Validation] If using CLong/CULong with LibraryImport, [assembly: DisableRuntimeMarshalling] is applied (line 432)
  • [Validation] No bool without explicit MarshalAs — always specify UnmanagedType.Bool (4-byte) or UnmanagedType.U1 (1-byte) to ensure normalization across the language boundary. (line 433)
  • [WorkflowStep] Step 5: Establish Memory Ownership (line 168)
  • [WorkflowStep] Step 6: Use SafeHandle for Native Handles (line 224)
  • [WorkflowStep] Step 7: Handle Errors (line 261)
  • [CodePattern] [DllImport] (line 93)
  • [CodePattern] [UnmanagedCallersOnly] (line 281)
  • [CodePattern] [UnmanagedCallConv] (line 111)
  • [CodePattern] sealed (line 228)
  • [CodePattern] [LibraryImport] (line 101)
  • [CodePattern] [Out] (line 144)
  • [CodePattern] [256] (line 176)
  • [CodePattern] [UnmanagedFunctionPointer] (line 300)
  • [CodePattern] [MarshalAs] (line 144)
Uncovered: dotnet-ai/mcp-csharp-create
  • [Validation] Project builds with no errors (dotnet build) (line 232)
  • [Validation] HTTP: app.MapMcp() is called in Program.cs (line 237)
  • [Validation] Server starts successfully with dotnet run (line 238)
  • [Pitfall] WithToolsFromAssembly() fails in AOT (line 247)
  • [WorkflowStep] Step 5: Add prompts and resources (optional) (line 151)
  • [CodePattern] [Description] (line 90)
  • [CodePattern] CancellationToken (line 90)
Uncovered: dotnet-ai/mcp-csharp-debug
  • [Validation] Breakpoints hit when debugging in IDE (line 185)
  • [Pitfall] HTTP server returns 404 at MCP endpoint (line 195)
Uncovered: dotnet-ai/mcp-csharp-publish
  • [Validation] NuGet: Package installs and runs via dnx PackageId@version (line 243)
  • [Validation] Azure: Server is reachable and tools respond (line 245)
  • [Validation] MCP Registry: Server appears at registry.modelcontextprotocol.io (line 246)
  • [Validation] MCP client can connect and call tools on the deployed server (line 247)
  • [Pitfall] Docker container exits immediately (line 255)
Uncovered: dotnet-ai/mcp-csharp-test
  • [Validation] All tests pass: dotnet test (line 165)
  • [Validation] Tests run in CI without manual setup (line 166)
  • [Pitfall] Full test suite runs are slow (line 176)
  • [WorkflowStep] Step 4: Run tests (line 138)
  • [CodePattern] [Theory] (line 57)
  • [CodePattern] [InlineData] (line 57)
  • [CodePattern] [Fact] (line 57)
Uncovered: dotnet-ai/technology-selection
  • [Validation] Non-deterministic outputs have validation and fallback paths (line 319)
  • [Validation] dotnet build -c Release -warnaserror completes cleanly (line 320)
  • [Pitfall] Over-engineering with LLMs (line 348)
  • [Pitfall] Cold start latency on ML.NET models (line 354)
Uncovered: dotnet-aspnetcore/configuring-opentelemetry-dotnet
  • [Validation] Traces appear in the observability backend (Jaeger, Aspire dashboard, etc.) (line 272)
  • [Validation] HTTP requests automatically create spans with correct verb, URL, status code (line 273)
  • [Validation] Health check endpoints are filtered from traces (line 277)
  • [Validation] Exception details appear on error spans (line 278)
  • [Pitfall] Missing HTTP client spans (line 286)
  • [Pitfall] High cardinality tags (line 287)
  • [CodePattern] readonly (line 124)
  • [CodePattern] [key] (line 241)
Uncovered: dotnet-aspnetcore/minimal-api-file-upload
  • [WorkflowStep] Step 1: CRITICAL — Understand IFormFile Binding in Minimal APIs (line 29)
  • [WorkflowStep] Step 5: CRITICAL — Streaming Large Files Without Buffering (line 170)
  • [CodePattern] [RequestSizeLimit] (line 54)
  • [CodePattern] [FromForm] (line 31)
Uncovered: dotnet-blazor/author-component
  • [CodePattern] [Parameter] (line 31)
Uncovered: dotnet-blazor/collect-user-input
  • [CodePattern] [SupplyParameterFromForm] (line 31)
  • [CodePattern] [Required] (line 135)
  • [CodePattern] [Range] (line 135)
  • [CodePattern] [CascadingParameter] (line 162)
Uncovered: dotnet-blazor/configure-auth
  • [CodePattern] [ExcludeFromInteractiveRouting] (line 152)
  • [CodePattern] [CascadingParameter] (line 51)
  • [CodePattern] [Authorize] (line 101)
Uncovered: dotnet-blazor/coordinate-components
  • [CodePattern] readonly (line 137)
  • [CodePattern] [CascadingParameter] (line 63)
Uncovered: dotnet-blazor/fetch-and-send-data
  • [CodePattern] [PersistentState] (line 84)
  • [CodePattern] [SupplyParameterFromQuery] (line 159)
  • [CodePattern] [Parameter] (line 159)
  • [CodePattern] [StreamRendering] (line 74)
Uncovered: dotnet-blazor/plan-ui-change
  • [CodePattern] [Parameter] (line 64)
Uncovered: dotnet-blazor/support-prerendering
  • [CodePattern] [ExcludeFromInteractiveRouting] (line 148)
  • [CodePattern] [CascadingParameter] (line 159)
  • [CodePattern] [PersistentState] (line 39)
Uncovered: dotnet-blazor/use-js-interop
  • [CodePattern] readonly (line 118)
  • [CodePattern] sealed (line 118)
Uncovered: dotnet-data/optimizing-ef-core-queries
  • [Validation] SQL logging shows expected number of queries (no N+1) (line 164)
  • [Validation] Read-only queries use AsNoTracking() (line 165)
  • [Validation] Hot-path queries use compiled queries (line 166)
  • [Validation] No client-side evaluation warnings in logs (line 167)
  • [Validation] Include/split strategy matches data shape (line 168)
  • [Pitfall] Global query filters forgotten in perf analysis (line 175)
  • [Pitfall] DbContext kept alive too long (line 176)
  • [Pitfall] String interpolation in FromSqlRaw (line 178)
  • [WorkflowStep] Step 1: Enable query logging to see the actual SQL (line 31)
  • [WorkflowStep] Step 4: Use compiled queries for hot paths (line 120)
  • [WorkflowStep] Step 5: Avoid common query traps (line 134)
  • [WorkflowStep] Step 6: Use raw SQL or FromSql for complex queries (line 144)
  • [CodePattern] readonly (line 122)
Uncovered: dotnet-diag/analyzing-dotnet-performance
  • [Validation] All critical patterns were checked (from reference files or inline recipes) (line 178)
  • [Validation] Topic-specific recipes run only when matching signals detected (line 179)
  • [Validation] Each finding includes a concrete code fix (line 180)
  • [Validation] Scan execution checklist is complete (all recipes run) (line 181)
  • [Validation] Summary table included at end (line 182)
  • [Pitfall] Suggesting ConfigureAwait(false) in app code (line 191)
  • [Pitfall] Recommending ValueTask everywhere (line 192)
  • [Pitfall] Flagging new HttpClient() in DI services (line 193)
  • [Pitfall] Suggesting CollectionsMarshal.AsSpan broadly (line 195)
Uncovered: dotnet-diag/clr-activation-debugging
  • [Validation] The entry point for each problematic activation was identified (line 289)
  • [Validation] SEM_FAILCRITICALERRORS state was noted for FOD-related issues (line 292)
  • [Validation] Multiple activations within a single log were individually traced (line 293)
Uncovered: dotnet-diag/dotnet-trace-collect
  • [Validation] The recommended tool is compatible with the developer's runtime, OS, and deployment topology (line 235)
  • [Validation] The output file is generated in the expected location (line 237)
Uncovered: dotnet-experimental/exp-mock-usage-analysis
  • [Validation] Production code was read and execution paths were traced (not just test code reviewed) (line 86)
Uncovered: dotnet-experimental/exp-test-maintainability
  • [Validation] Every finding shows the actual duplicated code, not just a description (line 188)
  • [Validation] Every suggestion includes a concrete before/after example (line 189)
  • [Validation] Findings are filtered through the 3+ occurrence threshold (line 190)
  • [Validation] Simple constructors are not flagged (line 191)
  • [Validation] If tests are clean, the report says so upfront (line 193)
  • [Pitfall] Suggesting extraction for 2 occurrences (line 200)
  • [Pitfall] Flagging simple new X() as boilerplate (line 203)
  • [CodePattern] [TestMethod] (line 67)
Uncovered: dotnet-maui/maui-collectionview
  • [Pitfall] EmptyView doesn't render correctly (line 329)
  • [Pitfall] Poor scroll performance (line 330)
Uncovered: dotnet-maui/maui-data-binding
  • [Pitfall] Specifying redundant Mode=OneWay / Mode=TwoWay (line 375)
  • [Pitfall] Mutating ObservableCollection off the UI thread (line 377)
  • [Pitfall] Complex converter chains in hot paths (line 378)
  • [Pitfall] Binding to non-public properties (line 380)
Uncovered: dotnet-maui/maui-dependency-injection
  • [CodePattern] readonly (line 102)
Uncovered: dotnet-maui/maui-safe-area
  • [CodePattern] readonly (line 65)
  • [CodePattern] [Flags] (line 48)
Uncovered: dotnet-maui/maui-theming
  • [CodePattern] [Activity] (line 226)
Uncovered: dotnet-msbuild/check-bin-obj-clash
  • [WorkflowStep] Step 2: Get an overview and list projects (line 48)
  • [WorkflowStep] Step 5: Check for double writes (line 62)
  • [WorkflowStep] Step 2: Replay the Binary Log to Text (line 78)
  • [WorkflowStep] Step 3: List All Projects (line 84)
Uncovered: dotnet-msbuild/directory-build-organization
  • [CodePattern] [MSBuild] (line 122)
Uncovered: dotnet-msbuild/msbuild-modernization
  • [WorkflowStep] Step 6: Remove Unnecessary Boilerplate (line 217)
Uncovered: dotnet-msbuild/msbuild-server
  • [Validation] MSBUILDUSESERVER=1 is set in the shell (line 59)
  • [Validation] Second sequential build is faster than the first (line 60)
Uncovered: dotnet-msbuild/resolve-project-references
  • [Validation] ResolveProjectReferences was not set as the optimization target (line 64)
Uncovered: dotnet-template-engine/template-authoring
  • [Validation] Template identity and shortName are unique and meaningful (line 102)
  • [Validation] All parameters have descriptions and appropriate defaults (line 103)
  • [Validation] Template can be installed, dry-run, and instantiated successfully (line 104)
  • [Validation] Created projects build cleanly with dotnet build (line 105)
  • [Validation] Conditional content produces correct output for all parameter combinations (line 106)
  • [Pitfall] Identity format issues (line 112)
  • [Pitfall] Missing parameter descriptions (line 114)
  • [Pitfall] Not testing all parameter combinations (line 115)
  • [Pitfall] Not setting classifications (line 117)
  • [WorkflowStep] Step 3: Refine the template (line 80)
  • [WorkflowStep] Step 4: Test the template locally (line 90)
Uncovered: dotnet-template-engine/template-comparison
  • [Validation] Differences relevant to the user's scenario are called out explicitly (line 90)
  • [WorkflowStep] Step 3: Recommend (line 81)
Uncovered: dotnet-template-engine/template-discovery
  • [Validation] User understands what the template produces before proceeding to creation (line 145)
  • [Pitfall] A dotnet new call fails with a "mutex"/"persistence" error and you return nothing (line 154)
Uncovered: dotnet-template-engine/template-instantiation
  • [Validation] If CPM is active, .csproj has no version attributes and Directory.Packages.props has matching entries (line 128)
  • [Pitfall] Creating projects without specifying the framework (line 137)
  • [WorkflowStep] Step 2: Analyze the workspace (line 50)
  • [WorkflowStep] Step 3: Preview the creation (line 59)
  • [WorkflowStep] Step 6: Template package management (line 109)
Uncovered: dotnet-template-engine/template-smart-defaults
  • [Validation] No parameter the user set explicitly was overridden (line 62)
  • [Validation] Only unset parameters were filled (line 63)
Uncovered: dotnet-template-engine/template-validation
  • [Pitfall] ShortName = "list" or "search" (line 150)
  • [Pitfall] Invalid datatype value (line 153)
  • [Pitfall] Parameter prefix collision (Auth vs AuthMode) (line 155)
  • [Pitfall] Source condition without parentheses (line 156)
  • [WorkflowStep] Step 1: Locate the template.json (line 124)
Uncovered: dotnet-test-migration/migrate-mstest-v1v2-to-v3
  • [Validation] Project builds with zero errors (line 185)
  • [Validation] All tests pass (dotnet test) -- compare pass/fail counts to pre-migration baseline (line 186)
  • [CodePattern] Assert.AreNotEqual (line 144)
Uncovered: dotnet-test-migration/migrate-mstest-v3-to-v4
  • [CodePattern] [TestMethod] (line 265)
  • [CodePattern] [Timeout] (line 212)
  • [CodePattern] [TestMethodAttribute] (line 172)
Uncovered: dotnet-test-migration/migrate-vstest-to-mtp
  • [Validation] dotnet build completes with zero errors (line 361)
  • [Validation] Test executable runs directly (e.g., ./bin/Debug/net8.0/MyTests.exe) (line 363)
  • [Validation] No vstest.console.exe invocations remain in CI scripts (line 366)
  • [CodePattern] [trait] (line 252)
Uncovered: dotnet-test-migration/migrate-xunit-to-mstest
  • [Validation] using Xunit; and using Xunit.Abstractions; removed (line 521)
  • [Validation] xunit.runner.json removed; equivalent config in .runsettings / [assembly: Parallelize] (line 522)
  • [Validation] Project builds with zero errors (line 524)
  • [CodePattern] Assert.False (line 347)
  • [CodePattern] [Fact] (line 308)
  • [CodePattern] [DoNotParallelize] (line 434)
  • [CodePattern] [TestClass] (line 277)
  • [CodePattern] [ClassInitialize] (line 277)
  • [CodePattern] readonly (line 262)
  • [CodePattern] sealed (line 277)
  • [CodePattern] [ClassCleanup] (line 277)
  • [CodePattern] Parallelize (line 405)
  • [CodePattern] DoNotParallelize (line 434)
  • [CodePattern] [TestMethod] (line 320)
  • [CodePattern] Assert.IsFalse (line 347)
Uncovered: dotnet-test-migration/migrate-xunit-to-xunit-v3
  • [WorkflowStep] Step 13: Build and verify (line 199)
  • [CodePattern] sealed (line 118)
Uncovered: dotnet-upgrade/dotnet-aot-compat
  • [CodePattern] [MSBuild] (line 67)
  • [CodePattern] [DynamicallyAccessedMembers] (line 119)
  • [CodePattern] [JsonSerializerContext] (line 169)
  • [CodePattern] [RequiresUnreferencedCode] (line 195)
Uncovered: dotnet-upgrade/migrate-nullable-references
  • [Validation] Project file(s) contain <Nullable>enable</Nullable> (or #nullable enable per-file for file-by-file strategy) (line 235)
  • [Validation] <WarningsAsErrors>nullable</WarningsAsErrors> added to project file to prevent regressions (line 237)
  • [Validation] No #nullable disable directives remain unless justified with a comment (line 239)
  • [Validation] Public API signatures accurately reflect null contracts (line 241)
  • [Validation] For public libraries: breaking changes documented in nullable-breaking-changes.md and reviewed by the user (line 242)
  • [Pitfall] Multi-target projects and older TFMs (line 265)
  • [Pitfall] Warnings reappear after upgrading a dependency (line 266)
Uncovered: dotnet-upgrade/thread-abort-migration
  • [Validation] No SYSLIB0006 pragma suppressions remain (line 117)

@AbhitejJohn AbhitejJohn marked this pull request as ready for review July 2, 2026 22:09
Copilot AI review requested due to automatic review settings July 2, 2026 22:09
Copilot AI reviewed Jul 2, 2026
View reviewed changes

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR updates the repository’s informational “skill-vs-baseline” Vally shadow harness to align with Vally 0.7.0 by switching from per-eval runs + a custom weighted score to a single vally experiment run plus vally compare-based scoring, and by removing the deprecated pairwise grader from eval specs.

Changes:

  • Replace the old baseline/skilled per-eval execution model with a single dotnet-skills.experiment.yaml experiment run, scoped via --eval-filter, then split results per eval and score with vally compare.
  • Update the adapter (eng/vally-adapter/adapt.mjs) to group outcomes by experiment.evalFile, run vally compare per skill, and emit per-skill results.json with credible-improvement pass criteria.
  • Update all affected eval.vally.yaml files to remove the pairwise grader (and adjust a few timeouts).
Show a summary per file
File Description
tests/dotnet11/system-text-json-net11/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-upgrade/thread-abort-migration/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-upgrade/migrate-nullable-references/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-upgrade/migrate-dotnet9-to-dotnet10/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-upgrade/migrate-dotnet8-to-dotnet9/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-upgrade/migrate-dotnet10-to-dotnet11/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-upgrade/dotnet-aot-compat/eval.vally.yaml Remove deprecated pairwise grader; convert timeout to seconds.
tests/dotnet-test/writing-mstest-tests/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/test-tagging/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/test-smell-detection/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/test-gap-analysis/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/test-anti-patterns/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/run-tests/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/mtp-hot-reload/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/migrate-static-to-wrapper/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/generate-testability-wrappers/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/detect-static-dependencies/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/crap-score/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/coverage-analysis/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/code-testing-agent/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/assertion-quality/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/agent.testability-migration/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test/agent.test-quality-auditor/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test-migration/migrate-xunit-to-xunit-v3/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test-migration/migrate-xunit-to-mstest/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test-migration/migrate-vstest-to-mtp/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test-migration/migrate-mstest-v3-to-v4/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test-migration/migrate-mstest-v1v2-to-v3/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-test-migration/agent.test-migration/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-template-engine/template-validation/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-template-engine/template-smart-defaults/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-template-engine/template-instantiation/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-template-engine/template-discovery/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-template-engine/template-comparison/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-template-engine/template-authoring/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-nuget/convert-to-cpm/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/resolve-project-references/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/msbuild-server/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/msbuild-modernization/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/msbuild-antipatterns/eval.vally.yaml Remove deprecated pairwise grader; convert timeout to seconds.
tests/dotnet-msbuild/incremental-build/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/including-generated-files/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/eval-performance/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/directory-build-organization/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/check-bin-obj-clash/eval.vally.yaml Remove deprecated pairwise grader; convert timeout to seconds.
tests/dotnet-msbuild/build-perf-diagnostics/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/build-perf-baseline/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/build-parallelism/eval.vally.yaml Remove deprecated pairwise grader; convert timeout to seconds.
tests/dotnet-msbuild/binlog-generation/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/binlog-failure-analysis/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-msbuild/agent.msbuild/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-theming/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-shell-navigation/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-safe-area/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-dependency-injection/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-data-binding/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-collectionview/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/maui-app-lifecycle/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-maui/dotnet-maui-doctor/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-experimental/exp-test-maintainability/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-experimental/exp-simd-vectorization/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-experimental/exp-mock-usage-analysis/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/microbenchmarking/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/dump-collect/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/dotnet-trace-collect/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/clr-activation-debugging/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/apple-crash-symbolication/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/android-tombstone-symbolication/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-diag/analyzing-dotnet-performance/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-data/optimizing-ef-core-queries/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/use-js-interop/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/support-prerendering/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/plan-ui-change/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/fetch-and-send-data/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/create-blazor-project/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/coordinate-components/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/configure-auth/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/collect-user-input/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-blazor/author-component/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-aspnetcore/minimal-api-file-upload/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-aspnetcore/configuring-opentelemetry-dotnet/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-ai/technology-selection/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-ai/mcp-csharp-test/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-ai/mcp-csharp-publish/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-ai/mcp-csharp-debug/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-ai/mcp-csharp-create/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-advanced/nuget-trusted-publishing/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-advanced/dotnet-pinvoke/eval.vally.yaml Remove deprecated pairwise grader.
tests/dotnet-advanced/csharp-scripts/eval.vally.yaml Remove deprecated pairwise grader.
eng/vally-adapter/run-vally-evals.sh Rework local runner to use vally experiment run + adapter + compare.
eng/vally-adapter/adapt.mjs Split experiment output by eval file; run vally compare and emit per-skill verdicts.
dotnet-skills.experiment.yaml New canonical experiment definition (baseline vs skilled variants).
.vally.yaml Remove legacy suite-based Vally config in favor of experiment-driven runs.
.github/workflows/vally-evaluation.yml Update CI shadow workflow to run the experiment, adapt results, and summarize compare-based scoring.

Copilot's findings

Tip

Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

  • Files reviewed: 94/94 changed files
  • Comments generated: 2

Comment thread eng/vally-adapter/adapt.mjs
Comment thread eng/vally-adapter/adapt.mjs Outdated
@github-actions github-actions Bot added the waiting-on-author PR state label label Jul 2, 2026
@github-actions

github-actions Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

👋 @adityamandaleeka — this PR has 2 unresolved review thread(s). When you're ready, please address the feedback and push an update; the triage bot will pick up the next state automatically. (Add the no-stale label to silence further pings.)

@adityamandaleeka
adapt.mjs: give --output-root a real default and mark it optional
a2845b5 
Address PR review: set the default (vally-results) at the parseArgs option
level so the CLI contract matches the help text, mark it optional in the usage
banner, and drop the now-redundant ?? fallback.

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
@adityamandaleeka adityamandaleeka enabled auto-merge (squash) July 6, 2026 04:38
@AbhitejJohn

AbhitejJohn commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

/evaluate

@github-actions github-actions Bot added pr-state/ready-for-eval PR is mergeable and awaiting evaluation and removed waiting-on-author PR state label labels Jul 6, 2026
@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Skill Validation Results

Skill Scenario Quality Skills Loaded Overfit Verdict
microbenchmarking Investigate runtime upgrade performance impact 2.3/5 ⏰ → 3.3/5 ⏰ 🟢 ✅ microbenchmarking; tools: skill, create / ✅ microbenchmarking; tools: read_bash, skill, create ✅ 0.11 ✅ [1]
template-validation Validate template with multiple errors 4.3/5 → 4.7/5 🟢 ✅ template-validation; tools: skill ✅ 0.16 ✅ [2]
template-validation Validate correct template and suggest improvements 1.3/5 → 5.0/5 🟢 ✅ template-validation; tools: glob, skill ✅ 0.16 ✅
maui-safe-area Handle notch and status bar safe areas on iOS 1.7/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: skill, report_intent / ✅ maui-safe-area; tools: skill ✅ 0.08 ✅
maui-safe-area Edge-to-edge layout with SafeAreaEdges 1.3/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: report_intent, skill / ✅ maui-safe-area; tools: skill, report_intent ✅ 0.08 ✅ [3]
maui-safe-area Keyboard avoidance with safe area for chat UI 1.0/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: skill, report_intent ✅ 0.08 ✅
maui-safe-area Avoid deprecated UseSafeArea in new .NET 10 project 1.0/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: skill ✅ 0.08 ✅
eval-performance Analyze MSBuild evaluation performance issues 5.0/5 → 5.0/5 ✅ eval-performance; tools: skill ✅ 0.18 ❌
exp-mock-usage-analysis Detect unused and unreachable mock setups 4.0/5 → 4.7/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅
exp-mock-usage-analysis Detect redundant mock configurations duplicated across tests 3.0/5 → 4.0/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅
exp-mock-usage-analysis Detect mocking of stable framework types 3.0/5 → 5.0/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅
exp-mock-usage-analysis Analyze mock usage in NSubstitute tests 3.0/5 → 4.3/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅
exp-mock-usage-analysis Analyze mock usage in FakeItEasy tests 4.3/5 → 5.0/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅ [4]
exp-mock-usage-analysis Detect excessive mock configuration sprawl 3.0/5 → 3.3/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅ [5]
migrate-xunit-to-xunit-v3 Migrate basic xUnit.net v2 project to v3 2.7/5 → 5.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill / ✅ migrate-xunit-to-xunit-v3; tools: skill, glob, create ✅ 0.05 ✅
migrate-xunit-to-xunit-v3 Detect incompatible target framework and stop migration 1.0/5 → 1.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.05 ✅
migrate-xunit-to-xunit-v3 Convert async void test methods to async Task 4.3/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.05 ✅ [6]
migrate-xunit-to-xunit-v3 Convert string-based attribute constructors to typeof syntax 3.3/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, create, grep, read_bash / ✅ migrate-xunit-to-xunit-v3; tools: skill, create ✅ 0.05 ✅ [7]
migrate-xunit-to-xunit-v3 Update custom FactAttribute to include source information parameters 1.7/5 → 3.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.05 ✅
migrate-xunit-to-xunit-v3 Update BeforeAfterTestAttribute overrides with IXunitTest parameter 2.3/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill / ✅ migrate-xunit-to-xunit-v3; tools: skill, create, read_bash ✅ 0.05 ✅
migrate-xunit-to-xunit-v3 Migrate project with YTest.MTP.XUnit2 to xUnit.net v3 preserving MTP 3.0/5 → 4.3/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, read_bash ✅ 0.05 ✅ [8]
migrate-xunit-to-xunit-v3 Migrate Xunit.SkippableFact to xUnit.net v3 built-in skip APIs 1.0/5 → 1.0/5 ⚠️ NOT ACTIVATED / ✅ migrate-xunit-to-xunit-v3; tools: report_intent, skill, view, edit, create, bash ✅ 0.05 ❌ [9]
migrate-xunit-to-xunit-v3 Migrate xUnit v2 packages managed via Central Package Management 4.3/5 → 5.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, web_fetch, create, glob / ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.05 ✅ [10]
migrate-xunit-to-xunit-v3 Recognize project already on xUnit.net v3 — no migration needed 2.0/5 → 4.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.05 ✅
migrate-xunit-to-xunit-v3 Consolidate xunit.extensibility packages and remove xunit.abstractions 1.0/5 → 3.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, edit, create, bash / ✅ migrate-xunit-to-xunit-v3; tools: skill, edit, bash ✅ 0.05 ✅ [11]
migrate-xunit-to-xunit-v3 Update Xunit.Combinatorial and Xunit.StaFact companion packages 3.7/5 → 5.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill / ✅ migrate-xunit-to-xunit-v3; tools: skill, create ✅ 0.05 ✅
run-tests Run tests in a VSTest MSTest project 4.0/5 → 3.7/5 ⏰ 🔴 ✅ run-tests; tools: skill, bash / ⚠️ NOT ACTIVATED 🟡 0.22 ❌ [12]
run-tests Run tests with trx reporting on MTP project (SDK 9) 2.0/5 → 5.0/5 🟢 ✅ run-tests; tools: report_intent, skill, view 🟡 0.22 ✅
run-tests Run tests with blame-hang on MTP project (SDK 10) 3.0/5 → 4.0/5 🟢 ⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill 🟡 0.22 ✅ [13]
run-tests Run tests on a specific TFM with TRX in a multi-TFM MTP project (SDK 9) 5.0/5 → 5.0/5 ✅ run-tests; tools: skill 🟡 0.22 ❌ [14]
run-tests Filter MSTest tests by category on VSTest 5.0/5 → 2.0/5 ⏰ 🔴 ⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill, glob 🟡 0.22 ❌ [15]
run-tests Filter NUnit tests by class name on VSTest 3.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view, bash / ⚠️ NOT ACTIVATED 🟡 0.22 ✅ [16]
run-tests Filter xUnit v3 tests by class on MTP 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view 🟡 0.22 ✅ [17]
run-tests Filter xUnit v3 tests by trait on MTP 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ⚠️ NOT ACTIVATED 🟡 0.22 ❌ [18]
run-tests Filter xUnit v3 tests by class pattern and trait using query filter language 1.0/5 → 1.0/5 ⏰ ✅ run-tests; tools: report_intent, view, skill, bash / ⚠️ NOT ACTIVATED 🟡 0.22 ❌ [19]
run-tests Filter TUnit tests by class using treenode-filter 2.3/5 → 4.0/5 🟢 ⚠️ NOT ACTIVATED 🟡 0.22 ✅ [20]
run-tests Combine multiple filter criteria on VSTest MSTest 3.7/5 → 5.0/5 🟢 ✅ run-tests; tools: report_intent, skill, view, bash / ✅ run-tests; tools: report_intent, skill, view 🟡 0.22 ✅
run-tests MTP project on SDK 9 must use -- separator for args 1.0/5 → 3.7/5 🟢 ⚠️ NOT ACTIVATED 🟡 0.22 ✅ [21]
run-tests MTP project on SDK 10 passes args directly 2.0/5 → 4.7/5 🟢 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.22 ❌ [22]
run-tests Detect test platform from Directory.Build.props 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.22 ✅ [23]
run-tests Negative test: do not use MTP syntax for a VSTest project 4.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ⚠️ NOT ACTIVATED 🟡 0.22 ✅ [24]
detect-static-dependencies Identify static dependencies in a multi-class project 1.0/5 ⏰ → 1.0/5 ⏰ ✅ detect-static-dependencies; tools: skill, report_intent, view / ✅ detect-static-dependencies; tools: skill, report_intent, view, glob ✅ 0.11 ✅
detect-static-dependencies Detect time-related statics and recommend TimeProvider 2.3/5 ⏰ → 1.7/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: skill ✅ 0.11 ❌ [25]
detect-static-dependencies Decline scan for non-C# project 2.0/5 ⏰ → 1.3/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill / ℹ️ not activated (expected) ✅ 0.11 ❌
detect-static-dependencies Verify structured report includes file count, categories, and top patterns 4.7/5 → 5.0/5 🟢 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: skill ✅ 0.11 ✅ [26]
detect-static-dependencies Exclude obj and bin directories from the scan 5.0/5 → 2.3/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: skill ✅ 0.11 ❌
detect-static-dependencies Detect statics inside lambda expressions and LINQ queries 4.3/5 → 3.0/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill / ✅ detect-static-dependencies; tools: skill, glob ✅ 0.11 ❌
maui-app-lifecycle Save and restore state on background 2.0/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: skill / ✅ maui-app-lifecycle; tools: report_intent, skill ✅ 0.12 ✅
maui-app-lifecycle Window lifecycle event subscription 4.0/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: skill / ✅ maui-app-lifecycle; tools: report_intent, skill ✅ 0.12 ✅ [27]
maui-app-lifecycle Platform-specific lifecycle mapping 4.0/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: skill ✅ 0.12 ✅
maui-app-lifecycle Avoid legacy Xamarin.Forms lifecycle methods 4.0/5 → 4.0/5 ✅ maui-app-lifecycle; tools: skill ✅ 0.12 ❌ [28]
crap-score Calculate CRAP score for a single method with partial coverage 3.3/5 → 4.3/5 🟢 ✅ crap-score; tools: skill, glob ✅ 0.07 ✅ [29]
crap-score Identify riskiest methods across a file 4.3/5 → 5.0/5 🟢 ✅ crap-score; tools: skill, glob / ✅ crap-score; tools: skill ✅ 0.07 ✅
crap-score Generate coverage then compute CRAP score 4.0/5 → 4.0/5 ✅ crap-score; tools: skill ✅ 0.07 ✅
migrate-mstest-v3-to-v4 Migrate custom TestMethodAttribute from Execute to ExecuteAsync 2.7/5 ⏰ → 4.0/5 ⏰ 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅ [30]
migrate-mstest-v3-to-v4 Replace ExpectedExceptionAttribute with Assert.ThrowsExactly 3.3/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill, bash ✅ 0.08 ❌ [31]
migrate-mstest-v3-to-v4 Fix multiple v4 breaking changes: Assert, ClassCleanup, TestContext, Timeout 2.0/5 ⏰ → 2.7/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Handle net6.0 target framework dropped in MSTest v4 3.7/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: report_intent, skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Fix TestMethodAttribute CallerInfo constructor breaking change 1.3/5 ⏰ → 4.7/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill, bash ✅ 0.08 ❌ [32]
migrate-mstest-v3-to-v4 Understand behavioral changes after MSTest v4 upgrade 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Handle MSTest.Sdk and MTP changes in v4 2.0/5 → 4.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ❌ [33]
migrate-mstest-v3-to-v4 Full MSTest v3 to v4 migration with multiple breaking changes 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Migrate MSTest.Sdk v3 project using ManagedType and TestTimeout 3.0/5 → 4.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅ [34]
migrate-mstest-v3-to-v4 Verified MSTest v3 to v4 package update with build and test 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Fix sealed custom TestMethodAttribute with Timeout changes 3.0/5 → 4.7/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Fix TestMethodAttribute and TestMethod display name constructor 5.0/5 → 5.0/5 ✅ migrate-mstest-v3-to-v4; tools: skill, bash ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Fix Assert.IsInstanceOfType out parameter removal 5.0/5 → 5.0/5 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ❌ [35]
migrate-mstest-v3-to-v4 Address TreatDiscoveryWarningsAsErrors and behavioral changes 2.0/5 → 3.3/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ✅
migrate-mstest-v3-to-v4 Correctly identify MSTest v3 project and recommend v4 migration 4.7/5 → 5.0/5 🟢 ✅ migrate-mstest-v3-to-v4; tools: skill ✅ 0.08 ❌ [36]
exp-simd-vectorization Optimize manual min/max with TensorPrimitives 1.0/5 ⏰ → 2.0/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, glob, create, report_intent, view / ✅ exp-simd-vectorization; tools: skill, report_intent, view, glob ✅ 0.17 ❌ [37]
exp-simd-vectorization Optimize manual product with TensorPrimitives 1.0/5 ⏰ → 3.0/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, edit, glob, create / ✅ exp-simd-vectorization; tools: skill, edit, glob, create, bash ✅ 0.17 ✅ [38]
exp-simd-vectorization No optimization opportunity — dictionary-based lookup service 1.7/5 ⏰ → 5.0/5 🟢 ⚠️ NOT ACTIVATED / ✅ exp-simd-vectorization; tools: skill ✅ 0.17 ✅ [39]
exp-simd-vectorization Optimize int array conditional increment with SIMD 3.7/5 → 3.7/5 ✅ exp-simd-vectorization; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.17 ❌ [40]
exp-simd-vectorization Optimize byte buffer bit reversal with SIMD 3.0/5 ⏰ → 3.0/5 ⏰ ✅ exp-simd-vectorization; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.17 ❌ [41]
incremental-build Analyze incremental build issues 3.0/5 → 3.0/5 ⚠️ NOT ACTIVATED ✅ 0.13 ❌ [42]
migrate-xunit-to-mstest Migrate basic xUnit v2 project to MSTest v4 preserving VSTest 4.0/5 → 4.7/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ✅
migrate-xunit-to-mstest Migrate basic xUnit v3 project to MSTest v4 preserving VSTest 5.0/5 → 4.7/5 🔴 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ❌
migrate-xunit-to-mstest Stop when target framework is unsupported by MSTest v4 2.0/5 → 2.0/5 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ✅
migrate-xunit-to-mstest Convert IClassFixture to ClassInitialize 4.0/5 → 4.7/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ✅ [43]
migrate-xunit-to-mstest Handle ICollectionFixture explicitly (do not silently widen scope) 4.0/5 → 4.3/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ✅ [44]
migrate-xunit-to-mstest Convert ITestOutputHelper to TestContext 4.7/5 → 4.7/5 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ❌ [45]
migrate-xunit-to-mstest Map exception assertions correctly (xUnit Throws -> MSTest ThrowsExactly) 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ❌ [46]
migrate-xunit-to-mstest Convert MemberData and TheoryData to DynamicData 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ❌ [47]
migrate-xunit-to-mstest Convert Skip, Trait, and Timeout 4.0/5 → 4.0/5 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, glob, create ✅ 0.08 ❌ [48]
migrate-xunit-to-mstest Preserve xUnit parallelization default with [assembly: Parallelize] 3.3/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ✅
migrate-xunit-to-mstest Convert xUnit v3 TestContext.Current.CancellationToken 3.7/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ✅ [49]
migrate-xunit-to-mstest Recognize project already on MSTest 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ❌ [50]
migrate-dotnet8-to-dotnet9 App with empty environment variables, ZIP encoding, and keyed DI services 3.0/5 → 4.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep, bash ✅ 0.08 ❌ [51]
migrate-dotnet8-to-dotnet9 C# 13 compiler breaking changes — InlineArray on record, iterator safe context, collection expressions 3.0/5 → 4.7/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: report_intent, skill, view / ✅ migrate-dotnet8-to-dotnet9; tools: skill, report_intent, view ✅ 0.08 ✅ [52]
migrate-dotnet8-to-dotnet9 ASP.NET Core app with DI validation, forwarded headers, and HttpClientFactory casting 2.5/5 → 2.0/5 ⏰ 🔴 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.08 ❌
migrate-dotnet8-to-dotnet9 EF Core app with migration patterns and Cosmos DB discriminator 3.0/5 → 4.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅
migrate-dotnet8-to-dotnet9 EF Core Cosmos DB app with existing documents and composite id format 2.0/5 ⏰ → 2.0/5 ⏰ ✅ migrate-dotnet8-to-dotnet9; tools: skill, create ✅ 0.08 ✅
migrate-dotnet8-to-dotnet9 App with JsonDocument null deserialization and BinaryFormatter fallback 4.3/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep ✅ 0.08 ✅ [53]
migrate-dotnet8-to-dotnet9 CI pipeline with Terminal Logger parsing and version constraints 2.0/5 → 2.7/5 🟢 ℹ️ not activated (expected) / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ❌ [54]
migrate-dotnet8-to-dotnet9 WinForms app with custom UserControls and PictureBox URL loading 3.3/5 → 4.3/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash, create, glob / ✅ migrate-dotnet8-to-dotnet9; tools: skill, create, bash ✅ 0.08 ✅
migrate-dotnet8-to-dotnet9 Containerized app with zlib dependency and runtime configuration 3.3/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅ [55]
migrate-dotnet8-to-dotnet9 EF Core Cosmos DB app with discriminator and sync I/O 3.0/5 → 4.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅
migrate-dotnet8-to-dotnet9 Library with String.Trim span overload, keyed services, and InlineArray 5.0/5 → 4.3/5 🔴 ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep ✅ 0.08 ❌ [56]
migrate-dotnet8-to-dotnet9 Containerized app with env var precedence reversal and zlib removal 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅
convert-to-cpm Decline CPM conversion for packages.config project 1.0/5 ⏰ → 3.7/5 🟢 ✅ convert-to-cpm; tools: skill 🟡 0.30 ✅ [57]
convert-to-cpm Recommend CPM when updating packages with version conflicts 2.0/5 → 3.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash, create 🟡 0.30 ✅
convert-to-cpm Recommend CPM when updating packages in a complex repository 2.0/5 → 3.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash, create / ✅ convert-to-cpm; tools: skill, create 🟡 0.30 ✅
convert-to-cpm Convert single project to CPM 2.0/5 → 4.5/5 🟢 ✅ convert-to-cpm; tools: skill, bash 🟡 0.30 ✅
convert-to-cpm Convert multi-project solution to CPM 2.5/5 → 4.5/5 🟢 ✅ convert-to-cpm; tools: skill, bash 🟡 0.30 ✅
convert-to-cpm Convert solution with MSBuild property versions to CPM 3.0/5 → 4.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash / ✅ convert-to-cpm; tools: skill, bash, glob 🟡 0.30 ✅
convert-to-cpm Convert solution with version conflicts to CPM 3.0/5 → 4.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash 🟡 0.30 ✅
convert-to-cpm Convert complex repository with multiple CPM challenges 3.0/5 → 4.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash 🟡 0.30 ✅
thread-abort-migration Worker thread with abort-based cancellation 5.0/5 → 5.0/5 ✅ thread-abort-migration; tools: skill, report_intent, bash ✅ 0.15 ❌ [58]
thread-abort-migration Timeout enforcement via Thread.Abort 4.3/5 → 5.0/5 🟢 ✅ thread-abort-migration; tools: skill ✅ 0.15 ✅ [59]
thread-abort-migration Blocking WaitHandle with Thread.Interrupt 4.0/5 → 4.7/5 🟢 ✅ thread-abort-migration; tools: skill / ✅ thread-abort-migration; tools: report_intent, skill ✅ 0.15 ✅ [60]
thread-abort-migration ASP.NET Response.End and Response.Redirect with Thread.Abort 4.0/5 → 5.0/5 🟢 ✅ thread-abort-migration; tools: skill ✅ 0.15 ✅ [61]
thread-abort-migration Thread.Join and Thread.Sleep only — should not migrate 3.7/5 → 5.0/5 🟢 ✅ thread-abort-migration; tools: skill / ✅ thread-abort-migration; tools: report_intent, skill ✅ 0.15 ✅ [62]
coverage-analysis Project-wide coverage analysis with existing Cobertura data 2.7/5 → 4.3/5 🟢 ✅ coverage-analysis; tools: skill, bash, create / ✅ coverage-analysis; tools: skill, bash, create, read_bash, stop_bash ✅ 0.10 ✅
coverage-analysis Run coverage from scratch without existing data 3.7/5 → 5.0/5 🟢 ✅ coverage-analysis; tools: skill, create / ✅ coverage-analysis; tools: skill, create, glob ✅ 0.10 ✅
coverage-analysis Coverage plateau diagnosis 3.0/5 → 4.7/5 🟢 ✅ coverage-analysis; tools: skill, bash, create, read_bash, stop_bash / ✅ coverage-analysis; tools: skill, bash, create ✅ 0.10 ✅
template-comparison Compare webapi vs webapp side by side 4.0/5 → 3.0/5 ⏰ 🔴 ✅ template-comparison; tools: skill 🟡 0.41 ✅ [63]
template-comparison Choose between blazor and blazorwasm 4.0/5 → 4.3/5 🟢 ✅ template-comparison; tools: skill 🟡 0.41 ✅ [64]
template-comparison Decide which template fits a background processing scenario 3.0/5 → 4.0/5 🟢 ✅ template-comparison; tools: skill 🟡 0.41 ✅
maui-dependency-injection Register services with correct lifetimes in MauiProgram.cs 4.7/5 → 5.0/5 🟢 ✅ maui-dependency-injection; tools: report_intent, skill / ✅ maui-dependency-injection; tools: skill ✅ 0.10 ❌ [65]
maui-dependency-injection Shell navigation auto-resolves DI-registered pages 5.0/5 → 5.0/5 ✅ maui-dependency-injection; tools: report_intent, skill / ⚠️ NOT ACTIVATED ✅ 0.10 ❌ [66]
maui-dependency-injection Platform-specific service registration with fallback 3.0/5 → 5.0/5 🟢 ✅ maui-dependency-injection; tools: report_intent, skill / ✅ maui-dependency-injection; tools: skill, report_intent ✅ 0.10 ✅
maui-dependency-injection Avoid AddScoped pitfall in MAUI 5.0/5 → 3.7/5 ⏰ 🔴 ✅ maui-dependency-injection; tools: report_intent, skill / ✅ maui-dependency-injection; tools: skill, report_intent ✅ 0.10 ❌ [67]
template-discovery Find template for web API project 2.3/5 → 4.0/5 🟢 ✅ template-discovery; tools: report_intent, skill, bash ✅ 0.19 ✅
template-discovery Inspect template parameters and compare choices 2.0/5 → 4.0/5 🟢 ✅ template-discovery; tools: skill, bash / ⚠️ NOT ACTIVATED ✅ 0.19 ✅
template-discovery Search NuGet for specialized template 4.0/5 → 4.0/5 ✅ template-discovery; tools: skill ✅ 0.19 ✅
template-discovery Resolve ambiguous project intent to multiple candidates 4.0/5 → 4.0/5 ✅ template-discovery; tools: skill ✅ 0.19 ✅
template-discovery Preview project creation with dry run 3.0/5 → 4.0/5 🟢 ✅ template-discovery; tools: skill ✅ 0.19 ✅ [68]
test-anti-patterns Detect mixed severity anti-patterns in repository service tests 5.0/5 → 5.0/5 ✅ test-anti-patterns; tools: skill, glob ✅ 0.20 ❌ [69]
test-anti-patterns Detect flakiness indicators and test coupling 5.0/5 → 5.0/5 ✅ test-anti-patterns; tools: skill, glob ✅ 0.20 ❌ [70]
test-anti-patterns Detect duplicated tests and magic values 4.0/5 → 5.0/5 🟢 ✅ test-anti-patterns; tools: skill, glob / ✅ test-anti-patterns; tools: skill ✅ 0.20 ✅ [71]
test-anti-patterns Recognize well-written tests without inventing false positives 4.3/5 → 4.3/5 ✅ test-anti-patterns; tools: skill, glob ✅ 0.20 ❌ [72]
test-anti-patterns Detect coverage-touching pattern across a service facade 5.0/5 → 4.7/5 🔴 ✅ test-anti-patterns; tools: skill, glob / ✅ test-anti-patterns; tools: skill ✅ 0.20 ❌ [73]
test-anti-patterns Detect self-referential assertions in round-trip and identity tests 4.3/5 → 4.3/5 ✅ test-anti-patterns; tools: skill ✅ 0.20 ✅ [74]
test-anti-patterns Polyglot: detect anti-patterns in a Python pytest suite 4.7/5 → 5.0/5 🟢 ✅ test-anti-patterns; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.20 ✅ [75]
mcp-csharp-publish Publish an MCP server as a NuGet tool package 3.0/5 → 3.0/5 ⏰ ✅ mcp-csharp-publish; tools: skill, glob 🟡 0.21 ❌ [76]
mcp-csharp-publish Deploy an HTTP MCP server to Azure Container Apps 3.0/5 → 3.7/5 ⏰ 🟢 ✅ mcp-csharp-publish; tools: skill, report_intent, view / ✅ mcp-csharp-publish; tools: report_intent, skill, view 🟡 0.21 ❌ [77]
mcp-csharp-publish Publish to the MCP Registry 1.0/5 ⏰ → 3.3/5 🟢 ✅ mcp-csharp-publish; tools: skill / ✅ mcp-csharp-publish; tools: skill, view, report_intent 🟡 0.21 ✅
test-tagging Tag an untagged MSTest test suite 3.3/5 → 4.3/5 🟢 ✅ test-tagging; tools: skill / ✅ test-tagging; tools: skill, glob 🟡 0.20 ✅
test-tagging Tag an untagged xUnit test suite 3.7/5 → 4.3/5 🟢 ✅ test-tagging; tools: skill 🟡 0.20 ✅ [78]
test-tagging Tag an untagged NUnit test suite 3.5/5 → 4.5/5 🟢 ✅ test-tagging; tools: skill 🟡 0.20 ✅
test-tagging Audit test distribution without modifying files 4.0/5 → 2.5/5 ⏰ 🔴 ✅ test-tagging; tools: skill 🟡 0.20 ❌ [79]
test-tagging Decline request to write new tests 4.0/5 → 4.0/5 ℹ️ not activated (expected) 🟡 0.20 ❌ [80]
test-tagging Tag a partially-tagged MSTest suite without duplicating existing traits 4.0/5 → 4.7/5 🟢 ✅ test-tagging; tools: skill 🟡 0.20 ✅ [81]
test-tagging Accurately classify NUnit tests with misleading method names 4.3/5 → 4.3/5 ✅ test-tagging; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.20 ❌ [82]
test-tagging Tag MSTest tests and verify the project still builds 4.7/5 → 4.7/5 ✅ test-tagging; tools: skill 🟡 0.20 ❌ [83]
test-tagging Report traits for a Go test suite without modifying source 3.0/5 → 4.0/5 🟢 ✅ test-tagging; tools: skill 🟡 0.20 ✅
maui-collectionview Basic CollectionView with data binding and DataTemplate 5.0/5 → 5.0/5 ✅ maui-collectionview; tools: skill ✅ 0.09 ❌ [84]
maui-collectionview Grid layout with CollectionView 5.0/5 → 5.0/5 ✅ maui-collectionview; tools: skill, report_intent / ✅ maui-collectionview; tools: report_intent, skill ✅ 0.09 ❌ [85]
maui-collectionview Selection and pull-to-refresh with CollectionView 5.0/5 → 3.7/5 ⏰ 🔴 ✅ maui-collectionview; tools: report_intent, skill ✅ 0.09 ❌ [86]
maui-collectionview Avoid ListView and ViewCell mistakes 5.0/5 → 3.7/5 ⏰ 🔴 ✅ maui-collectionview; tools: skill ✅ 0.09 ❌ [87]
create-blazor-project University course catalog with enrollment form 2.7/5 → 3.7/5 🟢 ✅ create-blazor-project; tools: skill, task, read_agent / ✅ create-blazor-project; tools: skill 🟡 0.27 ✅ [88]
create-blazor-project Recipe community with interactive ratings on static pages 4.0/5 → 5.0/5 🟢 ✅ create-blazor-project; tools: skill, glob 🟡 0.27 ✅ [89]
create-blazor-project Global logistics tracking for worldwide users 3.7/5 → 4.0/5 🟢 ✅ create-blazor-project; tools: skill, task, read_agent 🟡 0.27 ✅ [90]
mcp-csharp-create Implement MCP tools with proper attributes and DI 4.0/5 → 4.7/5 🟢 ✅ mcp-csharp-create; tools: skill ✅ 0.14 ✅
mcp-csharp-create Create an HTTP MCP server with tools and resources 4.3/5 → 4.0/5 🔴 ✅ mcp-csharp-create; tools: skill ✅ 0.14 ❌ [91]
mcp-csharp-create Create an MCP server with tools, prompts, and proper logging 3.3/5 → 4.0/5 🟢 ✅ mcp-csharp-create; tools: skill ✅ 0.14 ✅ [92]
code-testing-agent Generate tests for ContosoUniversity ASP.NET Core MVC app 3.0/5 → 3.0/5 ✅ code-testing-agent; tools: skill / ✅ code-testing-agent; code-testing-extensions; test-gap-analysis; assertion-quality; tools: skill, task, read_agent ✅ 0.19 ❌ [93]
code-testing-agent Generate pytest tests for the Flask tasks API (Python polyglot) 4.3/5 → 4.0/5 🔴 ✅ code-testing-agent; tools: skill, edit / ⚠️ NOT ACTIVATED ✅ 0.19 ❌ [94]
code-testing-agent Generate Vitest tests for the shopping-cart library (TypeScript polyglot) 4.7/5 → 4.7/5 ✅ code-testing-agent; tools: skill ✅ 0.19 ✅ [95]
code-testing-agent Does not revert a gutted-looking workspace (workspace integrity) 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED ✅ 0.19 ❌ [96]
resolve-project-references Explain misleading ResolveProjectReferences time 4.0/5 → 5.0/5 🟢 ✅ resolve-project-references; tools: skill / ✅ resolve-project-references; tools: skill, glob ✅ 0.16 ✅
test-gap-analysis Find boundary mutation gaps in tiered discount and shipping logic 4.7/5 → 5.0/5 🟢 ✅ test-gap-analysis; tools: skill ✅ 0.14 ❌ [97]
test-gap-analysis Find logic and null-check mutation gaps in access control code 4.7/5 → 5.0/5 🟢 ✅ test-gap-analysis; tools: skill ✅ 0.14 ✅ [98]
test-gap-analysis Acknowledge well-tested code with few surviving mutations 3.3/5 → 3.7/5 🟢 ✅ test-gap-analysis; tools: skill ✅ 0.14 ❌ [99]
test-gap-analysis Decline request to write new tests from scratch 3.7/5 → 3.7/5 ℹ️ not activated (expected) ✅ 0.14 ✅ [100]
test-gap-analysis Produce a risk-prioritized report that excludes trivial and generated code 4.0/5 → 4.3/5 🟢 ✅ test-gap-analysis; tools: skill ✅ 0.14 ✅ [101]
test-gap-analysis Flag the Rust ? operator propagation as an unobserved mutation point 5.0/5 → 5.0/5 ✅ test-gap-analysis; tools: skill, glob / ✅ test-gap-analysis; tools: skill ✅ 0.14 ❌ [102]
android-tombstone-symbolication Symbolicate .NET frames in an Android tombstone 4.0/5 → 3.0/5 🔴 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ❌ [103]
android-tombstone-symbolication Recognize tombstone with no .NET frames 5.0/5 → 5.0/5 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ❌ [104]
android-tombstone-symbolication Symbolicate CoreCLR frames in an Android tombstone 3.7/5 → 3.7/5 ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ❌ [105]
android-tombstone-symbolication Recognize NativeAOT tombstone with app binary and libSystem.Native.so 3.0/5 → 4.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill, bash / ✅ android-tombstone-symbolication; tools: skill, bash, read_bash, stop_bash ✅ 0.15 ❌ [106]
android-tombstone-symbolication Symbolicate multi-thread tombstone 3.0/5 ⏰ → 4.7/5 🟢 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ✅ [107]
android-tombstone-symbolication Handle .NET frames with no BuildId metadata 3.7/5 → 5.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill, bash / ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ✅ [108]
android-tombstone-symbolication Symbolicate tombstone with multiple .NET libraries and different BuildIds 3.3/5 → 3.7/5 🟢 ✅ android-tombstone-symbolication; tools: skill, read_bash, stop_bash / ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ❌ [109]
android-tombstone-symbolication Reject iOS crash log as wrong format 4.0/5 → 5.0/5 🟢 ℹ️ not activated (expected) ✅ 0.15 ❌ [110]
build-perf-diagnostics Diagnose slow build for a small project 5.0/5 → 4.0/5 🔴 ⚠️ NOT ACTIVATED 🟡 0.21 ❌
check-bin-obj-clash Diagnose bin/obj output path clashes 3.3/5 → 4.0/5 ⏰ 🟢 ✅ check-bin-obj-clash; tools: skill, binlog-binlog_overview, binlog-binlog_double_writes, binlog-binlog_evaluations, binlog-binlog_properties, glob, edit, binlog-binlog_evaluation_global_properties, binlog-binlog_evaluation_properties / ✅ check-bin-obj-clash; tools: glob, binlog-binlog_double_writes, skill, binlog-binlog_evaluations, binlog-binlog_evaluation_properties, binlog-binlog_overview, binlog-binlog_properties, binlog-binlog_evaluation_global_properties ✅ 0.16 ❌ [111]
migrate-nullable-references Enable NRT in a small library with mixed nullability 5.0/5 → 5.0/5 ✅ migrate-nullable-references; tools: skill ✅ 0.15 ❌ [112]
migrate-nullable-references File-by-file migration: only modify the targeted file 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED ✅ 0.15 ❌ [113]
migrate-nullable-references Enable NRT in ASP.NET Core Web API with EF Core 4.0/5 → 4.3/5 🟢 ⚠️ NOT ACTIVATED ✅ 0.15 ❌ [114]
dotnet-maui-doctor Plan macOS MAUI setup with Xcode 3.0/5 → 3.7/5 ⏰ 🟢 ✅ dotnet-maui-doctor; tools: skill, report_intent, view / ✅ dotnet-maui-doctor; tools: report_intent, skill, view ✅ 0.19 ✅ [115]
dotnet-maui-doctor Plan Linux MAUI environment for Android 3.0/5 → 2.3/5 ⏰ 🔴 ✅ dotnet-maui-doctor; tools: skill, report_intent, view ✅ 0.19 ❌ [116]
dotnet-maui-doctor Guardrail against workload update and repair 1.0/5 → 4.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill ✅ 0.19 ✅
dotnet-maui-doctor Diagnose non-Microsoft JDK causing build failure 2.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill, view / ✅ dotnet-maui-doctor; tools: skill, report_intent, view ✅ 0.19 ✅
dotnet-maui-doctor Plan complete MAUI setup on Windows 4.0/5 → 4.0/5 ✅ dotnet-maui-doctor; tools: skill, report_intent, view ✅ 0.19 ❌ [117]
dotnet-maui-doctor Prevent incorrect JAVA_HOME configuration 2.7/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill, report_intent ✅ 0.19 ✅
dotnet-maui-doctor Determine required Android SDK packages for specific .NET version 3.0/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill, view ✅ 0.19 ✅ [118]
dotnet-maui-doctor Fix stale MAUI workloads after SDK update 2.0/5 → 4.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill, report_intent, view ✅ 0.19 ✅
fetch-and-send-data Recipe browser with resilient data loading 3.0/5 → 3.7/5 🟢 ✅ fetch-and-send-data; tools: skill 🟡 0.22 ✅
fetch-and-send-data Real-time shipment tracker with Auto interactivity 4.0/5 → 4.0/5 ✅ fetch-and-send-data; tools: skill 🟡 0.22 ✅ [119]
author-component Author a data-loading search component 3.0/5 → 4.0/5 ⏰ 🟢 ✅ author-component; tools: skill, view, bash / ✅ author-component; tools: skill, view 🟡 0.22 ✅
author-component Author a multi-step wizard with async validation and shared state 2.7/5 ⏰ → 4.3/5 🟢 ✅ author-component; tools: skill, view, create / ✅ author-component; tools: skill, view 🟡 0.22 ✅ [120]
author-component Author a generic data table component 4.0/5 → 4.0/5 ✅ author-component; tools: skill, bash 🟡 0.22 ✅ [121]
author-component Author a real-time notification badge component 2.0/5 → 3.0/5 ⏰ 🟢 ✅ author-component; tools: skill, view 🟡 0.22 ❌ [122]
author-component Author a sortable list with code-behind pattern 4.0/5 → 3.3/5 ⏰ 🔴 ✅ author-component; tools: skill, bash 🟡 0.22 ❌
exp-test-maintainability Recommend data-driven patterns with display names for unclear parameters 3.3/5 → 4.3/5 ⏰ 🟢 ✅ exp-test-maintainability; tools: skill ✅ 0.15 ❌ [123]
exp-test-maintainability Recognize well-maintained tests that need minimal changes 4.0/5 → 5.0/5 🟢 ✅ exp-test-maintainability; tools: skill ✅ 0.15 ❌ [124]
exp-test-maintainability Detect repeated object construction and setup across test methods 3.3/5 → 5.0/5 🟢 ✅ exp-test-maintainability; tools: skill ✅ 0.15 ❌ [125]
exp-test-maintainability Recognize tests with minimal boilerplate that need no refactoring 3.3/5 → 3.3/5 ⏰ ✅ exp-test-maintainability; tools: skill ✅ 0.15 ❌ [126]
binlog-failure-analysis Diagnose build failures from binlog only (no source files) 4.0/5 → 4.0/5 ⚠️ NOT ACTIVATED ✅ 0.11 ❌ [127]
template-instantiation Create a console application 4.0/5 → 5.0/5 🟢 ✅ template-instantiation; tools: skill 🟡 0.22 ✅ [128]
msbuild-modernization Modernize legacy project to SDK-style 3.3/5 ⏰ → 4.7/5 ⏰ 🟢 ✅ msbuild-modernization; tools: skill, glob, bash / ✅ msbuild-modernization; tools: skill, bash ✅ 0.06 ✅ [129]
assertion-quality Identify low assertion diversity in equality-dominated test suite 1.7/5 ⏰ → 2.7/5 ⏰ 🟢 ✅ assertion-quality; tools: skill 🟡 0.21 ✅ [130]
assertion-quality Flag assertion-free tests and trivial-only assertions 4.5/5 → 4.0/5 🔴 ✅ assertion-quality; tools: skill, glob / ✅ assertion-quality; tools: skill 🟡 0.21 ❌ [131]
assertion-quality Recognize well-diversified assertion usage 4.0/5 → 5.0/5 🟢 ✅ assertion-quality; tools: skill, glob / ✅ assertion-quality; tools: skill 🟡 0.21 ✅
assertion-quality Identify self-referential assertions in identity and round-trip tests 3.0/5 → 3.0/5 ✅ assertion-quality; tools: skill, glob 🟡 0.21 ✅
assertion-quality Decline request to write new tests from scratch 2.7/5 ⏰ → 4.0/5 🟢 ℹ️ not activated (expected) 🟡 0.21 ❌ [132]
assertion-quality Polyglot: evaluate shallow assertions in a Jest/TypeScript OrderService suite 4.7/5 → 5.0/5 🟢 ✅ assertion-quality; tools: skill, glob 🟡 0.21 ❌ [133]
template-authoring Validate a template.json file 3.0/5 → 3.3/5 🟢 ✅ template-authoring; tools: glob, skill, bash / ⚠️ NOT ACTIVATED ✅ 0.19 ✅ [134]
template-authoring Create template from existing project 4.0/5 → 5.0/5 🟢 ✅ template-authoring; tools: skill ✅ 0.19 ✅
plan-ui-change Project management Kanban board 2.3/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, edit ✅ 0.20 ✅
plan-ui-change E-commerce product catalog with filters and pagination 2.7/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, glob, grep / ✅ plan-ui-change; author-component; tools: skill, grep ✅ 0.20 ✅
plan-ui-change Multi-step job application wizard 2.0/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, edit ✅ 0.20 ✅
plan-ui-change Application settings page with nested tab panels 3.0/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill ✅ 0.20 ✅
plan-ui-change Team chat interface with message threads 2.0/5 → 3.3/5 🟢 ✅ plan-ui-change; tools: skill, grep, edit / ✅ plan-ui-change; tools: skill, edit ✅ 0.20 ✅ [135]
configure-auth Login and account management in a globally interactive app 5.0/5 → 5.0/5 ✅ configure-auth; tools: skill ✅ 0.08 ❌ [136]
configure-auth Multi-tier app with WebAssembly auth 2.5/5 ⏰ → 5.0/5 🟢 ✅ configure-auth; tools: glob, skill, bash / ✅ configure-auth; tools: skill, bash ✅ 0.08 ✅
system-text-json-net11 Serialize JSON in .NET 11 with PascalCase property names 2.7/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ system-text-json-net11; tools: skill / ✅ system-text-json-net11; tools: skill, edit ✅ 0.06 ❌ [137]
system-text-json-net11 Type-safe JsonTypeInfo access without exceptions in .NET 11 2.0/5 ⏰ → 2.5/5 ⏰ 🟢 ✅ system-text-json-net11; tools: skill, edit, view ✅ 0.06 ✅ [138]
system-text-json-net11 Non-activation: camelCase JSON serialization on .NET 8 3.0/5 ⏰ → 5.0/5 🟢 ℹ️ not activated (expected) ✅ 0.06 ✅ [139]
mcp-csharp-test Write unit and integration tests for an MCP server 2.7/5 → 4.0/5 🟢 ✅ mcp-csharp-test; tools: skill, report_intent, view 🟡 0.26 ✅
mcp-csharp-test Test an HTTP MCP server with WebApplicationFactory 4.0/5 → 2.0/5 ⏰ 🔴 ✅ mcp-csharp-test; tools: skill, report_intent, view 🟡 0.26 ❌ [140]
mcp-csharp-test Create evaluations for an MCP server 2.0/5 → 4.7/5 🟢 ✅ mcp-csharp-test; tools: skill, view 🟡 0.26 ❌ [141]
template-smart-defaults AOT implies a compatible framework 2.0/5 → 4.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill, bash / ⚠️ NOT ACTIVATED 🟡 0.36 ✅
template-smart-defaults Auth implies HTTPS stays enabled 2.0/5 → 4.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.36 ✅ [142]
template-smart-defaults Controllers exclude the minimal-API flag 3.0/5 → 5.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.36 ✅ [143]
template-smart-defaults Never override an explicit user value 2.0/5 → 5.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.36 ✅
dump-collect Configure automatic crash dumps for CoreCLR app on Linux 4.3/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view 🟡 0.29 ❌ [144]
dump-collect Set up NativeAOT crash dumps with createdump in Kubernetes 2.7/5 → 3.7/5 ⏰ 🟢 ✅ dump-collect; tools: report_intent, skill, view 🟡 0.29 ✅ [145]
dump-collect Recover crash dump from macOS NativeAOT without createdump 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ⚠️ NOT ACTIVATED 🟡 0.29 ✅ [146]
dump-collect Configure CoreCLR dump collection in Alpine Docker as non-root 3.0/5 → 3.7/5 ⏰ 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.29 ✅ [147]
dump-collect Advisory: macOS NativeAOT crash dump recovery steps 4.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, view 🟡 0.29 ✅
dump-collect Advisory: CoreCLR Alpine Docker non-root configuration 4.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.29 ✅ [148]
dump-collect Advisory: NativeAOT Kubernetes dump collection setup 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.29 ✅
dump-collect Detect runtime and configure crash dumps for unknown .NET app on Linux 4.0/5 → 3.3/5 🔴 ✅ dump-collect; tools: skill, view 🟡 0.29 ❌ [149]
dump-collect Decline dump analysis request 2.0/5 ⏰ → 4.3/5 🟢 ℹ️ not activated (expected) 🟡 0.29 ✅ [150]
support-prerendering Equipment inventory loaded once 5.0/5 → 5.0/5 ✅ support-prerendering; tools: skill, glob 🟡 0.22 ✅ [151]
support-prerendering Notifications page with live polling 3.7/5 → 3.3/5 🔴 ✅ support-prerendering; tools: skill / ✅ support-prerendering; create-blazor-project; tools: skill, glob 🟡 0.22 ✅ [152]
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 9) 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 10) 1.3/5 → 3.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
mtp-hot-reload Enable hot reload when package already installed 2.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
mtp-hot-reload Suggest launchSettings.json configuration for hot reload 1.0/5 → 4.0/5 🟢 ✅ mtp-hot-reload; tools: skill, bash, create ✅ 0.08 ✅
mtp-hot-reload Use dotnet run not dotnet test for hot reload 2.3/5 → 3.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅ [153]
mtp-hot-reload Negative: VSTest project cannot use MTP hot reload 2.0/5 → 2.3/5 🟢 ✅ mtp-hot-reload; tools: skill, edit, bash, create / ✅ mtp-hot-reload; tools: skill, bash, create, edit ✅ 0.08 ❌ [154]
mtp-hot-reload Run specific failing test with hot reload filter 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
including-generated-files Diagnose generated file inclusion failure 3.3/5 → 4.3/5 ⏰ 🟢 ✅ including-generated-files; tools: skill ✅ 0.17 ❌ [155]
build-parallelism Analyze build parallelism bottlenecks 1.0/5 ⏰ → 2.5/5 ⏰ 🟢 ⚠️ NOT ACTIVATED ✅ 0.20 ❌ [156]

[1] ⚠️ High run-to-run variance (CV=153%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +11.4% due to: efficiency metrics
[2] ⚠️ High run-to-run variance (CV=910%) — consider re-running with --runs 5
[3] ⚠️ High run-to-run variance (CV=407%) — consider re-running with --runs 5
[4] ⚠️ High run-to-run variance (CV=90%) — consider re-running with --runs 5
[5] ⚠️ High run-to-run variance (CV=99%) — consider re-running with --runs 5
[6] ⚠️ High run-to-run variance (CV=270%) — consider re-running with --runs 5
[7] ⚠️ High run-to-run variance (CV=77%) — consider re-running with --runs 5
[8] ⚠️ High run-to-run variance (CV=63%) — consider re-running with --runs 5
[9] ⚠️ High run-to-run variance (CV=110%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -7.6% due to: tokens (4220 → 12615), tool calls (1 → 2)
[10] ⚠️ High run-to-run variance (CV=63%) — consider re-running with --runs 5
[11] ⚠️ High run-to-run variance (CV=109%) — consider re-running with --runs 5
[12] ⚠️ High run-to-run variance (CV=159%) — consider re-running with --runs 5
[13] ⚠️ High run-to-run variance (CV=498%) — consider re-running with --runs 5
[14] (Plugin) Quality unchanged but weighted score is -10.0% due to: tokens (25487 → 62730), tool calls (2 → 4), time (42.2s → 91.6s)
[15] ⚠️ High run-to-run variance (CV=74%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -7.9% due to: tokens (25467 → 56132), tool calls (2 → 4)
[16] ⚠️ High run-to-run variance (CV=68%) — consider re-running with --runs 5
[17] ⚠️ High run-to-run variance (CV=106%) — consider re-running with --runs 5
[18] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -2.8% due to: tokens (34927 → 53788)
[19] (Plugin) Quality unchanged but weighted score is -1.5% due to: tokens (12612 → 17264)
[20] ⚠️ High run-to-run variance (CV=94%) — consider re-running with --runs 5
[21] ⚠️ High run-to-run variance (CV=64%) — consider re-running with --runs 5
[22] ⚠️ High run-to-run variance (CV=126%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -24.2% due to: judgment, quality, tokens (25303 → 41628), tool calls (2 → 4), time (13.7s → 31.8s)
[23] ⚠️ High run-to-run variance (CV=83%) — consider re-running with --runs 5
[24] ⚠️ High run-to-run variance (CV=261%) — consider re-running with --runs 5
[25] ⚠️ High run-to-run variance (CV=82%) — consider re-running with --runs 5
[26] ⚠️ High run-to-run variance (CV=183%) — consider re-running with --runs 5
[27] ⚠️ High run-to-run variance (CV=224%) — consider re-running with --runs 5
[28] ⚠️ High run-to-run variance (CV=77%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -23.4% due to: completion (✓ → ✗), tokens (12730 → 31982), tool calls (0 → 1), time (19.4s → 53.5s)
[29] ⚠️ High run-to-run variance (CV=69%) — consider re-running with --runs 5
[30] ⚠️ High run-to-run variance (CV=318%) — consider re-running with --runs 5
[31] ⚠️ High run-to-run variance (CV=450%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -16.9% due to: judgment, tokens (59218 → 90641), time (99.6s → 156.7s), tool calls (6 → 8)
[32] ⚠️ High run-to-run variance (CV=285%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -56.1% due to: quality, judgment, tokens (43828 → 90089), time (80.1s → 116.3s), tool calls (5 → 7)
[33] ⚠️ High run-to-run variance (CV=229%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -16.5% due to: judgment, quality, tokens (59033 → 72792)
[34] ⚠️ High run-to-run variance (CV=227%) — consider re-running with --runs 5
[35] (Isolated) Quality unchanged but weighted score is -3.6% due to: tokens (123963 → 194525), time (79.0s → 104.1s)
[36] ⚠️ High run-to-run variance (CV=9225%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -12.1% due to: judgment, quality
[37] ⚠️ High run-to-run variance (CV=347%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -3.1% due to: errors (0 → 1), tokens (38718 → 50371), time (79.6s → 113.9s), tool calls (3 → 4)
[38] ⚠️ High run-to-run variance (CV=195%) — consider re-running with --runs 5
[39] ⚠️ High run-to-run variance (CV=147%) — consider re-running with --runs 5
[40] ⚠️ High run-to-run variance (CV=73%) — consider re-running with --runs 5
[41] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5
[42] (Plugin) Quality unchanged but weighted score is -5.4% due to: tokens (26126 → 47185), time (23.4s → 45.0s)
[43] ⚠️ High run-to-run variance (CV=359%) — consider re-running with --runs 5
[44] ⚠️ High run-to-run variance (CV=70%) — consider re-running with --runs 5
[45] ⚠️ High run-to-run variance (CV=155%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -1.3% due to: tokens (64235 → 176586), time (26.9s → 60.6s), tool calls (8 → 10)
[46] (Plugin) Quality unchanged but weighted score is -5.2% due to: tokens (74046 → 156916)
[47] (Plugin) Quality unchanged but weighted score is -7.2% due to: tokens (69896 → 209115), time (36.5s → 92.8s), tool calls (8 → 11)
[48] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -4.6% due to: tokens (129507 → 311630), tool calls (12 → 15)
[49] ⚠️ High run-to-run variance (CV=157%) — consider re-running with --runs 5
[50] ⚠️ High run-to-run variance (CV=146%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -4.5% due to: tokens (34363 → 64191)
[51] ⚠️ High run-to-run variance (CV=58%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -58.0% due to: quality, completion (✓ → ✗), judgment, tokens (42438 → 245864), errors (0 → 1), tool calls (10 → 22), time (74.7s → 188.1s)
[52] ⚠️ High run-to-run variance (CV=53%) — consider re-running with --runs 5
[53] ⚠️ High run-to-run variance (CV=225%) — consider re-running with --runs 5
[54] ⚠️ High run-to-run variance (CV=215%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -0.4% due to: tokens (40203 → 50242)
[55] ⚠️ High run-to-run variance (CV=67%) — consider re-running with --runs 5
[56] ⚠️ High run-to-run variance (CV=64%) — consider re-running with --runs 5
[57] ⚠️ High run-to-run variance (CV=201%) — consider re-running with --runs 5
[58] ⚠️ High run-to-run variance (CV=134%) — consider re-running with --runs 5
[59] ⚠️ High run-to-run variance (CV=296%) — consider re-running with --runs 5
[60] ⚠️ High run-to-run variance (CV=140%) — consider re-running with --runs 5
[61] ⚠️ High run-to-run variance (CV=181%) — consider re-running with --runs 5
[62] ⚠️ High run-to-run variance (CV=86%) — consider re-running with --runs 5
[63] ⚠️ High run-to-run variance (CV=1463%) — consider re-running with --runs 5
[64] ⚠️ High run-to-run variance (CV=60%) — consider re-running with --runs 5
[65] ⚠️ High run-to-run variance (CV=2310%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -5.2% due to: tokens (12946 → 32558), tool calls (0 → 1), time (33.1s → 89.2s)
[66] (Plugin) Quality unchanged but weighted score is -10.0% due to: tokens (12844 → 33294), tool calls (0 → 2), time (23.2s → 68.4s)
[67] ⚠️ High run-to-run variance (CV=75%) — consider re-running with --runs 5
[68] ⚠️ High run-to-run variance (CV=94%) — consider re-running with --runs 5
[69] ⚠️ High run-to-run variance (CV=262%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -8.0% due to: tokens (27775 → 67331), time (47.2s → 93.1s), tool calls (3 → 5)
[70] (Plugin) Quality unchanged but weighted score is -6.4% due to: tokens (40793 → 89824), tool calls (4 → 6), quality
[71] ⚠️ High run-to-run variance (CV=89%) — consider re-running with --runs 5
[72] ⚠️ High run-to-run variance (CV=72%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -17.7% due to: completion (✓ → ✗), tool calls (3 → 5), tokens (44258 → 58539)
[73] (Plugin) Quality unchanged but weighted score is -10.5% due to: tokens (28890 → 67292), time (68.5s → 122.3s), quality, tool calls (3 → 5)
[74] ⚠️ High run-to-run variance (CV=271%) — consider re-running with --runs 5
[75] ⚠️ High run-to-run variance (CV=1155%) — consider re-running with --runs 5
[76] ⚠️ High run-to-run variance (CV=481%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -62.1% due to: judgment, quality, tokens (25663 → 56677), tool calls (2 → 5), time (53.4s → 66.2s)
[77] ⚠️ High run-to-run variance (CV=353%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -68.0% due to: judgment, quality, tokens (12852 → 35424), tool calls (0 → 2), time (21.0s → 77.8s)
[78] ⚠️ High run-to-run variance (CV=114%) — consider re-running with --runs 5
[79] ⚠️ High run-to-run variance (CV=128%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.4% due to: tokens (43546 → 89990)
[80] (Isolated) Quality unchanged but weighted score is -19.5% due to: judgment, quality
[81] ⚠️ High run-to-run variance (CV=154%) — consider re-running with --runs 5
[82] ⚠️ High run-to-run variance (CV=616%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -7.0% due to: completion (✓ → ✗), tokens (124738 → 284187), time (107.9s → 155.4s), tool calls (19 → 24)
[83] ⚠️ High run-to-run variance (CV=304%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -1.8% due to: quality, tokens (354574 → 397383)
[84] ⚠️ High run-to-run variance (CV=73%) — consider re-running with --runs 5
[85] (Plugin) Quality unchanged but weighted score is -9.8% due to: tokens (12785 → 33278), tool calls (0 → 2), time (42.6s → 82.1s)
[86] ⚠️ High run-to-run variance (CV=79%) — consider re-running with --runs 5
[87] ⚠️ High run-to-run variance (CV=136%) — consider re-running with --runs 5
[88] ⚠️ High run-to-run variance (CV=1181%) — consider re-running with --runs 5
[89] ⚠️ High run-to-run variance (CV=122%) — consider re-running with --runs 5
[90] ⚠️ High run-to-run variance (CV=181%) — consider re-running with --runs 5
[91] ⚠️ High run-to-run variance (CV=434%) — consider re-running with --runs 5
[92] ⚠️ High run-to-run variance (CV=290%) — consider re-running with --runs 5
[93] ⚠️ High run-to-run variance (CV=55%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -20.5% due to: judgment, quality, tokens (2188124 → 2938452), time (515.1s → 620.9s)
[94] ⚠️ High run-to-run variance (CV=76%) — consider re-running with --runs 5
[95] ⚠️ High run-to-run variance (CV=360%) — consider re-running with --runs 5
[96] ⚠️ High run-to-run variance (CV=69%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -1.2% due to: tokens (91792 → 114715)
[97] ⚠️ High run-to-run variance (CV=857%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -1.7% due to: tokens (41116 → 87816), time (63.3s → 113.6s), tool calls (5 → 7)
[98] ⚠️ High run-to-run variance (CV=618%) — consider re-running with --runs 5
[99] ⚠️ High run-to-run variance (CV=4368%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -48.9% due to: judgment, quality
[100] ⚠️ High run-to-run variance (CV=3079%) — consider re-running with --runs 5
[101] ⚠️ High run-to-run variance (CV=85%) — consider re-running with --runs 5
[102] ⚠️ High run-to-run variance (CV=100%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -2.2% due to: tokens (51820 → 87758), time (25.2s → 40.7s)
[103] ⚠️ High run-to-run variance (CV=572%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.8% due to: quality
[104] (Plugin) Quality unchanged but weighted score is -5.8% due to: tokens (26387 → 48455), tool calls (2 → 3)
[105] ⚠️ High run-to-run variance (CV=359%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -15.5% due to: completion (✓ → ✗), quality
[106] ⚠️ High run-to-run variance (CV=342%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -56.0% due to: judgment, quality, tokens (27190 → 115375), tool calls (2 → 8), time (47.0s → 237.0s)
[107] ⚠️ High run-to-run variance (CV=115%) — consider re-running with --runs 5
[108] ⚠️ High run-to-run variance (CV=53%) — consider re-running with --runs 5
[109] ⚠️ High run-to-run variance (CV=88%) — consider re-running with --runs 5
[110] ⚠️ High run-to-run variance (CV=274%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -7.5% due to: judgment, tokens (26660 → 49616), quality, tool calls (2 → 3), time (18.6s → 25.5s)
[111] ⚠️ High run-to-run variance (CV=208%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -24.7% due to: judgment, tokens (85271 → 244408), quality, tool calls (9 → 22)
[112] (Plugin) Quality unchanged but weighted score is -5.6% due to: tokens (92795 → 190821)
[113] ⚠️ High run-to-run variance (CV=230%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.5% due to: tokens (88969 → 98692)
[114] ⚠️ High run-to-run variance (CV=255%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -28.8% due to: quality, judgment, time (119.2s → 202.3s), tokens (100674 → 129936)
[115] ⚠️ High run-to-run variance (CV=9065%) — consider re-running with --runs 5
[116] ⚠️ High run-to-run variance (CV=145%) — consider re-running with --runs 5
[117] ⚠️ High run-to-run variance (CV=58%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -22.2% due to: completion (✓ → ✗), tokens (13625 → 60993), tool calls (0 → 7), time (29.7s → 84.6s)
[118] ⚠️ High run-to-run variance (CV=59%) — consider re-running with --runs 5
[119] ⚠️ High run-to-run variance (CV=198%) — consider re-running with --runs 5
[120] ⚠️ High run-to-run variance (CV=217%) — consider re-running with --runs 5
[121] ⚠️ High run-to-run variance (CV=55%) — consider re-running with --runs 5
[122] ⚠️ High run-to-run variance (CV=43325%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -71.3% due to: judgment, quality, errors (0 → 1), tokens (26391 → 45835), tool calls (2 → 5), time (52.6s → 97.6s)
[123] ⚠️ High run-to-run variance (CV=359%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -11.1% due to: errors (0 → 1), time (48.4s → 103.2s), quality, tokens (39684 → 48342), tool calls (4 → 5)
[124] ⚠️ High run-to-run variance (CV=250%) — consider re-running with --runs 5
[125] ⚠️ High run-to-run variance (CV=407%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -5.3% due to: errors (0 → 1), tokens (41953 → 51553), time (67.0s → 95.3s), tool calls (4 → 5)
[126] ⚠️ High run-to-run variance (CV=95%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -70.8% due to: quality, judgment, errors (0 → 1), time (58.2s → 83.6s), tokens (40014 → 45440)
[127] ⚠️ High run-to-run variance (CV=439%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -6.8% due to: judgment, quality
[128] ⚠️ High run-to-run variance (CV=200%) — consider re-running with --runs 5
[129] ⚠️ High run-to-run variance (CV=2413%) — consider re-running with --runs 5
[130] ⚠️ High run-to-run variance (CV=5506%) — consider re-running with --runs 5
[131] (Plugin) Quality unchanged but weighted score is -6.4% due to: tokens (26484 → 62636), tool calls (2 → 3)
[132] ⚠️ High run-to-run variance (CV=4167%) — consider re-running with --runs 5
[133] ⚠️ High run-to-run variance (CV=464%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -1.5% due to: tokens (27125 → 63654), time (36.0s → 51.0s), tool calls (3 → 4)
[134] ⚠️ High run-to-run variance (CV=265%) — consider re-running with --runs 5
[135] ⚠️ High run-to-run variance (CV=51%) — consider re-running with --runs 5
[136] ⚠️ High run-to-run variance (CV=86%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.3% due to: tokens (309854 → 369963)
[137] ⚠️ High run-to-run variance (CV=1806%) — consider re-running with --runs 5
[138] ⚠️ High run-to-run variance (CV=109%) — consider re-running with --runs 5
[139] ⚠️ High run-to-run variance (CV=1498%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +48.8% due to: efficiency metrics
[140] ⚠️ High run-to-run variance (CV=85%) — consider re-running with --runs 5
[141] ⚠️ High run-to-run variance (CV=338%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -51.1% due to: judgment, quality, time (64.2s → 91.8s)
[142] (Plugin) Quality dropped but weighted score is +25.0% due to: completion (✗ → ✓)
[143] ⚠️ High run-to-run variance (CV=544%) — consider re-running with --runs 5
[144] ⚠️ High run-to-run variance (CV=173%) — consider re-running with --runs 5
[145] ⚠️ High run-to-run variance (CV=4438%) — consider re-running with --runs 5
[146] ⚠️ High run-to-run variance (CV=204%) — consider re-running with --runs 5
[147] ⚠️ High run-to-run variance (CV=3509%) — consider re-running with --runs 5
[148] ⚠️ High run-to-run variance (CV=74%) — consider re-running with --runs 5
[149] ⚠️ High run-to-run variance (CV=118%) — consider re-running with --runs 5
[150] ⚠️ High run-to-run variance (CV=59%) — consider re-running with --runs 5
[151] ⚠️ High run-to-run variance (CV=173%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +7.8% due to: completion (✗ → ✓)
[152] ⚠️ High run-to-run variance (CV=287%) — consider re-running with --runs 5. (Isolated) Quality dropped but weighted score is +11.6% due to: efficiency metrics
[153] ⚠️ High run-to-run variance (CV=76%) — consider re-running with --runs 5
[154] ⚠️ High run-to-run variance (CV=726%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -32.0% due to: judgment, quality, tokens (25320 → 137948), tool calls (2 → 7), time (23.3s → 92.6s)
[155] ⚠️ High run-to-run variance (CV=418%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -53.6% due to: judgment, quality, tokens (86358 → 116822)
[156] ⚠️ High run-to-run variance (CV=6208%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -8.4% due to: tokens (169760 → 325015), quality, tool calls (16 → 20)

⏰ timeout — run(s) hit the (30s, 60s, 120s, 160s, 180s, 240s, 300s, 420s, 600s) scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output (increase via timeout in eval.yaml)

Model: claude-opus-4.6 | Judge: claude-opus-4.6

🔍 Full Results - additional metrics and failure investigation steps

To investigate failures, paste this to your AI coding agent:

For PR 854 in dotnet/skills, download eval artifacts with gh run download 28769636244 --repo dotnet/skills --pattern "skill-validator-results-*" --dir ./eval-results, then fetch https://raw.githubusercontent.com/dotnet/skills/a2845b56d2bd28cad93f95090fa34a4c6c149478/eng/skill-validator/src/docs/InvestigatingResults.md and follow it to analyze the results.json files. Diagnose each failure, suggest fixes to the eval.yaml and skill content, and tell me what to fix first.

github-actions Bot added a commit that referenced this pull request Jul 6, 2026
@github-actions
Update PR token usage data (PR #854)
5ce5b35
@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Skill Validation Results

Skill Scenario Quality Skills Loaded Overfit Verdict
clr-activation-debugging Diagnose unexpected FOD dialog from native build tool 3.3/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill, bash ✅ 0.16 ❌ [1]
clr-activation-debugging Diagnose FOD suppressed but activation still failing 3.7/5 → 3.7/5 ⏰ ✅ clr-activation-debugging; tools: skill / ✅ clr-activation-debugging; tools: skill, bash ✅ 0.16 ❌ [2]
clr-activation-debugging Explain why same binary behaves differently under different launch methods 2.3/5 ⏰ → 5.0/5 🟢 ✅ clr-activation-debugging; tools: skill, bash / ✅ clr-activation-debugging; tools: skill ✅ 0.16 ✅ [3]
clr-activation-debugging Analyze healthy managed EXE activation 3.7/5 ⏰ → 1.0/5 ⏰ 🔴 ✅ clr-activation-debugging; tools: glob, skill, report_intent / ✅ clr-activation-debugging; tools: skill, glob, report_intent ✅ 0.16 ❌ [4]
clr-activation-debugging Identify multiple activation sequences in a single log 3.7/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ clr-activation-debugging; tools: skill, glob ✅ 0.16 ✅ [5]
clr-activation-debugging Explain useLegacyV2RuntimeActivationPolicy in activation log 2.3/5 ⏰ → 3.7/5 🟢 ✅ clr-activation-debugging; tools: report_intent, skill / ✅ clr-activation-debugging; tools: skill ✅ 0.16 ✅ [6]
clr-activation-debugging Decline non-CLR-activation issue 1.0/5 → 4.3/5 🟢 ✅ clr-activation-debugging; tools: skill, glob / ℹ️ not activated (expected) ✅ 0.16 ✅
msbuild-antipatterns Review MSBuild files for anti-patterns and style issues 5.0/5 → 3.7/5 ⏰ 🔴 ✅ msbuild-antipatterns; tools: skill, glob / ⚠️ NOT ACTIVATED ✅ 0.11 ❌ [7]
msbuild-antipatterns Add a module to an F# project 5.0/5 ⏰ → 3.7/5 ⏰ 🔴 ⚠️ NOT ACTIVATED ✅ 0.11 ❌ [8]
msbuild-antipatterns Fix broken file order causing FS0039 4.0/5 ⏰ → 3.7/5 ⏰ 🔴 ⚠️ NOT ACTIVATED ✅ 0.11 ❌ [9]
msbuild-antipatterns Add a signature file to define public API 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED ✅ 0.11 ❌ [10]
template-validation Validate template with multiple errors 3.7/5 → 3.7/5 ⏰ ✅ template-validation; tools: skill ✅ 0.14 ✅ [11]
template-validation Validate correct template and suggest improvements 1.7/5 → 3.3/5 🟢 ✅ template-validation; tools: glob, skill ✅ 0.14 ✅
maui-safe-area Handle notch and status bar safe areas on iOS 1.7/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: report_intent, skill ✅ 0.08 ✅
maui-safe-area Edge-to-edge layout with SafeAreaEdges 1.3/5 → 3.7/5 ⏰ 🟢 ✅ maui-safe-area; tools: skill, report_intent ✅ 0.08 ✅ [12]
maui-safe-area Keyboard avoidance with safe area for chat UI 1.0/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: skill, report_intent / ✅ maui-safe-area; tools: report_intent, skill ✅ 0.08 ✅
maui-safe-area Avoid deprecated UseSafeArea in new .NET 10 project 1.3/5 → 3.7/5 ⏰ 🟢 ✅ maui-safe-area; tools: skill ✅ 0.08 ❌ [13]
migrate-mstest-v1v2-to-v3 Migrate MSTest v1 project with assembly reference 3.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ✅
migrate-mstest-v1v2-to-v3 Migrate MSTest v2 NuGet project to v3 3.0/5 → 4.7/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ✅
migrate-mstest-v1v2-to-v3 Fix Assert.AreEqual object overload errors after v3 upgrade 4.7/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ❌ [14]
migrate-mstest-v1v2-to-v3 Migrate from .testsettings to .runsettings 3.3/5 → 4.3/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill, create, bash / ✅ migrate-mstest-v1v2-to-v3; tools: skill, create ✅ 0.07 ✅ [15]
migrate-mstest-v1v2-to-v3 Fix DataRow type mismatch errors after v3 upgrade 4.0/5 → 3.7/5 🔴 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ❌ [16]
migrate-mstest-v1v2-to-v3 Migrate to MSTest.Sdk project style 3.0/5 → 4.7/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ✅
migrate-mstest-v1v2-to-v3 Handle dropped target framework during v3 migration 2.0/5 → 3.7/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill, edit ✅ 0.07 ✅
migrate-mstest-v1v2-to-v3 Migrate complex MSTest v2 project with testsettings, DataRow issues, and dropped TFM 4.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ✅
migrate-mstest-v1v2-to-v3 Correctly identify MSTest v1 vs v2 and recommend different migration paths 4.0/5 → 5.0/5 🟢 ✅ migrate-mstest-v1v2-to-v3; tools: skill ✅ 0.07 ✅
exp-mock-usage-analysis Detect unused and unreachable mock setups 4.3/5 → 5.0/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅ [17]
exp-mock-usage-analysis Detect redundant mock configurations duplicated across tests 3.0/5 → 4.0/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅
exp-mock-usage-analysis Detect mocking of stable framework types 3.0/5 → 3.7/5 ⏰ 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ❌ [18]
exp-mock-usage-analysis Analyze mock usage in NSubstitute tests 3.3/5 → 3.3/5 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅ [19]
exp-mock-usage-analysis Analyze mock usage in FakeItEasy tests 4.7/5 → 4.7/5 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅ [20]
exp-mock-usage-analysis Detect excessive mock configuration sprawl 3.0/5 → 4.0/5 🟢 ✅ exp-mock-usage-analysis; tools: skill ✅ 0.09 ✅
generate-testability-wrappers Generate TimeProvider adoption for DateTime.UtcNow 4.0/5 → 5.0/5 🟢 ✅ generate-testability-wrappers; tools: skill / ✅ generate-testability-wrappers; tools: skill, glob, bash 🟡 0.26 ❌ [21]
generate-testability-wrappers Generate custom Environment wrapper 3.0/5 → 4.0/5 🟢 ✅ generate-testability-wrappers; tools: skill, glob 🟡 0.26 ❌ [22]
generate-testability-wrappers Recommend System.IO.Abstractions for file system calls 3.0/5 → 5.0/5 🟢 ✅ generate-testability-wrappers; tools: report_intent, skill, glob, view / ✅ generate-testability-wrappers; tools: report_intent, skill 🟡 0.26 ❌ [23]
generate-testability-wrappers Decline wrapper generation for already-abstracted code 3.0/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ generate-testability-wrappers; tools: skill 🟡 0.26 ✅ [24]
generate-testability-wrappers Provide ambient context alternative when DI is unavailable 1.3/5 → 3.3/5 🟢 ✅ generate-testability-wrappers; tools: skill, grep, create, edit / ⚠️ NOT ACTIVATED 🟡 0.26 ❌ [25]
migrate-static-to-wrapper Migrate DateTime.UtcNow to TimeProvider in a service class 4.7/5 ⏰ → 4.7/5 ⏰ ✅ migrate-static-to-wrapper; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [26]
migrate-static-to-wrapper Migrate only in scoped files, leaving others untouched 4.7/5 → 4.3/5 ⏰ 🔴 ✅ migrate-static-to-wrapper; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [27]
migrate-static-to-wrapper Update test doubles when migrating a service to TimeProvider 4.3/5 → 5.0/5 🟢 ✅ migrate-static-to-wrapper; tools: glob, skill / ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [28]
migrate-static-to-wrapper Handle a genuinely static class that cannot take constructor injection 2.3/5 → 2.3/5 ✅ migrate-static-to-wrapper; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.08 ✅ [29]
migrate-static-to-wrapper Decline migration when wrapper does not exist yet 4.0/5 → 4.7/5 🟢 ✅ migrate-static-to-wrapper; tools: skill ✅ 0.08 ❌ [30]
run-tests Run tests in a VSTest MSTest project 4.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, bash, glob / ⚠️ NOT ACTIVATED 🟡 0.25 ✅ [31]
run-tests Run tests with trx reporting on MTP project (SDK 9) 2.0/5 → 5.0/5 🟢 ✅ run-tests; tools: report_intent, skill, view 🟡 0.25 ✅
run-tests Run tests with blame-hang on MTP project (SDK 10) 1.7/5 → 3.3/5 🟢 ⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill 🟡 0.25 ✅ [32]
run-tests Run tests on a specific TFM with TRX in a multi-TFM MTP project (SDK 9) 3.7/5 → 5.0/5 🟢 ✅ run-tests; tools: view, skill / ✅ run-tests; tools: skill, view 🟡 0.25 ✅ [33]
run-tests Filter MSTest tests by category on VSTest 3.7/5 ⏰ → 4.7/5 🟢 ⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill 🟡 0.25 ✅ [34]
run-tests Filter NUnit tests by class name on VSTest 3.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view, bash / ⚠️ NOT ACTIVATED 🟡 0.25 ❌ [35]
run-tests Filter xUnit v3 tests by class on MTP 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view 🟡 0.25 ❌ [36]
run-tests Filter xUnit v3 tests by trait on MTP 1.0/5 ⏰ → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ⚠️ NOT ACTIVATED 🟡 0.25 ❌ [37]
run-tests Filter xUnit v3 tests by class pattern and trait using query filter language 1.0/5 → 1.0/5 ⚠️ NOT ACTIVATED 🟡 0.25 ❌ [38]
run-tests Filter TUnit tests by class using treenode-filter 2.3/5 → 3.7/5 🟢 ⚠️ NOT ACTIVATED 🟡 0.25 ✅ [39]
run-tests Combine multiple filter criteria on VSTest MSTest 3.7/5 → 5.0/5 🟢 ✅ run-tests; tools: report_intent, skill, view, bash / ✅ run-tests; tools: report_intent, skill, view, glob 🟡 0.25 ✅ [40]
run-tests MTP project on SDK 9 must use -- separator for args 1.0/5 → 3.7/5 🟢 ⚠️ NOT ACTIVATED 🟡 0.25 ❌ [41]
run-tests MTP project on SDK 10 passes args directly 2.0/5 → 4.3/5 🟢 ⚠️ NOT ACTIVATED 🟡 0.25 ✅ [42]
run-tests Detect test platform from Directory.Build.props 1.7/5 → 5.0/5 🟢 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.25 ✅ [43]
run-tests Negative test: do not use MTP syntax for a VSTest project 4.3/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view, glob / ⚠️ NOT ACTIVATED 🟡 0.25 ❌ [44]
detect-static-dependencies Identify static dependencies in a multi-class project 3.7/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill ✅ 0.10 ✅ [45]
detect-static-dependencies Detect time-related statics and recommend TimeProvider 4.3/5 → 4.0/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob ✅ 0.10 ❌ [46]
detect-static-dependencies Decline scan for non-C# project 2.3/5 ⏰ → 2.3/5 ⏰ ✅ detect-static-dependencies; tools: skill, report_intent, view, grep / ✅ detect-static-dependencies; tools: glob, skill, report_intent, view ✅ 0.10 ❌ [47]
detect-static-dependencies Verify structured report includes file count, categories, and top patterns 4.7/5 → 5.0/5 🟢 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: skill ✅ 0.10 ✅ [48]
detect-static-dependencies Exclude obj and bin directories from the scan 3.7/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob ✅ 0.10 ❌ [49]
detect-static-dependencies Detect statics inside lambda expressions and LINQ queries 4.3/5 → 2.0/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob ✅ 0.10 ❌ [50]
maui-app-lifecycle Save and restore state on background 2.0/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: skill / ✅ maui-app-lifecycle; tools: report_intent, skill ✅ 0.16 ❌ [51]
maui-app-lifecycle Window lifecycle event subscription 3.7/5 → 3.7/5 ⏰ ✅ maui-app-lifecycle; tools: skill / ✅ maui-app-lifecycle; tools: report_intent, skill ✅ 0.16 ❌ [52]
maui-app-lifecycle Platform-specific lifecycle mapping 4.0/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: skill ✅ 0.16 ❌ [53]
maui-app-lifecycle Avoid legacy Xamarin.Forms lifecycle methods 4.0/5 → 4.0/5 ✅ maui-app-lifecycle; tools: skill ✅ 0.16 ❌ [54]
crap-score Calculate CRAP score for a single method with partial coverage 3.3/5 → 4.0/5 🟢 ✅ crap-score; tools: skill, glob / ✅ crap-score; tools: skill ✅ 0.07 ✅ [55]
crap-score Identify riskiest methods across a file 4.0/5 → 5.0/5 🟢 ✅ crap-score; tools: skill ✅ 0.07 ✅
crap-score Generate coverage then compute CRAP score 4.0/5 ⏰ → 4.0/5 ✅ crap-score; tools: skill ✅ 0.07 ✅ [56]
directory-build-organization Organize build infrastructure for a multi-project repo 3.5/5 → 5.0/5 🟢 ✅ directory-build-organization; tools: skill, create, edit, bash / ⚠️ NOT ACTIVATED ✅ 0.20 ✅ [57]
coordinate-components Warehouse dashboard with site selector and live stock alerts 4.0/5 → 4.0/5 ✅ coordinate-components; tools: skill ✅ 0.20 ❌ [58]
coordinate-components Multi-tenant notification hub with cross-component fan-out 1.3/5 → 4.7/5 🟢 ✅ coordinate-components; tools: skill ✅ 0.20 ✅
exp-simd-vectorization Optimize manual min/max with TensorPrimitives 1.0/5 ⏰ → 2.7/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, create, bash, glob / ✅ exp-simd-vectorization; tools: skill, bash, create, glob 🟡 0.21 ✅ [59]
exp-simd-vectorization Optimize manual product with TensorPrimitives 1.0/5 ⏰ → 3.0/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, glob, create, bash 🟡 0.21 ✅ [60]
exp-simd-vectorization No optimization opportunity — dictionary-based lookup service 1.0/5 → 2.3/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, bash, create / ✅ exp-simd-vectorization; tools: skill 🟡 0.21 ✅ [61]
exp-simd-vectorization Optimize int array conditional increment with SIMD 3.7/5 → 3.7/5 ✅ exp-simd-vectorization; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.21 ❌ [62]
exp-simd-vectorization Optimize byte buffer bit reversal with SIMD 4.0/5 → 3.0/5 ⏰ 🔴 ✅ exp-simd-vectorization; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.21 ❌ [63]
incremental-build Analyze incremental build issues 3.0/5 → 3.0/5 ⚠️ NOT ACTIVATED ✅ 0.13 ❌ [64]
migrate-xunit-to-mstest Migrate basic xUnit v2 project to MSTest v4 preserving VSTest 4.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ✅ [65]
migrate-xunit-to-mstest Migrate basic xUnit v3 project to MSTest v4 preserving VSTest 4.7/5 → 4.7/5 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ❌ [66]
migrate-xunit-to-mstest Stop when target framework is unsupported by MSTest v4 1.7/5 → 2.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, bash ✅ 0.11 ✅ [67]
migrate-xunit-to-mstest Convert IClassFixture to ClassInitialize 4.3/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.11 ✅ [68]
migrate-xunit-to-mstest Handle ICollectionFixture explicitly (do not silently widen scope) 3.7/5 → 4.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ✅ [69]
migrate-xunit-to-mstest Convert ITestOutputHelper to TestContext 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ❌ [70]
migrate-xunit-to-mstest Map exception assertions correctly (xUnit Throws -> MSTest ThrowsExactly) 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ❌ [71]
migrate-xunit-to-mstest Convert MemberData and TheoryData to DynamicData 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.11 ❌ [72]
migrate-xunit-to-mstest Convert Skip, Trait, and Timeout 4.0/5 → 4.0/5 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.11 ❌ [73]
migrate-xunit-to-mstest Preserve xUnit parallelization default with [assembly: Parallelize] 3.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ✅
migrate-xunit-to-mstest Convert xUnit v3 TestContext.Current.CancellationToken 4.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ✅ [74]
migrate-xunit-to-mstest Recognize project already on MSTest 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.11 ❌ [75]
migrate-dotnet8-to-dotnet9 App with empty environment variables, ZIP encoding, and keyed DI services 3.0/5 → 3.7/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash, grep / ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep, bash ✅ 0.08 ❌ [76]
migrate-dotnet8-to-dotnet9 C# 13 compiler breaking changes — InlineArray on record, iterator safe context, collection expressions 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: report_intent, skill, view / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅
migrate-dotnet8-to-dotnet9 ASP.NET Core app with DI validation, forwarded headers, and HttpClientFactory casting 2.7/5 → 2.3/5 ⏰ 🔴 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.08 ❌ [77]
migrate-dotnet8-to-dotnet9 EF Core app with migration patterns and Cosmos DB discriminator 3.7/5 → 4.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅ [78]
migrate-dotnet8-to-dotnet9 EF Core Cosmos DB app with existing documents and composite id format 4.0/5 → 2.7/5 ⏰ 🔴 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash, create ✅ 0.08 ❌ [79]
migrate-dotnet8-to-dotnet9 App with JsonDocument null deserialization and BinaryFormatter fallback 4.7/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill / ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep ✅ 0.08 ✅ [80]
migrate-dotnet8-to-dotnet9 CI pipeline with Terminal Logger parsing and version constraints 2.3/5 → 2.7/5 🟢 ℹ️ not activated (expected) / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅ [81]
migrate-dotnet8-to-dotnet9 WinForms app with custom UserControls and PictureBox URL loading 3.7/5 → 4.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, glob, bash, create / ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.08 ✅ [82]
migrate-dotnet8-to-dotnet9 Containerized app with zlib dependency and runtime configuration 3.7/5 → 3.7/5 ⏰ ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ❌ [83]
migrate-dotnet8-to-dotnet9 EF Core Cosmos DB app with discriminator and sync I/O 3.3/5 → 4.7/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash ✅ 0.08 ❌ [84]
migrate-dotnet8-to-dotnet9 Library with String.Trim span overload, keyed services, and InlineArray 5.0/5 → 5.0/5 ✅ migrate-dotnet8-to-dotnet9; tools: skill, grep, bash ✅ 0.08 ❌ [85]
migrate-dotnet8-to-dotnet9 Containerized app with env var precedence reversal and zlib removal 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet8-to-dotnet9; tools: skill, bash / ✅ migrate-dotnet8-to-dotnet9; tools: skill ✅ 0.08 ✅
coverage-analysis Project-wide coverage analysis with existing Cobertura data 2.0/5 → 4.7/5 🟢 ✅ coverage-analysis; tools: skill, view, read_bash, stop_bash, create, bash / ✅ coverage-analysis; tools: skill, view, glob, create, bash, read_bash, stop_bash ✅ 0.10 ✅
coverage-analysis Run coverage from scratch without existing data 4.0/5 → 5.0/5 🟢 ✅ coverage-analysis; tools: skill, glob, create / ✅ coverage-analysis; tools: skill, create ✅ 0.10 ✅
coverage-analysis Coverage plateau diagnosis 3.0/5 → 4.7/5 🟢 ✅ coverage-analysis; tools: skill, view, create, bash, read_bash, stop_bash / ✅ coverage-analysis; tools: skill, view, create, bash, read_bash, stop_bash, glob ✅ 0.10 ✅
build-perf-baseline Establish build performance baseline and recommend optimizations 2.0/5 ⏰ → 3.5/5 ⏰ 🟢 ✅ build-perf-baseline; tools: skill, binlog-binlog_overview, binlog-binlog_diagnose, binlog-binlog_build_graph, binlog-binlog_expensive_tasks, binlog-binlog_analyzer_summary, binlog-binlog_incremental_analysis, binlog-binlog_search, binlog-binlog_explain_property / ⚠️ NOT ACTIVATED 🟡 0.33 ✅ [86]
migrate-dotnet10-to-dotnet11 Console app with compression and TAR operations 1.0/5 ⏰ → 4.7/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, view ✅ 0.06 ✅
migrate-dotnet10-to-dotnet11 C# 15 compiler breaking changes — Span safe-context, nameof, with() 3.0/5 → 4.7/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.06 ✅
migrate-dotnet10-to-dotnet11 EF Core app with Cosmos DB provider using sync APIs 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, bash, grep / ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view ✅ 0.06 ❌ [87]
migrate-dotnet10-to-dotnet11 Deployment to older hardware with minimum requirement changes 3.3/5 → 4.7/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.06 ✅ [88]
migrate-dotnet10-to-dotnet11 Cryptography app using DSA on macOS 3.7/5 → 4.3/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.06 ❌ [89]
migrate-dotnet10-to-dotnet11 Basic TFM update with Docker and global.json 4.3/5 → 4.0/5 🔴 ✅ migrate-dotnet10-to-dotnet11; tools: skill ✅ 0.06 ❌ [90]
migrate-dotnet10-to-dotnet11 C# 15 dynamic operator and ref readonly delegate issues 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, bash, view / ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view ✅ 0.06 ✅
writing-mstest-tests Write unit tests for a service class 4.0/5 → 4.3/5 🟢 ✅ writing-mstest-tests; tools: skill, glob 🟡 0.41 ✅ [91]
writing-mstest-tests Write data-driven tests for a calculator 3.3/5 → 4.7/5 🟢 ✅ writing-mstest-tests; tools: skill, glob 🟡 0.41 ✅
writing-mstest-tests Write async tests with cancellation 3.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.41 ✅
writing-mstest-tests Fix swapped Assert.AreEqual arguments 5.0/5 → 4.3/5 🔴 ⚠️ NOT ACTIVATED 🟡 0.41 ❌
writing-mstest-tests Modernize legacy test patterns 4.7/5 → 3.3/5 ⏰ 🔴 ✅ writing-mstest-tests; tools: skill 🟡 0.41 ❌
writing-mstest-tests Replace ExpectedException with Assert.Throws 2.7/5 → 3.0/5 🟢 ⚠️ NOT ACTIVATED 🟡 0.41 ✅ [92]
writing-mstest-tests Use proper collection assertions 2.3/5 → 4.7/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.41 ✅ [93]
writing-mstest-tests Use proper type assertions instead of casts 4.0/5 → 3.3/5 🔴 ✅ writing-mstest-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.41 ❌ [94]
writing-mstest-tests Set up test lifecycle correctly 2.7/5 → 4.0/5 🟢 ✅ writing-mstest-tests; tools: skill, report_intent 🟡 0.41 ✅
writing-mstest-tests Use DynamicData with ValueTuples over object arrays 3.0/5 → 4.3/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.41 ✅ [95]
writing-mstest-tests Use string assertions for format validation 4.0/5 → 4.3/5 🟢 ✅ writing-mstest-tests; tools: skill, glob / ✅ writing-mstest-tests; tools: skill 🟡 0.41 ✅
writing-mstest-tests Use comparison assertions for boundary testing 2.7/5 → 4.7/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.41 ✅ [96]
writing-mstest-tests Write tests with collection, null, and reference assertions 3.7/5 → 4.0/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.41 ✅ [97]
writing-mstest-tests Configure conditional execution, retry, and cleanup 2.0/5 → 4.7/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.41 ✅
writing-mstest-tests Configure test parallelization and MSTest.Sdk project 3.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.41 ✅
maui-dependency-injection Register services with correct lifetimes in MauiProgram.cs 3.3/5 ⏰ → 5.0/5 🟢 ✅ maui-dependency-injection; tools: report_intent, skill / ✅ maui-dependency-injection; tools: skill ✅ 0.10 ✅ [98]
maui-dependency-injection Shell navigation auto-resolves DI-registered pages 5.0/5 → 5.0/5 ✅ maui-dependency-injection; tools: report_intent, skill / ✅ maui-shell-navigation; maui-dependency-injection; tools: report_intent, skill ✅ 0.10 ❌ [99]
maui-dependency-injection Platform-specific service registration with fallback 3.0/5 → 5.0/5 🟢 ✅ maui-dependency-injection; tools: skill / ✅ maui-dependency-injection; tools: skill, report_intent ✅ 0.10 ✅
maui-dependency-injection Avoid AddScoped pitfall in MAUI 5.0/5 → 5.0/5 ✅ maui-dependency-injection; tools: report_intent, skill / ✅ maui-dependency-injection; tools: skill, report_intent ✅ 0.10 ❌ [100]
configuring-opentelemetry-dotnet Set up OpenTelemetry tracing and metrics with custom spans in ASP.NET Core 4.0/5 → 4.7/5 🟢 ✅ configuring-opentelemetry-dotnet; tools: report_intent, skill / ✅ configuring-opentelemetry-dotnet; tools: skill ✅ 0.15 ✅
configuring-opentelemetry-dotnet Configure all three OpenTelemetry signals with correct OTLP export 3.7/5 → 5.0/5 🟢 ✅ configuring-opentelemetry-dotnet; tools: report_intent, skill / ✅ configuring-opentelemetry-dotnet; tools: skill, report_intent ✅ 0.15 ✅
configuring-opentelemetry-dotnet Propagate trace context across a message queue 5.0/5 → 5.0/5 ✅ configuring-opentelemetry-dotnet; tools: skill ✅ 0.15 ❌ [101]
template-discovery Find template for web API project 2.0/5 → 4.0/5 🟢 ✅ template-discovery; tools: skill, report_intent, bash / ✅ template-discovery; tools: report_intent, skill, bash ✅ 0.19 ✅
template-discovery Inspect template parameters and compare choices 2.7/5 → 4.0/5 🟢 ✅ template-discovery; tools: skill, bash / ⚠️ NOT ACTIVATED ✅ 0.19 ✅ [102]
template-discovery Search NuGet for specialized template 4.3/5 → 4.0/5 🔴 ✅ template-discovery; tools: skill ✅ 0.19 ✅ [103]
template-discovery Resolve ambiguous project intent to multiple candidates 4.0/5 → 3.5/5 🔴 ✅ template-discovery; tools: skill ✅ 0.19 ✅
template-discovery Preview project creation with dry run 3.0/5 → 4.0/5 🟢 ✅ template-discovery; tools: skill / ✅ template-discovery; tools: skill, task ✅ 0.19 ✅ [104]
use-js-interop Auto-saving notepad that survives page reloads 3.7/5 → 4.0/5 🟢 ✅ use-js-interop; tools: skill, edit / ✅ use-js-interop; tools: skill 🟡 0.22 ❌ [105]
use-js-interop User activity tracker that detects idle timeout 4.0/5 → 4.3/5 🟢 ✅ use-js-interop; tools: skill 🟡 0.22 ✅ [106]
use-js-interop Responsive layout that adapts to screen size 3.7/5 → 4.0/5 🟢 ✅ use-js-interop; tools: skill 🟡 0.22 ✅ [107]
use-js-interop Infinite scroll list using IntersectionObserver 3.5/5 → 4.5/5 🟢 ✅ use-js-interop; tools: skill, edit / ✅ use-js-interop; tools: skill 🟡 0.22 ✅ [108]
test-anti-patterns Detect mixed severity anti-patterns in repository service tests 5.0/5 → 5.0/5 ✅ test-anti-patterns; tools: skill, glob / ✅ test-anti-patterns; tools: skill ✅ 0.17 ❌ [109]
test-anti-patterns Detect flakiness indicators and test coupling 5.0/5 → 5.0/5 ✅ test-anti-patterns; tools: skill, glob / ✅ test-anti-patterns; tools: skill, grep, glob ✅ 0.17 ❌ [110]
test-anti-patterns Detect duplicated tests and magic values 4.0/5 → 5.0/5 🟢 ✅ test-anti-patterns; tools: skill, glob / ✅ test-anti-patterns; tools: skill ✅ 0.17 ❌ [111]
test-anti-patterns Recognize well-written tests without inventing false positives 3.7/5 → 4.3/5 🟢 ✅ test-anti-patterns; tools: skill, bash, glob / ✅ test-anti-patterns; tools: skill ✅ 0.17 ❌ [112]
test-anti-patterns Detect coverage-touching pattern across a service facade 5.0/5 → 5.0/5 ✅ test-anti-patterns; tools: skill, glob ✅ 0.17 ❌
test-anti-patterns Detect self-referential assertions in round-trip and identity tests 4.3/5 → 4.7/5 🟢 ✅ test-anti-patterns; tools: skill ✅ 0.17 ❌ [113]
test-anti-patterns Polyglot: detect anti-patterns in a Python pytest suite 4.3/5 → 5.0/5 🟢 ✅ test-anti-patterns; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.17 ✅ [114]
mcp-csharp-publish Publish an MCP server as a NuGet tool package 3.0/5 → 4.0/5 🟢 ✅ mcp-csharp-publish; tools: skill, glob ✅ 0.18 ✅
mcp-csharp-publish Deploy an HTTP MCP server to Azure Container Apps 3.0/5 → 4.3/5 🟢 ✅ mcp-csharp-publish; tools: skill, report_intent, view ✅ 0.18 ✅ [115]
mcp-csharp-publish Publish to the MCP Registry 2.0/5 ⏰ → 3.7/5 🟢 ✅ mcp-csharp-publish; tools: skill, view / ✅ mcp-csharp-publish; tools: skill, view, report_intent ✅ 0.18 ✅ [116]
technology-selection ML.NET classification on tabular data 2.3/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ technology-selection; tools: skill, read_bash, stop_bash / ✅ technology-selection; tools: skill 🟡 0.39 ✅ [117]
technology-selection LLM integration with MEAI abstraction 1.0/5 → 1.0/5 ⚠️ NOT ACTIVATED 🟡 0.39 ✅ [118]
technology-selection Reject LLM for tabular classification 3.0/5 → 4.0/5 🟢 ✅ technology-selection; tools: skill, read_bash, stop_bash / ✅ technology-selection; tools: skill 🟡 0.39 ❌ [119]
technology-selection Agentic workflow with guardrails 2.0/5 → 1.3/5 ⏰ 🔴 ✅ technology-selection; tools: skill, create 🟡 0.39 ❌
technology-selection Natural-language scenario decomposition — RAG chatbot 3.3/5 → 4.0/5 🟢 ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill, edit, bash 🟡 0.39 ✅ [120]
technology-selection RAG pipeline with vector search 3.7/5 → 4.3/5 🟢 ✅ technology-selection; tools: skill 🟡 0.39 ✅
test-tagging Tag an untagged MSTest test suite 3.7/5 → 5.0/5 🟢 ✅ test-tagging; tools: skill / ✅ test-tagging; tools: skill, glob 🟡 0.31 ✅ [121]
test-tagging Tag an untagged xUnit test suite 3.0/5 → 4.0/5 🟢 ✅ test-tagging; tools: skill / ✅ test-tagging; tools: skill, glob 🟡 0.31 ✅ [122]
test-tagging Tag an untagged NUnit test suite 3.3/5 → 5.0/5 🟢 ✅ test-tagging; tools: skill 🟡 0.31 ✅
test-tagging Audit test distribution without modifying files 4.0/5 → 4.3/5 🟢 ✅ test-tagging; tools: skill 🟡 0.31 ❌ [123]
test-tagging Decline request to write new tests 4.0/5 → 3.7/5 🔴 ℹ️ not activated (expected) 🟡 0.31 ❌ [124]
test-tagging Tag a partially-tagged MSTest suite without duplicating existing traits 4.0/5 → 4.0/5 ✅ test-tagging; tools: skill, glob / ✅ test-tagging; tools: skill 🟡 0.31 ✅ [125]
test-tagging Accurately classify NUnit tests with misleading method names 4.7/5 → 5.0/5 🟢 ✅ test-tagging; tools: skill, glob / ⚠️ NOT ACTIVATED 🟡 0.31 ✅ [126]
test-tagging Tag MSTest tests and verify the project still builds 4.3/5 → 4.7/5 🟢 ✅ test-tagging; tools: skill 🟡 0.31 ✅ [127]
test-tagging Report traits for a Go test suite without modifying source 3.3/5 → 4.0/5 🟢 ✅ test-tagging; tools: skill 🟡 0.31 ❌ [128]
mcp-csharp-create Implement MCP tools with proper attributes and DI 3.7/5 → 4.7/5 🟢 ✅ mcp-csharp-create; tools: skill, view ✅ 0.12 ✅ [129]
mcp-csharp-create Create an HTTP MCP server with tools and resources 2.3/5 ⏰ → 4.3/5 🟢 ✅ mcp-csharp-create; tools: skill, grep / ✅ mcp-csharp-create; tools: skill ✅ 0.12 ✅ [130]
mcp-csharp-create Create an MCP server with tools, prompts, and proper logging 1.7/5 ⏰ → 5.0/5 🟢 ✅ mcp-csharp-create; tools: skill, view ✅ 0.12 ✅
binlog-generation Build project with /bl flag 1.0/5 → 5.0/5 🟢 ✅ binlog-generation; tools: skill, glob / ⚠️ NOT ACTIVATED 🟡 0.29 ❌ [131]
binlog-generation Build with /bl in PowerShell 3.0/5 → 5.0/5 🟢 ✅ binlog-generation; tools: skill, glob 🟡 0.29 ❌ [132]
binlog-generation Build multiple configurations with unique binlogs 2.0/5 → 3.0/5 🟢 ✅ binlog-generation; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.29 ✅ [133]
test-gap-analysis Find boundary mutation gaps in tiered discount and shipping logic 5.0/5 → 5.0/5 ✅ test-gap-analysis; tools: skill ✅ 0.13 ❌ [134]
test-gap-analysis Find logic and null-check mutation gaps in access control code 4.3/5 → 5.0/5 🟢 ✅ test-gap-analysis; tools: skill ✅ 0.13 ✅ [135]
test-gap-analysis Acknowledge well-tested code with few surviving mutations 4.0/5 → 4.0/5 ✅ test-gap-analysis; tools: skill ✅ 0.13 ❌ [136]
test-gap-analysis Decline request to write new tests from scratch 3.7/5 → 3.7/5 ℹ️ not activated (expected) ✅ 0.13 ✅ [137]
test-gap-analysis Produce a risk-prioritized report that excludes trivial and generated code 3.3/5 → 4.7/5 🟢 ✅ test-gap-analysis; tools: skill ✅ 0.13 ✅ [138]
test-gap-analysis Flag the Rust ? operator propagation as an unobserved mutation point 4.3/5 → 5.0/5 🟢 ✅ test-gap-analysis; tools: skill, glob / ✅ test-gap-analysis; tools: skill ✅ 0.13 ✅ [139]
maui-theming Add light/dark mode support using AppThemeBinding 4.7/5 → 5.0/5 🟢 ✅ maui-theming; tools: report_intent, skill ✅ 0.07 ❌ [140]
maui-theming Create custom themes with ResourceDictionary switching 4.0/5 → 5.0/5 🟢 ✅ maui-theming; tools: skill ✅ 0.07 ✅
maui-theming Detect and respond to system theme changes 5.0/5 → 5.0/5 ✅ maui-theming; tools: report_intent, skill / ✅ maui-theming; tools: skill ✅ 0.07 ❌ [141]
maui-theming Avoid common theming mistakes 5.0/5 → 5.0/5 ✅ maui-theming; tools: skill, report_intent / ✅ maui-theming; tools: skill ✅ 0.07 ❌ [142]
android-tombstone-symbolication Symbolicate .NET frames in an Android tombstone 3.5/5 ⏰ → 2.5/5 ⏰ 🔴 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ❌ [143]
android-tombstone-symbolication Recognize tombstone with no .NET frames 5.0/5 → 5.0/5 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ❌ [144]
android-tombstone-symbolication Symbolicate CoreCLR frames in an Android tombstone 3.0/5 → 2.5/5 🔴 ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ❌ [145]
android-tombstone-symbolication Recognize NativeAOT tombstone with app binary and libSystem.Native.so 3.0/5 → 3.7/5 ⏰ 🟢 ✅ android-tombstone-symbolication; tools: skill, bash, read_bash ✅ 0.15 ❌ [146]
android-tombstone-symbolication Symbolicate multi-thread tombstone 3.0/5 ⏰ → 4.3/5 🟢 ✅ android-tombstone-symbolication; tools: skill / ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ✅ [147]
android-tombstone-symbolication Handle .NET frames with no BuildId metadata 4.0/5 → 5.0/5 🟢 ✅ android-tombstone-symbolication; tools: skill, bash ✅ 0.15 ✅ [148]
android-tombstone-symbolication Symbolicate tombstone with multiple .NET libraries and different BuildIds 3.7/5 → 3.7/5 ✅ android-tombstone-symbolication; tools: skill / ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ❌ [149]
android-tombstone-symbolication Reject iOS crash log as wrong format 4.0/5 → 4.7/5 🟢 ℹ️ not activated (expected) ✅ 0.15 ❌ [150]
build-perf-diagnostics Diagnose slow build for a small project 4.5/5 → 4.5/5 ⚠️ NOT ACTIVATED 🟡 0.27 ❌ [151]
check-bin-obj-clash Diagnose bin/obj output path clashes 4.0/5 → 5.0/5 🟢 ✅ check-bin-obj-clash; tools: glob, skill, binlog-binlog_overview, binlog-binlog_double_writes, binlog-binlog_evaluations, binlog-binlog_properties, binlog-binlog_evaluation_properties, binlog-binlog_evaluation_global_properties, edit / ✅ check-bin-obj-clash; tools: skill, binlog-binlog_overview, binlog-binlog_errors, binlog-binlog_double_writes, binlog-binlog_evaluations, binlog-binlog_evaluation_properties, glob, binlog-binlog_properties, binlog-binlog_evaluation_global_properties ✅ 0.11 ✅ [152]
migrate-nullable-references Enable NRT in a small library with mixed nullability 5.0/5 → 5.0/5 ✅ migrate-nullable-references; tools: skill ✅ 0.15 ❌ [153]
migrate-nullable-references File-by-file migration: only modify the targeted file 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED ✅ 0.15 ❌ [154]
migrate-nullable-references Enable NRT in ASP.NET Core Web API with EF Core 4.0/5 → 4.7/5 🟢 ⚠️ NOT ACTIVATED ✅ 0.15 ✅ [155]
fetch-and-send-data Recipe browser with resilient data loading 3.0/5 → 4.0/5 🟢 ✅ fetch-and-send-data; tools: skill 🟡 0.23 ✅
fetch-and-send-data Real-time shipment tracker with Auto interactivity 4.0/5 → 4.0/5 ✅ fetch-and-send-data; tools: skill 🟡 0.23 ✅ [156]
author-component Author a data-loading search component 3.3/5 → 4.7/5 🟢 ✅ author-component; tools: skill, view, bash ✅ 0.18 ✅ [157]
author-component Author a multi-step wizard with async validation and shared state 3.7/5 ⏰ → 3.0/5 ⏰ 🔴 ✅ author-component; tools: skill, view ✅ 0.18 ❌ [158]
author-component Author a generic data table component 4.0/5 → 3.3/5 ⏰ 🔴 ✅ author-component; tools: skill, view, bash ✅ 0.18 ❌ [159]
author-component Author a real-time notification badge component 2.0/5 → 3.3/5 ⏰ 🟢 ✅ author-component; tools: skill, view, bash / ✅ author-component; tools: skill, view ✅ 0.18 ✅ [160]
author-component Author a sortable list with code-behind pattern 4.0/5 → 4.7/5 ⏰ 🟢 ✅ author-component; tools: skill, bash ✅ 0.18 ✅ [161]
msbuild-modernization Modernize legacy project to SDK-style 4.0/5 ⏰ → 3.7/5 ⏰ 🔴 ✅ msbuild-modernization; tools: skill, glob / ✅ msbuild-modernization; tools: skill ✅ 0.06 ❌ [162]
migrate-dotnet9-to-dotnet10 Console app with System.Linq.Async, SIGTERM, and BufferedStream 5.0/5 → 4.3/5 🔴 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view, grep ✅ 0.05 ❌
migrate-dotnet9-to-dotnet10 Expression tree code broken by C# 14 span overload resolution 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, bash, grep, view ✅ 0.05 ❌ [163]
migrate-dotnet9-to-dotnet10 ASP.NET Core app with WebHostBuilder, OpenAPI, and forwarded headers 4.3/5 → 4.7/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.05 ❌ [164]
migrate-dotnet9-to-dotnet10 ASP.NET Core app with OpenAPI transformers using Microsoft.OpenApi v1 APIs 3.3/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep, view, bash / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view, grep ✅ 0.05 ✅ [165]
migrate-dotnet9-to-dotnet10 EF Core app with Azure SQL JSON columns and parameterized collections 2.3/5 → 4.7/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.05 ✅ [166]
migrate-dotnet9-to-dotnet10 EF Core app with dynamic ExecuteUpdate and complex types 4.3/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.05 ❌ [167]
migrate-dotnet9-to-dotnet10 SQLite app with DateTimeOffset timezone handling 2.3/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view, grep ✅ 0.05 ✅
migrate-dotnet9-to-dotnet10 Worker service with config null array binding and ProviderAlias assembly change 3.7/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.05 ✅ [168]
migrate-dotnet9-to-dotnet10 Cryptography app with OpenSSL, X.509, and Rfc2898DeriveBytes 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.05 ❌ [169]
migrate-dotnet9-to-dotnet10 SDK and NuGet obscure tooling changes 5.0/5 → 4.0/5 🔴 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.05 ❌
migrate-dotnet9-to-dotnet10 JSON polymorphism with conflicting property names and XmlSerializer 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.05 ✅
migrate-dotnet9-to-dotnet10 WinForms and WPF desktop app with System.Drawing and DynamicResource 2.7/5 → 4.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view, report_intent ✅ 0.05 ❌ [170]
migrate-dotnet9-to-dotnet10 Containerized single-file app with P/Invoke and IDispatchEx 3.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view ✅ 0.05 ✅ [171]
migrate-dotnet9-to-dotnet10 App using SslStream properties and SystemEvents 2.7/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill ✅ 0.05 ✅ [172]
migrate-dotnet9-to-dotnet10 Library with NuGet auditing, transitive deps, and InlineArray 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view, grep / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.05 ✅ [173]
migrate-dotnet9-to-dotnet10 C# 14 compiler breaking changes — field keyword, extension keyword, disposal 4.3/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view ✅ 0.05 ✅ [174]
migrate-dotnet9-to-dotnet10 Blazor WASM app with generic math shift masking and tar operations 3.3/5 → 3.7/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view, grep ✅ 0.05 ❌ [175]
assertion-quality Identify low assertion diversity in equality-dominated test suite 3.0/5 → 2.3/5 ⏰ 🔴 ✅ assertion-quality; tools: skill, glob / ✅ assertion-quality; tools: skill 🟡 0.22 ❌ [176]
assertion-quality Flag assertion-free tests and trivial-only assertions 4.0/5 → 4.0/5 ✅ assertion-quality; tools: skill, glob 🟡 0.22 ❌ [177]
assertion-quality Recognize well-diversified assertion usage 4.0/5 → 4.7/5 🟢 ✅ assertion-quality; tools: skill, glob 🟡 0.22 ✅
assertion-quality Identify self-referential assertions in identity and round-trip tests 4.3/5 → 4.0/5 🔴 ✅ assertion-quality; tools: skill, glob / ✅ assertion-quality; tools: skill 🟡 0.22 ❌ [178]
assertion-quality Decline request to write new tests from scratch 3.7/5 ⏰ → 3.0/5 ⏰ 🔴 ℹ️ not activated (expected) 🟡 0.22 ❌
assertion-quality Polyglot: evaluate shallow assertions in a Jest/TypeScript OrderService suite 4.7/5 → 5.0/5 🟢 ✅ assertion-quality; tools: skill, glob 🟡 0.22 ❌ [179]
plan-ui-change Project management Kanban board 2.0/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, edit ✅ 0.16 ✅
plan-ui-change E-commerce product catalog with filters and pagination 2.7/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, grep / ✅ plan-ui-change; tools: skill, edit, grep ✅ 0.16 ✅
plan-ui-change Multi-step job application wizard 2.0/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, edit ✅ 0.16 ✅
plan-ui-change Application settings page with nested tab panels 3.0/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill ✅ 0.16 ✅
plan-ui-change Team chat interface with message threads 2.7/5 → 4.0/5 🟢 ✅ plan-ui-change; tools: skill, edit / ✅ plan-ui-change; tools: skill, edit, grep ✅ 0.16 ✅
configure-auth Login and account management in a globally interactive app 4.3/5 → 5.0/5 🟢 ✅ configure-auth; tools: skill ✅ 0.06 ✅ [180]
configure-auth Multi-tier app with WebAssembly auth 3.0/5 → 4.5/5 🟢 ✅ configure-auth; tools: skill, glob / ✅ configure-auth; tools: skill ✅ 0.06 ✅
apple-crash-symbolication Parse .NET frames and locate dSYMs from an iOS crash log 3.0/5 → 4.0/5 🟢 ✅ apple-crash-symbolication; tools: skill, bash ✅ 0.17 ✅ [181]
apple-crash-symbolication Investigate root cause of a .NET MAUI iOS crash 3.0/5 → 2.5/5 ⏰ 🔴 ✅ apple-crash-symbolication; tools: skill, bash ✅ 0.17 ✅ [182]
apple-crash-symbolication Reject Android tombstone passed as iOS crash log 4.0/5 → 4.3/5 🟢 ℹ️ not activated (expected) ✅ 0.17 ✅ [183]
nuget-trusted-publishing Set up trusted publishing for a new NuGet library 2.7/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ nuget-trusted-publishing; tools: skill, view, create / ✅ nuget-trusted-publishing; tools: skill, view ✅ 0.20 ❌
nuget-trusted-publishing Set up NuGet publishing without mentioning trusted publishing 3.0/5 → 4.3/5 🟢 ✅ nuget-trusted-publishing; tools: skill, report_intent, view ✅ 0.20 ❌ [184]
nuget-trusted-publishing Migrate existing workflow from API key to trusted publishing 3.0/5 → 4.0/5 🟢 ✅ nuget-trusted-publishing; tools: skill, report_intent, glob ✅ 0.20 ✅ [185]
mcp-csharp-test Write unit and integration tests for an MCP server 2.7/5 → 2.0/5 ⏰ 🔴 ✅ mcp-csharp-test; tools: skill, report_intent, view 🟡 0.23 ❌ [186]
mcp-csharp-test Test an HTTP MCP server with WebApplicationFactory 3.7/5 → 3.7/5 ⏰ ✅ mcp-csharp-test; tools: skill, report_intent, view 🟡 0.23 ❌ [187]
mcp-csharp-test Create evaluations for an MCP server 1.7/5 ⏰ → 2.3/5 ⏰ 🟢 ✅ mcp-csharp-test; tools: skill, view 🟡 0.23 ❌ [188]
dump-collect Configure automatic crash dumps for CoreCLR app on Linux 4.3/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.28 ❌ [189]
dump-collect Set up NativeAOT crash dumps with createdump in Kubernetes 2.3/5 ⏰ → 5.0/5 🟢 ✅ dump-collect; tools: skill, view, report_intent 🟡 0.28 ✅ [190]
dump-collect Recover crash dump from macOS NativeAOT without createdump 3.3/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ⚠️ NOT ACTIVATED 🟡 0.28 ❌ [191]
dump-collect Configure CoreCLR dump collection in Alpine Docker as non-root 3.0/5 → 3.7/5 ⏰ 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.28 ✅ [192]
dump-collect Advisory: macOS NativeAOT crash dump recovery steps 4.0/5 → 2.0/5 ⏰ 🔴 ✅ dump-collect; tools: skill, view 🟡 0.28 ✅ [193]
dump-collect Advisory: CoreCLR Alpine Docker non-root configuration 3.7/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.28 ✅ [194]
dump-collect Advisory: NativeAOT Kubernetes dump collection setup 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.28 ✅
dump-collect Detect runtime and configure crash dumps for unknown .NET app on Linux 4.0/5 → 4.0/5 ✅ dump-collect; tools: skill, view 🟡 0.28 ❌ [195]
dump-collect Decline dump analysis request 1.7/5 ⏰ → 4.0/5 🟢 ℹ️ not activated (expected) 🟡 0.28 ✅ [196]
minimal-api-file-upload Implement secure file upload in ASP.NET Core 8 minimal API 3.0/5 → 5.0/5 🟢 ✅ minimal-api-file-upload; tools: report_intent, skill / ✅ minimal-api-file-upload; tools: skill ✅ 0.06 ✅
minimal-api-file-upload Upload multiple files with metadata in minimal API 4.0/5 → 5.0/5 🟢 ✅ minimal-api-file-upload; tools: skill, report_intent / ✅ minimal-api-file-upload; tools: skill ✅ 0.06 ✅
minimal-api-file-upload Stream very large file uploads without buffering 5.0/5 → 5.0/5 ✅ minimal-api-file-upload; tools: skill ✅ 0.06 ❌ [197]
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 9) 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.10 ✅
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 10) 1.0/5 → 2.3/5 ⏰ 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.10 ✅ [198]
mtp-hot-reload Enable hot reload when package already installed 2.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.10 ✅
mtp-hot-reload Suggest launchSettings.json configuration for hot reload 1.0/5 → 4.3/5 🟢 ✅ mtp-hot-reload; tools: skill, bash, create ✅ 0.10 ✅
mtp-hot-reload Use dotnet run not dotnet test for hot reload 2.3/5 → 3.3/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.10 ✅ [199]
mtp-hot-reload Negative: VSTest project cannot use MTP hot reload 2.0/5 → 2.0/5 ✅ mtp-hot-reload; tools: skill, edit, bash, create ✅ 0.10 ❌ [200]
mtp-hot-reload Run specific failing test with hot reload filter 1.0/5 → 4.7/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.10 ✅
including-generated-files Diagnose generated file inclusion failure 3.3/5 ⏰ → 4.3/5 ⏰ 🟢 ✅ including-generated-files; tools: skill ✅ 0.17 ❌ [201]
build-parallelism Analyze build parallelism bottlenecks 2.7/5 ⏰ → 3.0/5 ⏰ 🟢 ✅ build-parallelism; tools: glob, binlog-binlog_build_graph, binlog-binlog_overview, binlog-binlog_errors, edit, binlog-binlog_expensive_projects, binlog-binlog_projects, skill / ⚠️ NOT ACTIVATED ✅ 0.15 ✅ [202]

[1] ⚠️ High run-to-run variance (CV=341%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -74.1% due to: quality, judgment, tokens (36960 → 64292)
[2] ⚠️ High run-to-run variance (CV=209%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -67.7% due to: quality, judgment, tokens (39288 → 51565), time (52.7s → 73.0s)
[3] ⚠️ High run-to-run variance (CV=92%) — consider re-running with --runs 5
[4] ⚠️ High run-to-run variance (CV=87%) — consider re-running with --runs 5
[5] ⚠️ High run-to-run variance (CV=289%) — consider re-running with --runs 5
[6] ⚠️ High run-to-run variance (CV=76%) — consider re-running with --runs 5
[7] ⚠️ High run-to-run variance (CV=146%) — consider re-running with --runs 5
[8] ⚠️ High run-to-run variance (CV=151%) — consider re-running with --runs 5
[9] ⚠️ High run-to-run variance (CV=100%) — consider re-running with --runs 5
[10] (Plugin) Quality unchanged but weighted score is -4.8% due to: tokens (66446 → 142692)
[11] ⚠️ High run-to-run variance (CV=583%) — consider re-running with --runs 5
[12] ⚠️ High run-to-run variance (CV=156%) — consider re-running with --runs 5
[13] ⚠️ High run-to-run variance (CV=1061%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -23.9% due to: judgment, quality
[14] ⚠️ High run-to-run variance (CV=672%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -19.5% due to: judgment, quality, tokens (57919 → 84894), tool calls (7 → 9)
[15] ⚠️ High run-to-run variance (CV=188%) — consider re-running with --runs 5
[16] ⚠️ High run-to-run variance (CV=73%) — consider re-running with --runs 5
[17] ⚠️ High run-to-run variance (CV=367%) — consider re-running with --runs 5
[18] ⚠️ High run-to-run variance (CV=344%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -63.6% due to: quality, judgment, time (36.1s → 98.6s), tokens (27629 → 33668)
[19] ⚠️ High run-to-run variance (CV=88%) — consider re-running with --runs 5
[20] ⚠️ High run-to-run variance (CV=184%) — consider re-running with --runs 5
[21] ⚠️ High run-to-run variance (CV=181%) — consider re-running with --runs 5
[22] ⚠️ High run-to-run variance (CV=1195%) — consider re-running with --runs 5
[23] ⚠️ High run-to-run variance (CV=116%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -3.0% due to: completion (✓ → ✗), tokens (12771 → 82691), tool calls (0 → 8), time (31.5s → 109.7s)
[24] ⚠️ High run-to-run variance (CV=638%) — consider re-running with --runs 5
[25] ⚠️ High run-to-run variance (CV=103%) — consider re-running with --runs 5
[26] ⚠️ High run-to-run variance (CV=320%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -42.9% due to: judgment, quality, tokens (67990 → 89348)
[27] ⚠️ High run-to-run variance (CV=71%) — consider re-running with --runs 5
[28] ⚠️ High run-to-run variance (CV=268%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -0.2% due to: tokens (107665 → 118525)
[29] ⚠️ High run-to-run variance (CV=616%) — consider re-running with --runs 5
[30] ⚠️ High run-to-run variance (CV=214%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -20.6% due to: judgment, quality, tokens (86348 → 119172), time (101.6s → 159.1s)
[31] ⚠️ High run-to-run variance (CV=197%) — consider re-running with --runs 5
[32] ⚠️ High run-to-run variance (CV=168%) — consider re-running with --runs 5
[33] ⚠️ High run-to-run variance (CV=271%) — consider re-running with --runs 5
[34] ⚠️ High run-to-run variance (CV=238%) — consider re-running with --runs 5
[35] ⚠️ High run-to-run variance (CV=151%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -1.6% due to: tool calls (1 → 2), tokens (24944 → 34934), time (27.4s → 39.6s)
[36] ⚠️ High run-to-run variance (CV=90%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -8.2% due to: tokens (24962 → 53195), tool calls (1 → 3), time (33.8s → 42.7s)
[37] ⚠️ High run-to-run variance (CV=149%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -33.0% due to: quality, judgment
[38] ⚠️ High run-to-run variance (CV=63%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -8.7% due to: tokens (12660 → 22001), tool calls (0 → 2), time (11.8s → 25.7s)
[39] ⚠️ High run-to-run variance (CV=92%) — consider re-running with --runs 5
[40] ⚠️ High run-to-run variance (CV=172%) — consider re-running with --runs 5
[41] ⚠️ High run-to-run variance (CV=97%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -6.8% due to: tokens (25203 → 40608), time (19.0s → 41.7s), tool calls (2 → 3)
[42] ⚠️ High run-to-run variance (CV=119%) — consider re-running with --runs 5
[43] ⚠️ High run-to-run variance (CV=17689%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +2.1% due to: time (50.5s → 25.6s), tool calls (6 → 4)
[44] ⚠️ High run-to-run variance (CV=612%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -13.9% due to: judgment, tokens (25593 → 34974)
[45] ⚠️ High run-to-run variance (CV=173%) — consider re-running with --runs 5. (Isolated) Quality dropped but weighted score is +2.8% due to: efficiency metrics
[46] ⚠️ High run-to-run variance (CV=77%) — consider re-running with --runs 5
[47] ⚠️ High run-to-run variance (CV=51%) — consider re-running with --runs 5
[48] ⚠️ High run-to-run variance (CV=135%) — consider re-running with --runs 5
[49] ⚠️ High run-to-run variance (CV=304%) — consider re-running with --runs 5
[50] ⚠️ High run-to-run variance (CV=71%) — consider re-running with --runs 5
[51] ⚠️ High run-to-run variance (CV=287%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -41.0% due to: judgment, quality, tokens (13015 → 26381), tool calls (0 → 2), time (19.3s → 93.7s)
[52] ⚠️ High run-to-run variance (CV=62%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -26.4% due to: judgment, quality, tokens (12761 → 23157), tool calls (0 → 1), time (17.2s → 71.6s)
[53] ⚠️ High run-to-run variance (CV=292%) — consider re-running with --runs 5
[54] ⚠️ High run-to-run variance (CV=191%) — consider re-running with --runs 5
[55] ⚠️ High run-to-run variance (CV=147%) — consider re-running with --runs 5
[56] ⚠️ High run-to-run variance (CV=174%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +7.3% due to: completion (✗ → ✓)
[57] ⚠️ High run-to-run variance (CV=421%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +2.0% due to: efficiency metrics
[58] (Isolated) Quality unchanged but weighted score is -1.3% due to: tokens (180317 → 342416), time (202.3s → 376.0s)
[59] ⚠️ High run-to-run variance (CV=139%) — consider re-running with --runs 5
[60] ⚠️ High run-to-run variance (CV=108%) — consider re-running with --runs 5
[61] ⚠️ High run-to-run variance (CV=449%) — consider re-running with --runs 5
[62] ⚠️ High run-to-run variance (CV=77%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -5.4% due to: tokens (39839 → 68086), time (45.3s → 63.2s), tool calls (3 → 4)
[63] ⚠️ High run-to-run variance (CV=70%) — consider re-running with --runs 5
[64] ⚠️ High run-to-run variance (CV=114%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -16.6% due to: judgment, quality, tokens (26116 → 39725)
[65] ⚠️ High run-to-run variance (CV=554%) — consider re-running with --runs 5
[66] ⚠️ High run-to-run variance (CV=86%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -20.6% due to: judgment, tokens (76443 → 160326), quality
[67] ⚠️ High run-to-run variance (CV=86%) — consider re-running with --runs 5
[68] ⚠️ High run-to-run variance (CV=1147%) — consider re-running with --runs 5
[69] ⚠️ High run-to-run variance (CV=119%) — consider re-running with --runs 5
[70] ⚠️ High run-to-run variance (CV=61%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -7.1% due to: tokens (68942 → 209399), time (30.1s → 74.1s), tool calls (8 → 12)
[71] (Isolated) Quality unchanged but weighted score is -6.0% due to: tokens (73040 → 157524), tool calls (8 → 10)
[72] (Plugin) Quality unchanged but weighted score is -7.0% due to: tokens (69915 → 196026), time (66.7s → 94.4s), tool calls (8 → 11)
[73] ⚠️ High run-to-run variance (CV=68%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -6.4% due to: tokens (99416 → 347759), tool calls (10 → 16), time (102.7s → 164.0s)
[74] ⚠️ High run-to-run variance (CV=78%) — consider re-running with --runs 5
[75] (Plugin) Quality unchanged but weighted score is -1.1% due to: tokens (34348 → 68703)
[76] ⚠️ High run-to-run variance (CV=565%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -29.7% due to: judgment, quality, tokens (42028 → 231273), tool calls (10 → 23), time (106.1s → 200.7s)
[77] ⚠️ High run-to-run variance (CV=137%) — consider re-running with --runs 5
[78] ⚠️ High run-to-run variance (CV=183%) — consider re-running with --runs 5
[79] ⚠️ High run-to-run variance (CV=84%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.4% due to: tokens (201063 → 325842), time (206.2s → 293.8s), tool calls (18 → 22)
[80] ⚠️ High run-to-run variance (CV=1790%) — consider re-running with --runs 5
[81] ⚠️ High run-to-run variance (CV=104%) — consider re-running with --runs 5
[82] ⚠️ High run-to-run variance (CV=5082%) — consider re-running with --runs 5
[83] ⚠️ High run-to-run variance (CV=206%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -76.9% due to: quality, judgment, tokens (60429 → 108484), time (50.6s → 190.0s)
[84] ⚠️ High run-to-run variance (CV=164%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -11.6% due to: judgment, quality
[85] ⚠️ High run-to-run variance (CV=108%) — consider re-running with --runs 5
[86] ⚠️ High run-to-run variance (CV=146%) — consider re-running with --runs 5
[87] (Isolated) Quality improved but weighted score is -10.0% due to: tokens (13335 → 50461), tool calls (0 → 4), time (27.8s → 60.4s)
[88] ⚠️ High run-to-run variance (CV=61%) — consider re-running with --runs 5
[89] ⚠️ High run-to-run variance (CV=1576%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -21.5% due to: judgment, tokens (13588 → 49031), tool calls (0 → 4), time (43.6s → 77.6s)
[90] ⚠️ High run-to-run variance (CV=174%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -7.2% due to: tokens (12705 → 33011), tool calls (0 → 1), time (13.1s → 30.9s)
[91] ⚠️ High run-to-run variance (CV=287%) — consider re-running with --runs 5
[92] ⚠️ High run-to-run variance (CV=109%) — consider re-running with --runs 5
[93] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5
[94] ⚠️ High run-to-run variance (CV=74%) — consider re-running with --runs 5
[95] ⚠️ High run-to-run variance (CV=241%) — consider re-running with --runs 5
[96] ⚠️ High run-to-run variance (CV=55%) — consider re-running with --runs 5
[97] ⚠️ High run-to-run variance (CV=97%) — consider re-running with --runs 5
[98] ⚠️ High run-to-run variance (CV=145%) — consider re-running with --runs 5
[99] ⚠️ High run-to-run variance (CV=52%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -19.4% due to: judgment, tokens (12845 → 28951), tool calls (0 → 2)
[100] ⚠️ High run-to-run variance (CV=135%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -20.7% due to: judgment, tokens (12682 → 28801), tool calls (0 → 2), time (35.4s → 51.9s)
[101] ⚠️ High run-to-run variance (CV=60%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -21.6% due to: judgment, tokens (13267 → 29142), tool calls (0 → 1), time (26.9s → 49.0s)
[102] ⚠️ High run-to-run variance (CV=82%) — consider re-running with --runs 5
[103] ⚠️ High run-to-run variance (CV=162%) — consider re-running with --runs 5
[104] ⚠️ High run-to-run variance (CV=52%) — consider re-running with --runs 5
[105] ⚠️ High run-to-run variance (CV=348%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -2.4% due to: quality, tokens (107145 → 125246)
[106] ⚠️ High run-to-run variance (CV=94%) — consider re-running with --runs 5
[107] ⚠️ High run-to-run variance (CV=74%) — consider re-running with --runs 5
[108] ⚠️ High run-to-run variance (CV=164%) — consider re-running with --runs 5
[109] (Plugin) Quality unchanged but weighted score is -9.8% due to: tokens (27912 → 67149), tool calls (3 → 6), time (54.3s → 105.3s)
[110] ⚠️ High run-to-run variance (CV=121%) — consider re-running with --runs 5
[111] ⚠️ High run-to-run variance (CV=232%) — consider re-running with --runs 5
[112] (Isolated) Quality improved but weighted score is -3.1% due to: tokens (35470 → 65307), tool calls (3 → 7)
[113] ⚠️ High run-to-run variance (CV=84%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -21.0% due to: judgment, tokens (42392 → 75719), quality, time (60.1s → 114.8s), tool calls (5 → 6)
[114] ⚠️ High run-to-run variance (CV=52%) — consider re-running with --runs 5
[115] ⚠️ High run-to-run variance (CV=1302%) — consider re-running with --runs 5
[116] ⚠️ High run-to-run variance (CV=87%) — consider re-running with --runs 5
[117] ⚠️ High run-to-run variance (CV=161%) — consider re-running with --runs 5
[118] ⚠️ High run-to-run variance (CV=569%) — consider re-running with --runs 5
[119] ⚠️ High run-to-run variance (CV=441%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -20.0% due to: judgment, tokens (111065 → 546068), tool calls (12 → 26), time (85.6s → 271.7s)
[120] ⚠️ High run-to-run variance (CV=1939%) — consider re-running with --runs 5
[121] ⚠️ High run-to-run variance (CV=57%) — consider re-running with --runs 5
[122] ⚠️ High run-to-run variance (CV=129%) — consider re-running with --runs 5
[123] ⚠️ High run-to-run variance (CV=94%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -5.3% due to: quality, tokens (43485 → 53225)
[124] ⚠️ High run-to-run variance (CV=65%) — consider re-running with --runs 5
[125] ⚠️ High run-to-run variance (CV=51%) — consider re-running with --runs 5
[126] ⚠️ High run-to-run variance (CV=124%) — consider re-running with --runs 5
[127] ⚠️ High run-to-run variance (CV=142%) — consider re-running with --runs 5
[128] ⚠️ High run-to-run variance (CV=211%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -10.4% due to: tokens (25859 → 84649), time (14.6s → 32.5s), tool calls (3 → 5), quality
[129] ⚠️ High run-to-run variance (CV=229%) — consider re-running with --runs 5
[130] ⚠️ High run-to-run variance (CV=86%) — consider re-running with --runs 5
[131] ⚠️ High run-to-run variance (CV=4541%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -0.1% due to: tokens (38562 → 46508)
[132] ⚠️ High run-to-run variance (CV=132%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -7.5% due to: tokens (25509 → 79878), tool calls (2 → 3), time (27.8s → 41.5s)
[133] ⚠️ High run-to-run variance (CV=191%) — consider re-running with --runs 5
[134] (Plugin) Quality unchanged but weighted score is -6.4% due to: tokens (41205 → 87381), time (79.7s → 109.8s), tool calls (5 → 6)
[135] ⚠️ High run-to-run variance (CV=127%) — consider re-running with --runs 5
[136] ⚠️ High run-to-run variance (CV=59%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -8.8% due to: judgment, quality
[137] ⚠️ High run-to-run variance (CV=115%) — consider re-running with --runs 5
[138] ⚠️ High run-to-run variance (CV=57%) — consider re-running with --runs 5
[139] ⚠️ High run-to-run variance (CV=163%) — consider re-running with --runs 5
[140] (Plugin) Quality unchanged but weighted score is -8.4% due to: tokens (13153 → 33064), tool calls (0 → 2), time (20.5s → 42.7s)
[141] ⚠️ High run-to-run variance (CV=133%) — consider re-running with --runs 5
[142] ⚠️ High run-to-run variance (CV=68%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -24.5% due to: judgment, quality, tokens (17118 → 29123), tool calls (0 → 2), time (21.3s → 51.5s)
[143] ⚠️ High run-to-run variance (CV=319%) — consider re-running with --runs 5
[144] (Isolated) Quality unchanged but weighted score is -7.3% due to: tokens (26279 → 44996), time (39.8s → 90.3s), tool calls (2 → 3)
[145] ⚠️ High run-to-run variance (CV=254%) — consider re-running with --runs 5
[146] ⚠️ High run-to-run variance (CV=156%) — consider re-running with --runs 5
[147] ⚠️ High run-to-run variance (CV=393%) — consider re-running with --runs 5
[148] ⚠️ High run-to-run variance (CV=135%) — consider re-running with --runs 5
[149] ⚠️ High run-to-run variance (CV=142%) — consider re-running with --runs 5
[150] ⚠️ High run-to-run variance (CV=479%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -28.3% due to: judgment, quality, tokens (26651 → 49655), tool calls (2 → 3), time (22.0s → 28.0s)
[151] ⚠️ High run-to-run variance (CV=86%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -2.0% due to: tokens (27218 → 233011), tool calls (5 → 15), time (28.4s → 75.7s)
[152] ⚠️ High run-to-run variance (CV=116%) — consider re-running with --runs 5
[153] (Plugin) Quality unchanged but weighted score is -5.1% due to: tokens (91985 → 172430)
[154] ⚠️ High run-to-run variance (CV=60%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.4% due to: time (107.4s → 204.9s), tokens (98412 → 115322)
[155] ⚠️ High run-to-run variance (CV=362%) — consider re-running with --runs 5
[156] ⚠️ High run-to-run variance (CV=10374%) — consider re-running with --runs 5
[157] ⚠️ High run-to-run variance (CV=57%) — consider re-running with --runs 5
[158] ⚠️ High run-to-run variance (CV=85%) — consider re-running with --runs 5
[159] ⚠️ High run-to-run variance (CV=75%) — consider re-running with --runs 5
[160] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[161] ⚠️ High run-to-run variance (CV=157%) — consider re-running with --runs 5
[162] ⚠️ High run-to-run variance (CV=122%) — consider re-running with --runs 5
[163] ⚠️ High run-to-run variance (CV=80%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -28.2% due to: judgment, quality, tokens (14594 → 89196), tool calls (0 → 5), time (76.0s → 96.6s)
[164] (Isolated) Quality improved but weighted score is -30.0% due to: judgment, quality, tokens (13486 → 54646), tool calls (0 → 3), time (26.2s → 57.9s)
[165] ⚠️ High run-to-run variance (CV=270%) — consider re-running with --runs 5
[166] ⚠️ High run-to-run variance (CV=97%) — consider re-running with --runs 5
[167] (Plugin) Quality improved but weighted score is -5.6% due to: tokens (32072 → 58458), tool calls (2 → 3)
[168] ⚠️ High run-to-run variance (CV=50%) — consider re-running with --runs 5
[169] ⚠️ High run-to-run variance (CV=108%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -13.5% due to: judgment, quality
[170] ⚠️ High run-to-run variance (CV=133%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -17.7% due to: judgment, tokens (30971 → 53574), quality
[171] ⚠️ High run-to-run variance (CV=87%) — consider re-running with --runs 5
[172] ⚠️ High run-to-run variance (CV=95%) — consider re-running with --runs 5
[173] ⚠️ High run-to-run variance (CV=279%) — consider re-running with --runs 5
[174] ⚠️ High run-to-run variance (CV=956%) — consider re-running with --runs 5
[175] ⚠️ High run-to-run variance (CV=575%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.7% due to: tokens (26357 → 85545), tool calls (2 → 8)
[176] ⚠️ High run-to-run variance (CV=109%) — consider re-running with --runs 5
[177] (Plugin) Quality unchanged but weighted score is -7.2% due to: tokens (26477 → 67277), tool calls (2 → 3), time (37.0s → 51.5s)
[178] ⚠️ High run-to-run variance (CV=382%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -0.1% due to: tokens (32329 → 61946), time (58.2s → 137.3s), tool calls (2 → 3)
[179] ⚠️ High run-to-run variance (CV=481%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -2.5% due to: tokens (27064 → 71907), time (32.6s → 65.3s), tool calls (3 → 5)
[180] ⚠️ High run-to-run variance (CV=92%) — consider re-running with --runs 5
[181] ⚠️ High run-to-run variance (CV=62%) — consider re-running with --runs 5
[182] ⚠️ High run-to-run variance (CV=373%) — consider re-running with --runs 5
[183] ⚠️ High run-to-run variance (CV=346%) — consider re-running with --runs 5
[184] ⚠️ High run-to-run variance (CV=1165%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -59.0% due to: quality, judgment, tokens (12991 → 40901), tool calls (0 → 3), time (23.8s → 86.5s)
[185] ⚠️ High run-to-run variance (CV=2131%) — consider re-running with --runs 5
[186] ⚠️ High run-to-run variance (CV=179%) — consider re-running with --runs 5
[187] ⚠️ High run-to-run variance (CV=242%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -9.6% due to: tokens (13240 → 39550), tool calls (0 → 3), time (29.9s → 108.6s)
[188] ⚠️ High run-to-run variance (CV=585%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -33.9% due to: judgment, quality, errors (0 → 1)
[189] ⚠️ High run-to-run variance (CV=190%) — consider re-running with --runs 5
[190] ⚠️ High run-to-run variance (CV=738%) — consider re-running with --runs 5
[191] ⚠️ High run-to-run variance (CV=110%) — consider re-running with --runs 5
[192] ⚠️ High run-to-run variance (CV=3344%) — consider re-running with --runs 5
[193] ⚠️ High run-to-run variance (CV=116%) — consider re-running with --runs 5
[194] ⚠️ High run-to-run variance (CV=69%) — consider re-running with --runs 5
[195] ⚠️ High run-to-run variance (CV=257%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -11.8% due to: judgment, tokens (26190 → 70203), quality, tool calls (2 → 6), time (29.7s → 60.3s)
[196] ⚠️ High run-to-run variance (CV=70%) — consider re-running with --runs 5
[197] (Plugin) Quality unchanged but weighted score is -6.1% due to: tokens (13298 → 29917), tool calls (0 → 1)
[198] ⚠️ High run-to-run variance (CV=226%) — consider re-running with --runs 5
[199] ⚠️ High run-to-run variance (CV=93%) — consider re-running with --runs 5
[200] ⚠️ High run-to-run variance (CV=116%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -12.8% due to: tokens (34606 → 106756), quality, tool calls (3 → 7), time (40.3s → 106.0s)
[201] ⚠️ High run-to-run variance (CV=200%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -7.2% due to: judgment, quality, tokens (71039 → 116941)
[202] ⚠️ High run-to-run variance (CV=284%) — consider re-running with --runs 5

⏰ timeout — run(s) hit the (30s, 60s, 120s, 160s, 180s, 240s, 300s, 360s, 420s) scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output (increase via timeout in eval.yaml)

Model: claude-opus-4.6 | Judge: claude-opus-4.6

🔍 Full Results - additional metrics and failure investigation steps

To investigate failures, paste this to your AI coding agent:

For PR 854 in dotnet/skills, download eval artifacts with gh run download 28770610285 --repo dotnet/skills --pattern "skill-validator-results-*" --dir ./eval-results, then fetch https://raw.githubusercontent.com/dotnet/skills/a2845b56d2bd28cad93f95090fa34a4c6c149478/eng/skill-validator/src/docs/InvestigatingResults.md and follow it to analyze the results.json files. Diagnose each failure, suggest fixes to the eval.yaml and skill content, and tell me what to fix first.

▶ Sessions Visualisation -- interactive replay of all evaluation sessions
📊 Session Analytics (preview) -- aggregated metrics across evaluation sessions

@AbhitejJohn

AbhitejJohn commented Jul 6, 2026

Copy link
Copy Markdown
Collaborator

/evaluate

github-actions Bot added a commit that referenced this pull request Jul 6, 2026
@github-actions
Update PR token usage data (PR #854)
3727031
@github-actions

github-actions Bot commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

Skill Validation Results

Skill Scenario Quality Skills Loaded Overfit Verdict
dotnet-aot-compat Make Azure.ResourceManager AOT-compatible 2.5/5 → 2.5/5 ⏰ ✅ dotnet-aot-compat; tools: skill, create, task, read_agent / ✅ dotnet-aot-compat; tools: glob, skill, create, task, read_agent, stop_bash ✅ 0.10 ❌ [1]
msbuild-antipatterns Review MSBuild files for anti-patterns and style issues 5.0/5 → 3.7/5 ⏰ 🔴 ✅ msbuild-antipatterns; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.09 ❌ [2]
msbuild-antipatterns Add a module to an F# project 3.3/5 ⏰ → 3.7/5 ⏰ 🟢 ⚠️ NOT ACTIVATED ✅ 0.09 ✅ [3]
msbuild-antipatterns Fix broken file order causing FS0039 4.0/5 → 4.0/5 ⏰ ⚠️ NOT ACTIVATED ✅ 0.09 ❌ [4]
msbuild-antipatterns Add a signature file to define public API 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED ✅ 0.09 ❌ [5]
microbenchmarking Investigate runtime upgrade performance impact 2.5/5 ⏰ → 3.5/5 🟢 ✅ microbenchmarking; tools: skill, read_bash / ✅ microbenchmarking; tools: read_bash, skill ✅ 0.11 ❌ [6]
template-validation Validate template with multiple errors 4.0/5 → 5.0/5 🟢 ✅ template-validation; tools: skill ✅ 0.14 ✅ [7]
template-validation Validate correct template and suggest improvements 2.3/5 → 3.3/5 🟢 ✅ template-validation; tools: glob, skill ✅ 0.14 ✅
maui-safe-area Handle notch and status bar safe areas on iOS 1.7/5 → 4.7/5 🟢 ✅ maui-safe-area; tools: report_intent, skill ✅ 0.12 ✅
maui-safe-area Edge-to-edge layout with SafeAreaEdges 1.0/5 → 3.7/5 ⏰ 🟢 ✅ maui-safe-area; tools: report_intent, skill / ✅ maui-safe-area; tools: skill, report_intent ✅ 0.12 ✅ [8]
maui-safe-area Keyboard avoidance with safe area for chat UI 1.0/5 → 5.0/5 🟢 ✅ maui-safe-area; tools: report_intent, skill / ✅ maui-safe-area; tools: skill, report_intent ✅ 0.12 ✅
maui-safe-area Avoid deprecated UseSafeArea in new .NET 10 project 1.0/5 ⏰ → 5.0/5 🟢 ✅ maui-safe-area; tools: skill ✅ 0.12 ✅
generate-testability-wrappers Generate TimeProvider adoption for DateTime.UtcNow 3.7/5 → 5.0/5 🟢 ✅ generate-testability-wrappers; tools: skill / ✅ generate-testability-wrappers; tools: skill, grep, glob, bash 🟡 0.24 ❌ [9]
generate-testability-wrappers Generate custom Environment wrapper 3.0/5 → 3.3/5 ⏰ 🟢 ✅ generate-testability-wrappers; tools: skill, glob / ✅ generate-testability-wrappers; tools: skill 🟡 0.24 ✅ [10]
generate-testability-wrappers Recommend System.IO.Abstractions for file system calls 2.7/5 → 3.7/5 ⏰ 🟢 ✅ generate-testability-wrappers; tools: skill, report_intent, view / ✅ generate-testability-wrappers; tools: report_intent, skill, glob, view 🟡 0.24 ✅ [11]
generate-testability-wrappers Decline wrapper generation for already-abstracted code 2.0/5 → 3.3/5 ⏰ 🟢 ✅ generate-testability-wrappers; tools: skill / ℹ️ not activated (expected) 🟡 0.24 ✅ [12]
generate-testability-wrappers Provide ambient context alternative when DI is unavailable 1.0/5 → 2.3/5 ⏰ 🟢 ✅ generate-testability-wrappers; tools: skill, create, edit / ✅ generate-testability-wrappers; tools: edit, skill 🟡 0.24 ❌ [13]
migrate-static-to-wrapper Migrate DateTime.UtcNow to TimeProvider in a service class 5.0/5 → 5.0/5 ✅ migrate-static-to-wrapper; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [14]
migrate-static-to-wrapper Migrate only in scoped files, leaving others untouched 5.0/5 → 5.0/5 ✅ migrate-static-to-wrapper; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [15]
migrate-static-to-wrapper Update test doubles when migrating a service to TimeProvider 5.0/5 → 5.0/5 ✅ migrate-static-to-wrapper; tools: glob, skill / ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [16]
migrate-static-to-wrapper Handle a genuinely static class that cannot take constructor injection 2.7/5 → 2.3/5 🔴 ⚠️ NOT ACTIVATED ✅ 0.08 ❌ [17]
migrate-static-to-wrapper Decline migration when wrapper does not exist yet 4.0/5 → 4.3/5 🟢 ✅ migrate-static-to-wrapper; tools: skill ✅ 0.08 ❌ [18]
migrate-xunit-to-xunit-v3 Migrate basic xUnit.net v2 project to v3 3.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill / ✅ migrate-xunit-to-xunit-v3; tools: skill, glob, create ✅ 0.07 ✅
migrate-xunit-to-xunit-v3 Detect incompatible target framework and stop migration 1.0/5 → 1.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, glob, create / ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.07 ✅
migrate-xunit-to-xunit-v3 Convert async void test methods to async Task 5.0/5 → 4.3/5 🔴 ✅ migrate-xunit-to-xunit-v3; tools: skill / ✅ migrate-xunit-to-xunit-v3; tools: skill, glob ✅ 0.07 ❌ [19]
migrate-xunit-to-xunit-v3 Convert string-based attribute constructors to typeof syntax 5.0/5 → 4.3/5 🔴 ✅ migrate-xunit-to-xunit-v3; tools: skill, create, grep / ✅ migrate-xunit-to-xunit-v3; tools: skill, create ✅ 0.07 ❌ [20]
migrate-xunit-to-xunit-v3 Update custom FactAttribute to include source information parameters 2.7/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill / ✅ migrate-xunit-to-xunit-v3; tools: skill, create ✅ 0.07 ✅ [21]
migrate-xunit-to-xunit-v3 Update BeforeAfterTestAttribute overrides with IXunitTest parameter 4.0/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, create / ✅ migrate-xunit-to-xunit-v3; tools: skill, create, read_bash ✅ 0.07 ✅ [22]
migrate-xunit-to-xunit-v3 Migrate project with YTest.MTP.XUnit2 to xUnit.net v3 preserving MTP 3.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, stop_bash / ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.07 ✅ [23]
migrate-xunit-to-xunit-v3 Migrate Xunit.SkippableFact to xUnit.net v3 built-in skip APIs 5.0/5 → 5.0/5 ✅ migrate-xunit-to-xunit-v3; tools: skill, glob, create / ✅ migrate-xunit-to-xunit-v3; tools: skill, create ✅ 0.07 ✅
migrate-xunit-to-xunit-v3 Migrate xUnit v2 packages managed via Central Package Management 4.7/5 → 4.7/5 ✅ migrate-xunit-to-xunit-v3; tools: skill, create, glob, web_fetch, read_bash / ✅ migrate-xunit-to-xunit-v3; tools: skill, create, glob, read_bash ✅ 0.07 ✅ [24]
migrate-xunit-to-xunit-v3 Recognize project already on xUnit.net v3 — no migration needed 2.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.07 ✅
migrate-xunit-to-xunit-v3 Consolidate xunit.extensibility packages and remove xunit.abstractions 3.0/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, create / ✅ migrate-xunit-to-xunit-v3; tools: skill ✅ 0.07 ✅
migrate-xunit-to-xunit-v3 Update Xunit.Combinatorial and Xunit.StaFact companion packages 4.0/5 → 4.7/5 🟢 ✅ migrate-xunit-to-xunit-v3; tools: skill, glob, create / ✅ migrate-xunit-to-xunit-v3; tools: skill, create ✅ 0.07 ✅ [25]
run-tests Run tests in a VSTest MSTest project 4.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, bash / ⚠️ NOT ACTIVATED ✅ 0.16 ❌ [26]
run-tests Run tests with trx reporting on MTP project (SDK 9) 2.0/5 → 5.0/5 🟢 ✅ run-tests; tools: report_intent, skill, view ✅ 0.16 ✅
run-tests Run tests with blame-hang on MTP project (SDK 10) 2.3/5 → 4.0/5 🟢 ⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill ✅ 0.16 ✅ [27]
run-tests Run tests on a specific TFM with TRX in a multi-TFM MTP project (SDK 9) 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED / ✅ run-tests; tools: skill ✅ 0.16 ❌ [28]
run-tests Filter MSTest tests by category on VSTest 5.0/5 → 3.7/5 ⏰ 🔴 ⚠️ NOT ACTIVATED ✅ 0.16 ❌ [29]
run-tests Filter NUnit tests by class name on VSTest 3.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view, bash / ✅ run-tests; tools: view, skill ✅ 0.16 ✅ [30]
run-tests Filter xUnit v3 tests by class on MTP 1.0/5 → 3.7/5 🟢 ✅ run-tests; tools: skill, view ✅ 0.16 ✅ [31]
run-tests Filter xUnit v3 tests by trait on MTP 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ⚠️ NOT ACTIVATED ✅ 0.16 ✅ [32]
run-tests Filter xUnit v3 tests by class pattern and trait using query filter language 1.0/5 → 1.0/5 ⚠️ NOT ACTIVATED ✅ 0.16 ❌ [33]
run-tests Filter TUnit tests by class using treenode-filter 1.7/5 → 4.0/5 🟢 ⚠️ NOT ACTIVATED ✅ 0.16 ✅ [34]
run-tests Combine multiple filter criteria on VSTest MSTest 3.3/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, report_intent, view / ✅ run-tests; tools: report_intent, skill, view ✅ 0.16 ✅ [35]
run-tests MTP project on SDK 9 must use -- separator for args 1.0/5 → 2.3/5 🟢 ⚠️ NOT ACTIVATED ✅ 0.16 ✅ [36]
run-tests MTP project on SDK 10 passes args directly 1.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.16 ✅
run-tests Detect test platform from Directory.Build.props 1.3/5 → 5.0/5 🟢 ✅ run-tests; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.16 ❌ [37]
run-tests Negative test: do not use MTP syntax for a VSTest project 4.0/5 → 5.0/5 🟢 ✅ run-tests; tools: skill, view / ⚠️ NOT ACTIVATED ✅ 0.16 ❌ [38]
detect-static-dependencies Identify static dependencies in a multi-class project 3.3/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob ✅ 0.07 ✅ [39]
detect-static-dependencies Detect time-related statics and recommend TimeProvider 4.3/5 → 3.0/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: skill ✅ 0.07 ❌
detect-static-dependencies Decline scan for non-C# project 2.0/5 ⏰ → 4.0/5 ⏰ 🟢 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: glob, skill ✅ 0.07 ❌ [40]
detect-static-dependencies Verify structured report includes file count, categories, and top patterns 4.0/5 → 5.0/5 🟢 ✅ detect-static-dependencies; tools: skill, glob / ✅ detect-static-dependencies; tools: skill ✅ 0.07 ✅
detect-static-dependencies Exclude obj and bin directories from the scan 1.0/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ detect-static-dependencies; tools: skill, glob ✅ 0.07 ❌ [41]
detect-static-dependencies Detect statics inside lambda expressions and LINQ queries 4.3/5 → 2.7/5 ⏰ 🔴 ✅ detect-static-dependencies; tools: skill / ✅ detect-static-dependencies; tools: skill, glob ✅ 0.07 ❌
maui-app-lifecycle Save and restore state on background 2.3/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: skill / ✅ maui-app-lifecycle; tools: skill, report_intent ✅ 0.16 ✅
maui-app-lifecycle Window lifecycle event subscription 4.0/5 → 5.0/5 🟢 ✅ maui-app-lifecycle; tools: report_intent, skill ✅ 0.16 ❌ [42]
maui-app-lifecycle Platform-specific lifecycle mapping 4.0/5 → 4.7/5 🟢 ✅ maui-app-lifecycle; tools: skill, report_intent / ✅ maui-app-lifecycle; tools: skill ✅ 0.16 ✅
maui-app-lifecycle Avoid legacy Xamarin.Forms lifecycle methods 4.0/5 → 4.0/5 ✅ maui-app-lifecycle; tools: skill ✅ 0.16 ❌ [43]
crap-score Calculate CRAP score for a single method with partial coverage 3.7/5 → 3.7/5 ⏰ ✅ crap-score; tools: skill, glob ✅ 0.07 ❌ [44]
crap-score Identify riskiest methods across a file 4.0/5 → 5.0/5 🟢 ✅ crap-score; tools: skill, bash / ✅ crap-score; tools: skill ✅ 0.07 ✅
crap-score Generate coverage then compute CRAP score 4.0/5 → 2.7/5 ⏰ 🔴 ✅ crap-score; tools: skill, edit ✅ 0.07 ❌ [45]
directory-build-organization Organize build infrastructure for a multi-project repo 3.7/5 → 4.3/5 ⏰ 🟢 ✅ directory-build-organization; tools: skill, create, edit, bash / ✅ directory-build-organization; tools: skill, create, edit, bash, task, read_agent ✅ 0.20 ❌ [46]
coordinate-components Warehouse dashboard with site selector and live stock alerts 4.0/5 → 4.7/5 🟢 ✅ coordinate-components; tools: skill 🟡 0.22 ❌ [47]
coordinate-components Multi-tenant notification hub with cross-component fan-out 1.0/5 → 4.7/5 🟢 ✅ coordinate-components; tools: skill 🟡 0.22 ✅ [48]
exp-simd-vectorization Optimize manual min/max with TensorPrimitives 1.0/5 ⏰ → 4.0/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, glob, create, bash / ✅ exp-simd-vectorization; tools: skill, glob, bash ✅ 0.20 ✅
exp-simd-vectorization Optimize manual product with TensorPrimitives 1.0/5 → 2.3/5 ⏰ 🟢 ✅ exp-simd-vectorization; tools: skill, glob, create, bash ✅ 0.20 ✅ [49]
exp-simd-vectorization No optimization opportunity — dictionary-based lookup service 1.0/5 → 4.7/5 🟢 ✅ exp-simd-vectorization; tools: skill ✅ 0.20 ✅
exp-simd-vectorization Optimize int array conditional increment with SIMD 2.5/5 ⏰ → 4.0/5 🟢 ✅ exp-simd-vectorization; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.20 ✅ [50]
exp-simd-vectorization Optimize byte buffer bit reversal with SIMD 3.0/5 ⏰ → 2.5/5 ⏰ 🔴 ✅ exp-simd-vectorization; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.20 ❌
incremental-build Analyze incremental build issues 3.0/5 → 3.0/5 ⚠️ NOT ACTIVATED ✅ 0.15 ❌ [51]
migrate-xunit-to-mstest Migrate basic xUnit v2 project to MSTest v4 preserving VSTest 4.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ✅
migrate-xunit-to-mstest Migrate basic xUnit v3 project to MSTest v4 preserving VSTest 5.0/5 → 4.7/5 🔴 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ❌ [52]
migrate-xunit-to-mstest Stop when target framework is unsupported by MSTest v4 2.0/5 → 2.0/5 ✅ migrate-xunit-to-mstest; tools: skill, bash ✅ 0.08 ✅
migrate-xunit-to-mstest Convert IClassFixture to ClassInitialize 4.3/5 → 4.3/5 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ✅ [53]
migrate-xunit-to-mstest Handle ICollectionFixture explicitly (do not silently widen scope) 4.0/5 → 4.3/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ✅ [54]
migrate-xunit-to-mstest Convert ITestOutputHelper to TestContext 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ❌ [55]
migrate-xunit-to-mstest Map exception assertions correctly (xUnit Throws -> MSTest ThrowsExactly) 4.7/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create / ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ✅ [56]
migrate-xunit-to-mstest Convert MemberData and TheoryData to DynamicData 5.0/5 → 4.0/5 🔴 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ❌ [57]
migrate-xunit-to-mstest Convert Skip, Trait, and Timeout 4.0/5 → 4.0/5 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ❌ [58]
migrate-xunit-to-mstest Preserve xUnit parallelization default with [assembly: Parallelize] 1.0/5 → 1.0/5 ✅ migrate-xunit-to-mstest; tools: skill / ✅ migrate-xunit-to-mstest; tools: skill, edit, create, bash ✅ 0.08 ❌ [59]
migrate-xunit-to-mstest Convert xUnit v3 TestContext.Current.CancellationToken 4.0/5 → 5.0/5 🟢 ✅ migrate-xunit-to-mstest; tools: skill, create ✅ 0.08 ✅
migrate-xunit-to-mstest Recognize project already on MSTest 5.0/5 → 5.0/5 ✅ migrate-xunit-to-mstest; tools: skill ✅ 0.08 ❌ [60]
convert-to-cpm Decline CPM conversion for packages.config project 1.0/5 → 3.0/5 🟢 ✅ convert-to-cpm; tools: skill / ℹ️ not activated (expected) 🟡 0.27 ✅ [61]
convert-to-cpm Recommend CPM when updating packages with version conflicts 2.0/5 → 3.0/5 🟢 ✅ convert-to-cpm; tools: skill, bash, create 🟡 0.27 ✅
convert-to-cpm Recommend CPM when updating packages in a complex repository 2.0/5 → 2.0/5 ✅ convert-to-cpm; tools: skill, create, bash / ✅ convert-to-cpm; tools: skill 🟡 0.27 ✅ [62]
convert-to-cpm Convert single project to CPM 2.0/5 → 4.5/5 🟢 ✅ convert-to-cpm; tools: skill, bash 🟡 0.27 ✅
convert-to-cpm Convert multi-project solution to CPM 3.0/5 → 4.5/5 🟢 ✅ convert-to-cpm; tools: skill, bash 🟡 0.27 ✅
convert-to-cpm Convert solution with MSBuild property versions to CPM 3.0/5 → 4.0/5 🟢 ✅ convert-to-cpm; tools: skill, glob, bash / ✅ convert-to-cpm; tools: skill, bash 🟡 0.27 ✅ [63]
convert-to-cpm Convert solution with version conflicts to CPM 3.0/5 → 2.0/5 🔴 ✅ convert-to-cpm; tools: skill, bash, read_bash 🟡 0.27 ❌ [64]
convert-to-cpm Convert complex repository with multiple CPM challenges 1.0/5 → 1.0/5 ✅ convert-to-cpm; tools: skill / ✅ convert-to-cpm; tools: skill, create, edit, bash 🟡 0.27 ❌ [65]
msbuild-server Recommend MSBuild Server for slow CLI incremental builds 2.3/5 ⏰ → 5.0/5 🟢 ✅ msbuild-server; tools: skill ✅ 0.20 ✅
csharp-scripts Avoid activating for language-agnostic calendar script 5.0/5 → 1.7/5 ⏰ 🔴 ✅ csharp-scripts; tools: skill, create 🟡 0.33 ❌
csharp-scripts Test a C# language feature with a file-based app 2.3/5 ⏰ → 1.3/5 ⏰ 🔴 ✅ csharp-scripts; tools: skill, create / ✅ csharp-scripts; tools: skill 🟡 0.33 ❌
csharp-scripts Compose a file-based app from helper files 2.3/5 ⏰ → 2.7/5 ⏰ 🟢 ⚠️ NOT ACTIVATED 🟡 0.33 ❌ [66]
thread-abort-migration Worker thread with abort-based cancellation 5.0/5 → 5.0/5 ✅ thread-abort-migration; tools: skill, report_intent / ✅ thread-abort-migration; tools: skill ✅ 0.12 ❌ [67]
thread-abort-migration Timeout enforcement via Thread.Abort 4.7/5 → 3.7/5 ⏰ 🔴 ✅ thread-abort-migration; tools: skill ✅ 0.12 ❌ [68]
thread-abort-migration Blocking WaitHandle with Thread.Interrupt 4.0/5 → 4.7/5 🟢 ✅ thread-abort-migration; tools: skill, report_intent, bash / ✅ thread-abort-migration; tools: report_intent, skill ✅ 0.12 ✅ [69]
thread-abort-migration ASP.NET Response.End and Response.Redirect with Thread.Abort 4.0/5 → 3.7/5 ⏰ 🔴 ✅ thread-abort-migration; tools: skill, report_intent / ✅ thread-abort-migration; tools: skill ✅ 0.12 ✅ [70]
thread-abort-migration Thread.Join and Thread.Sleep only — should not migrate 4.0/5 → 5.0/5 🟢 ✅ thread-abort-migration; tools: report_intent, skill ✅ 0.12 ✅
coverage-analysis Project-wide coverage analysis with existing Cobertura data 2.3/5 → 5.0/5 🟢 ✅ coverage-analysis; tools: skill, bash, create / ✅ coverage-analysis; tools: skill, bash, create, read_bash, stop_bash 🟡 0.24 ✅
coverage-analysis Run coverage from scratch without existing data 3.7/5 → 5.0/5 🟢 ✅ coverage-analysis; tools: skill, create, glob, read_bash, stop_bash / ✅ coverage-analysis; tools: skill, create, glob 🟡 0.24 ✅
coverage-analysis Coverage plateau diagnosis 3.3/5 → 5.0/5 🟢 ✅ coverage-analysis; tools: skill, create, bash / ✅ coverage-analysis; tools: skill, view, create, bash 🟡 0.24 ✅ [71]
build-perf-baseline Establish build performance baseline and recommend optimizations 2.3/5 ⏰ → 2.0/5 ⏰ 🔴 ✅ build-perf-baseline; tools: skill, binlog-binlog_overview, binlog-binlog_build_graph, binlog-binlog_diagnose, binlog-binlog_expensive_projects, binlog-binlog_expensive_targets, binlog-binlog_analyzer_summary, binlog-binlog_double_writes, binlog-binlog_incremental_analysis, binlog-binlog_properties, binlog-binlog_expensive_tasks, binlog-binlog_expensive_analyzers, create, binlog-binlog_explain_property, binlog-binlog_imports, binlog-binlog_search_files, binlog-binlog_files / ⚠️ NOT ACTIVATED 🟡 0.36 ❌ [72]
template-comparison Compare webapi vs webapp side by side 4.0/5 → 4.0/5 ✅ template-comparison; tools: skill 🟡 0.43 ✅
template-comparison Choose between blazor and blazorwasm 4.0/5 → 4.0/5 ✅ template-comparison; tools: skill 🟡 0.43 ✅ [73]
template-comparison Decide which template fits a background processing scenario 3.0/5 → 4.3/5 🟢 ✅ template-comparison; tools: skill, bash 🟡 0.43 ✅
migrate-dotnet10-to-dotnet11 Console app with compression and TAR operations 1.0/5 ⏰ → 4.3/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, view ✅ 0.07 ✅
migrate-dotnet10-to-dotnet11 C# 15 compiler breaking changes — Span safe-context, nameof, with() 3.0/5 → 4.3/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.07 ❌ [74]
migrate-dotnet10-to-dotnet11 EF Core app with Cosmos DB provider using sync APIs 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view, bash / ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.07 ❌ [75]
migrate-dotnet10-to-dotnet11 Deployment to older hardware with minimum requirement changes 3.7/5 → 4.0/5 🟢 ⚠️ NOT ACTIVATED / ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view ✅ 0.07 ✅ [76]
migrate-dotnet10-to-dotnet11 Cryptography app using DSA on macOS 3.3/5 → 4.7/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: report_intent, skill, view ✅ 0.07 ✅ [77]
migrate-dotnet10-to-dotnet11 Basic TFM update with Docker and global.json 4.7/5 → 4.0/5 🔴 ✅ migrate-dotnet10-to-dotnet11; tools: skill ✅ 0.07 ❌ [78]
migrate-dotnet10-to-dotnet11 C# 15 dynamic operator and ref readonly delegate issues 3.0/5 → 4.3/5 🟢 ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, bash, grep, view / ✅ migrate-dotnet10-to-dotnet11; tools: skill, report_intent, view ✅ 0.07 ✅ [79]
writing-mstest-tests Write unit tests for a service class 4.0/5 → 4.3/5 🟢 ✅ writing-mstest-tests; tools: skill, glob / ✅ writing-mstest-tests; tools: skill 🟡 0.35 ✅ [80]
writing-mstest-tests Write data-driven tests for a calculator 3.0/5 ⏰ → 4.7/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.35 ✅
writing-mstest-tests Write async tests with cancellation 3.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.35 ✅ [81]
writing-mstest-tests Fix swapped Assert.AreEqual arguments 4.3/5 → 4.3/5 ⚠️ NOT ACTIVATED 🟡 0.35 ❌ [82]
writing-mstest-tests Modernize legacy test patterns 4.0/5 ⏰ → 4.0/5 ⏰ ✅ writing-mstest-tests; tools: skill 🟡 0.35 ❌ [83]
writing-mstest-tests Replace ExpectedException with Assert.Throws 3.0/5 → 3.7/5 🟢 ✅ writing-mstest-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.35 ❌ [84]
writing-mstest-tests Use proper collection assertions 2.7/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.35 ✅
writing-mstest-tests Use proper type assertions instead of casts 3.7/5 → 3.7/5 ✅ writing-mstest-tests; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.35 ❌ [85]
writing-mstest-tests Set up test lifecycle correctly 2.0/5 → 4.0/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.35 ✅
writing-mstest-tests Use DynamicData with ValueTuples over object arrays 3.0/5 → 4.3/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.35 ❌ [86]
writing-mstest-tests Use string assertions for format validation 3.7/5 → 4.7/5 🟢 ✅ writing-mstest-tests; tools: skill, view, bash, edit / ✅ writing-mstest-tests; tools: skill, view, glob, bash, edit 🟡 0.35 ✅
writing-mstest-tests Use comparison assertions for boundary testing 2.3/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.35 ✅ [87]
writing-mstest-tests Write tests with collection, null, and reference assertions 3.7/5 → 3.7/5 ✅ writing-mstest-tests; tools: skill 🟡 0.35 ✅ [88]
writing-mstest-tests Configure conditional execution, retry, and cleanup 2.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill / ✅ writing-mstest-tests; tools: report_intent, skill 🟡 0.35 ✅
writing-mstest-tests Configure test parallelization and MSTest.Sdk project 3.0/5 → 5.0/5 🟢 ✅ writing-mstest-tests; tools: skill 🟡 0.35 ✅
maui-dependency-injection Register services with correct lifetimes in MauiProgram.cs 4.7/5 → 5.0/5 🟢 ✅ maui-dependency-injection; tools: report_intent, skill ✅ 0.10 ❌ [89]
maui-dependency-injection Shell navigation auto-resolves DI-registered pages 5.0/5 → 5.0/5 ✅ maui-dependency-injection; tools: skill, report_intent / ✅ maui-shell-navigation; maui-dependency-injection; tools: report_intent, skill ✅ 0.10 ❌ [90]
maui-dependency-injection Platform-specific service registration with fallback 3.0/5 → 5.0/5 🟢 ✅ maui-dependency-injection; tools: skill, report_intent / ✅ maui-dependency-injection; tools: report_intent, skill ✅ 0.10 ✅
maui-dependency-injection Avoid AddScoped pitfall in MAUI 4.7/5 → 5.0/5 🟢 ✅ maui-dependency-injection; tools: report_intent, skill ✅ 0.10 ✅ [91]
template-discovery Find template for web API project 2.3/5 → 4.0/5 🟢 ✅ template-discovery; tools: report_intent, skill, bash ✅ 0.19 ✅
template-discovery Inspect template parameters and compare choices 2.3/5 ⏰ → 4.0/5 🟢 ✅ template-discovery; tools: skill / ⚠️ NOT ACTIVATED ✅ 0.19 ✅ [92]
template-discovery Search NuGet for specialized template 4.0/5 → 3.7/5 🔴 ✅ template-discovery; tools: skill ✅ 0.19 ✅ [93]
template-discovery Resolve ambiguous project intent to multiple candidates 4.0/5 → 3.0/5 ⏰ 🔴 ✅ template-discovery; tools: skill ✅ 0.19 ✅ [94]
template-discovery Preview project creation with dry run 3.0/5 → 4.0/5 🟢 ✅ template-discovery; tools: skill ✅ 0.19 ✅ [95]
maui-shell-navigation Set up Shell navigation with tabs and flyout 4.7/5 → 5.0/5 🟢 ✅ maui-shell-navigation; tools: report_intent, skill ✅ 0.10 ✅ [96]
maui-shell-navigation Navigate with parameters using GoToAsync 5.0/5 → 3.7/5 ⏰ 🔴 ✅ maui-shell-navigation; tools: report_intent, skill / ✅ maui-shell-navigation; tools: skill ✅ 0.10 ❌ [97]
maui-shell-navigation Handle back navigation and unsaved changes guard 2.3/5 → 5.0/5 🟢 ✅ maui-shell-navigation; tools: report_intent, skill ✅ 0.10 ✅
maui-shell-navigation Diagnose common Shell navigation mistakes 4.3/5 → 5.0/5 🟢 ✅ maui-shell-navigation; tools: report_intent, skill ✅ 0.10 ✅ [98]
technology-selection ML.NET classification on tabular data 2.7/5 ⏰ → 4.0/5 ⏰ 🟢 ✅ technology-selection; tools: skill, stop_bash / ✅ technology-selection; tools: skill 🟡 0.43 ✅ [99]
technology-selection LLM integration with MEAI abstraction 1.0/5 → 1.0/5 ⚠️ NOT ACTIVATED 🟡 0.43 ❌ [100]
technology-selection Reject LLM for tabular classification 3.0/5 → 4.7/5 🟢 ✅ technology-selection; tools: skill 🟡 0.43 ✅
technology-selection Agentic workflow with guardrails 2.0/5 → 2.7/5 ⏰ 🟢 ✅ technology-selection; tools: skill, create / ✅ technology-selection; tools: skill 🟡 0.43 ✅ [101]
technology-selection Natural-language scenario decomposition — RAG chatbot 3.7/5 → 4.0/5 🟢 ✅ technology-selection; tools: skill / ✅ technology-selection; tools: skill, bash 🟡 0.43 ✅ [102]
technology-selection RAG pipeline with vector search 3.7/5 → 4.3/5 🟢 ✅ technology-selection; tools: skill 🟡 0.43 ✅
maui-collectionview Basic CollectionView with data binding and DataTemplate 5.0/5 → 3.7/5 ⏰ 🔴 ✅ maui-collectionview; tools: skill / ✅ maui-collectionview; tools: report_intent, skill ✅ 0.07 ❌ [103]
maui-collectionview Grid layout with CollectionView 3.7/5 ⏰ → 3.7/5 ⏰ ✅ maui-collectionview; tools: report_intent, skill ✅ 0.07 ✅ [104]
maui-collectionview Selection and pull-to-refresh with CollectionView 5.0/5 → 2.3/5 ⏰ 🔴 ✅ maui-collectionview; tools: skill, report_intent / ✅ maui-collectionview; tools: report_intent, skill ✅ 0.07 ❌ [105]
maui-collectionview Avoid ListView and ViewCell mistakes 5.0/5 → 3.7/5 ⏰ 🔴 ✅ maui-collectionview; tools: skill ✅ 0.07 ❌ [106]
create-blazor-project University course catalog with enrollment form 2.0/5 → 5.0/5 🟢 ✅ create-blazor-project; tools: skill, task, glob, read_agent / ✅ create-blazor-project; tools: skill 🟡 0.28 ✅ [107]
create-blazor-project Recipe community with interactive ratings on static pages 4.0/5 → 5.0/5 🟢 ✅ create-blazor-project; tools: skill 🟡 0.28 ✅
create-blazor-project Global logistics tracking for worldwide users 3.7/5 → 4.0/5 🟢 ✅ create-blazor-project; tools: skill, task, glob, read_agent / ✅ create-blazor-project; tools: skill, task, read_agent, glob 🟡 0.28 ✅ [108]
analyzing-dotnet-performance Detects compiled regex startup budget and regex chain allocations 4.0/5 → 2.0/5 ⏰ 🔴 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ❌
analyzing-dotnet-performance Detects CurrentCulture comparer and compiled regex budget in inflection rules 4.3/5 → 3.7/5 ⏰ 🔴 ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ❌ [109]
analyzing-dotnet-performance Finds per-call Dictionary allocation not hoisted to static 2.7/5 ⏰ → 2.7/5 ⏰ ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ❌ [110]
analyzing-dotnet-performance Catches compound allocations in recursive number converter with ToLower 4.0/5 → 4.0/5 ⏰ ✅ analyzing-dotnet-performance; tools: skill, grep / ✅ analyzing-dotnet-performance; tools: skill, grep, bash ✅ 0.12 ✅ [111]
analyzing-dotnet-performance Finds StringComparison.Ordinal missing and FrozenDictionary opportunities 5.0/5 → 1.0/5 ⏰ 🔴 ✅ analyzing-dotnet-performance; tools: skill, grep / ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ❌
analyzing-dotnet-performance Detects Aggregate+Replace chain and struct missing IEquatable 4.0/5 → 4.3/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, grep / ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ✅ [112]
analyzing-dotnet-performance Finds branched Replace chain in format string manipulation 3.0/5 → 4.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, bash / ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ✅
analyzing-dotnet-performance Catches LINQ on hot-path string processing and All(char.IsUpper) 4.3/5 → 5.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, grep / ✅ analyzing-dotnet-performance; tools: skill, grep, bash ✅ 0.12 ✅ [113]
analyzing-dotnet-performance Detects LINQ pipeline in TimeSpan formatting and collection processing 3.0/5 → 3.0/5 ✅ analyzing-dotnet-performance; tools: skill, grep ✅ 0.12 ✅ [114]
analyzing-dotnet-performance Flags Span inconsistencies and compound method chains in truncation library 4.0/5 → 4.0/5 ✅ analyzing-dotnet-performance; tools: skill ✅ 0.12 ❌ [115]
analyzing-dotnet-performance Identifies unsealed leaf classes and locale hierarchy patterns 3.0/5 → 5.0/5 🟢 ✅ analyzing-dotnet-performance; tools: skill, grep ✅ 0.12 ✅
dotnet-pinvoke Generate LibraryImport declaration from C header (.NET 8+) 4.3/5 ⏰ → 5.0/5 🟢 ✅ dotnet-pinvoke; tools: skill ✅ 0.09 ❌ [116]
dotnet-pinvoke Generate LibraryImport declaration from C header (.NET Framework) 1.0/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ dotnet-pinvoke; tools: report_intent, skill ✅ 0.09 ✅ [117]
binlog-generation Build project with /bl flag 1.0/5 → 5.0/5 🟢 ✅ binlog-generation; tools: skill, glob / ⚠️ NOT ACTIVATED 🟡 0.32 ✅ [118]
binlog-generation Build with /bl in PowerShell 2.7/5 → 5.0/5 🟢 ✅ binlog-generation; tools: skill, glob 🟡 0.32 ✅
binlog-generation Build multiple configurations with unique binlogs 2.7/5 → 2.7/5 ⚠️ NOT ACTIVATED 🟡 0.32 ❌ [119]
resolve-project-references Explain misleading ResolveProjectReferences time 4.0/5 → 3.7/5 ⏰ 🔴 ✅ resolve-project-references; tools: skill / ✅ resolve-project-references; tools: skill, glob ✅ 0.14 ❌ [120]
migrate-vstest-to-mtp Migrate MSTest project from VSTest to Microsoft.Testing.Platform 3.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill, create, edit, bash ✅ 0.10 ✅
migrate-vstest-to-mtp Migrate NUnit project from VSTest to Microsoft.Testing.Platform 1.7/5 ⏰ → 2.3/5 ⏰ 🟢 ✅ migrate-vstest-to-mtp; tools: skill, create ✅ 0.10 ✅ [121]
migrate-vstest-to-mtp Migrate xUnit.net v2 project from VSTest to Microsoft.Testing.Platform 2.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill, create ✅ 0.10 ✅ [122]
migrate-vstest-to-mtp Update Azure DevOps pipeline from VSTest task to MTP 3.7/5 → 4.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: skill, bash ✅ 0.10 ✅ [123]
migrate-vstest-to-mtp Migrate MSTest.Sdk project that explicitly uses VSTest 3.0/5 → 3.3/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill, glob / ✅ migrate-vstest-to-mtp; tools: skill, create ✅ 0.10 ✅
migrate-vstest-to-mtp Translate dotnet test VSTest arguments to MTP equivalents 4.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 ✅ [124]
migrate-vstest-to-mtp Handle exit code 8 when migrating from VSTest to MTP 3.0/5 → 4.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 ✅ [125]
migrate-vstest-to-mtp Configure dotnet test MTP mode on .NET 10 SDK 2.0/5 → 4.7/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 ✅
migrate-vstest-to-mtp Migrate xUnit.net VSTest filter syntax to MTP 1.3/5 → 4.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 ✅
migrate-vstest-to-mtp Set OutputType=Exe only for test projects in Directory.Build.props 4.0/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill / ✅ migrate-vstest-to-mtp; tools: report_intent, skill ✅ 0.10 ✅ [126]
migrate-vstest-to-mtp Full VSTest to MTP migration plan for MSTest solution 2.7/5 → 5.0/5 🟢 ✅ migrate-vstest-to-mtp; tools: skill ✅ 0.10 ✅
android-tombstone-symbolication Symbolicate .NET frames in an Android tombstone 4.3/5 → 3.0/5 🔴 ✅ android-tombstone-symbolication; tools: skill, stop_bash / ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ❌
android-tombstone-symbolication Recognize tombstone with no .NET frames 5.0/5 → 5.0/5 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ❌ [127]
android-tombstone-symbolication Symbolicate CoreCLR frames in an Android tombstone 3.7/5 → 2.7/5 🔴 ✅ android-tombstone-symbolication; tools: skill, read_bash, stop_bash / ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ❌ [128]
android-tombstone-symbolication Recognize NativeAOT tombstone with app binary and libSystem.Native.so 3.0/5 → 3.0/5 ⏰ ✅ android-tombstone-symbolication; tools: skill, bash, read_bash ✅ 0.15 ❌ [129]
android-tombstone-symbolication Symbolicate multi-thread tombstone 1.7/5 ⏰ → 4.7/5 🟢 ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ✅
android-tombstone-symbolication Handle .NET frames with no BuildId metadata 3.7/5 → 4.3/5 🟢 ✅ android-tombstone-symbolication; tools: skill, bash / ✅ android-tombstone-symbolication; tools: skill ✅ 0.15 ✅ [130]
android-tombstone-symbolication Symbolicate tombstone with multiple .NET libraries and different BuildIds 3.3/5 → 3.3/5 ✅ android-tombstone-symbolication; tools: skill / ✅ android-tombstone-symbolication; tools: skill, read_bash ✅ 0.15 ❌
android-tombstone-symbolication Reject iOS crash log as wrong format 4.0/5 → 4.7/5 🟢 ℹ️ not activated (expected) ✅ 0.15 ❌ [131]
build-perf-diagnostics Diagnose slow build for a small project 4.7/5 → 4.3/5 🔴 ⚠️ NOT ACTIVATED 🟡 0.21 ❌ [132]
check-bin-obj-clash Diagnose bin/obj output path clashes 4.0/5 → 5.0/5 🟢 ✅ check-bin-obj-clash; tools: skill, binlog-binlog_overview, binlog-binlog_errors, binlog-binlog_evaluations, binlog-binlog_evaluation_properties, edit, binlog-binlog_double_writes, binlog-binlog_properties, binlog-binlog_evaluation_global_properties / ✅ check-bin-obj-clash; tools: skill, binlog-binlog_overview, binlog-binlog_errors, binlog-binlog_evaluations, binlog-binlog_properties, binlog-binlog_evaluation_global_properties, binlog-binlog_double_writes ✅ 0.14 ✅ [133]
migrate-nullable-references Enable NRT in a small library with mixed nullability 5.0/5 → 5.0/5 ✅ migrate-nullable-references; tools: skill ✅ 0.14 ❌ [134]
migrate-nullable-references File-by-file migration: only modify the targeted file 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED ✅ 0.14 ❌ [135]
migrate-nullable-references Enable NRT in ASP.NET Core Web API with EF Core 4.3/5 → 3.3/5 🔴 ⚠️ NOT ACTIVATED ✅ 0.14 ❌ [136]
dotnet-maui-doctor Plan macOS MAUI setup with Xcode 3.0/5 → 3.7/5 ⏰ 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill, view ✅ 0.20 ✅ [137]
dotnet-maui-doctor Plan Linux MAUI environment for Android 3.0/5 → 2.3/5 ⏰ 🔴 ✅ dotnet-maui-doctor; tools: report_intent, skill, view, bash / ✅ dotnet-maui-doctor; tools: report_intent, skill, view ✅ 0.20 ❌ [138]
dotnet-maui-doctor Guardrail against workload update and repair 1.0/5 → 4.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill ✅ 0.20 ✅
dotnet-maui-doctor Diagnose non-Microsoft JDK causing build failure 1.7/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill, report_intent, view ✅ 0.20 ✅ [139]
dotnet-maui-doctor Plan complete MAUI setup on Windows 4.0/5 → 4.0/5 ✅ dotnet-maui-doctor; tools: skill, report_intent, view ✅ 0.20 ❌ [140]
dotnet-maui-doctor Prevent incorrect JAVA_HOME configuration 3.3/5 → 5.0/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill ✅ 0.20 ✅
dotnet-maui-doctor Determine required Android SDK packages for specific .NET version 3.7/5 → 4.3/5 🟢 ✅ dotnet-maui-doctor; tools: report_intent, skill, view ✅ 0.20 ✅
dotnet-maui-doctor Fix stale MAUI workloads after SDK update 2.0/5 → 4.0/5 🟢 ✅ dotnet-maui-doctor; tools: skill, report_intent, view / ✅ dotnet-maui-doctor; tools: report_intent, skill, view ✅ 0.20 ✅
collect-user-input Event registration with custom validation 4.0/5 → 4.7/5 🟢 ✅ collect-user-input; tools: skill ✅ 0.14 ✅ [141]
collect-user-input Multi-step booking form with cross-field validation 3.3/5 → 4.0/5 🟢 ✅ collect-user-input; tools: skill ✅ 0.14 ✅ [142]
fetch-and-send-data Recipe browser with resilient data loading 3.0/5 → 4.0/5 🟢 ✅ fetch-and-send-data; tools: skill 🟡 0.21 ✅
fetch-and-send-data Real-time shipment tracker with Auto interactivity 4.0/5 → 4.0/5 ✅ fetch-and-send-data; tools: skill 🟡 0.21 ✅ [143]
author-component Author a data-loading search component 3.3/5 → 4.0/5 🟢 ✅ author-component; tools: skill, view, bash ✅ 0.18 ✅ [144]
author-component Author a multi-step wizard with async validation and shared state 3.7/5 ⏰ → 4.0/5 ⏰ 🟢 ✅ author-component; tools: skill, view ✅ 0.18 ❌
author-component Author a generic data table component 4.0/5 → 2.3/5 ⏰ 🔴 ✅ author-component; tools: skill, bash / ✅ author-component; tools: skill, bash, view ✅ 0.18 ❌ [145]
author-component Author a real-time notification badge component 2.3/5 → 4.3/5 🟢 ✅ author-component; tools: skill, view ✅ 0.18 ✅
author-component Author a sortable list with code-behind pattern 4.0/5 → 4.7/5 🟢 ✅ author-component; tools: skill, bash ✅ 0.18 ✅ [146]
binlog-failure-analysis Diagnose build failures from binlog only (no source files) 4.0/5 → 4.0/5 ⚠️ NOT ACTIVATED ✅ 0.11 ❌ [147]
template-instantiation Create a console application 4.0/5 → 3.0/5 ⏰ 🔴 ✅ template-instantiation; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.22 ✅ [148]
migrate-dotnet9-to-dotnet10 Console app with System.Linq.Async, SIGTERM, and BufferedStream 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, view, grep ✅ 0.04 ❌ [149]
migrate-dotnet9-to-dotnet10 Expression tree code broken by C# 14 span overload resolution 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view, grep ✅ 0.04 ❌ [150]
migrate-dotnet9-to-dotnet10 ASP.NET Core app with WebHostBuilder, OpenAPI, and forwarded headers 3.7/5 → 4.7/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.04 ❌ [151]
migrate-dotnet9-to-dotnet10 ASP.NET Core app with OpenAPI transformers using Microsoft.OpenApi v1 APIs 2.7/5 ⏰ → 4.7/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, bash, view, grep / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view ✅ 0.04 ✅ [152]
migrate-dotnet9-to-dotnet10 EF Core app with Azure SQL JSON columns and parameterized collections 2.0/5 → 3.7/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.04 ✅ [153]
migrate-dotnet9-to-dotnet10 EF Core app with dynamic ExecuteUpdate and complex types 4.7/5 → 4.0/5 🔴 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.04 ❌ [154]
migrate-dotnet9-to-dotnet10 SQLite app with DateTimeOffset timezone handling 1.0/5 → 4.3/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep, view ✅ 0.04 ✅
migrate-dotnet9-to-dotnet10 Worker service with config null array binding and ProviderAlias assembly change 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.04 ✅ [155]
migrate-dotnet9-to-dotnet10 Cryptography app with OpenSSL, X.509, and Rfc2898DeriveBytes 5.0/5 → 5.0/5 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.04 ❌ [156]
migrate-dotnet9-to-dotnet10 SDK and NuGet obscure tooling changes 4.3/5 → 4.0/5 🔴 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view, report_intent ✅ 0.04 ❌ [157]
migrate-dotnet9-to-dotnet10 JSON polymorphism with conflicting property names and XmlSerializer 2.3/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep, view / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.04 ✅ [158]
migrate-dotnet9-to-dotnet10 WinForms and WPF desktop app with System.Drawing and DynamicResource 5.0/5 → 4.0/5 🔴 ✅ migrate-dotnet9-to-dotnet10; tools: skill, view ✅ 0.04 ❌
migrate-dotnet9-to-dotnet10 Containerized single-file app with P/Invoke and IDispatchEx 3.7/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view ✅ 0.04 ✅
migrate-dotnet9-to-dotnet10 App using SslStream properties and SystemEvents 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill ✅ 0.04 ✅ [159]
migrate-dotnet9-to-dotnet10 Library with NuGet auditing, transitive deps, and InlineArray 3.3/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view ✅ 0.04 ✅ [160]
migrate-dotnet9-to-dotnet10 C# 14 compiler breaking changes — field keyword, extension keyword, disposal 4.0/5 → 5.0/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view, grep / ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, view ✅ 0.04 ✅ [161]
migrate-dotnet9-to-dotnet10 Blazor WASM app with generic math shift masking and tar operations 3.3/5 → 4.3/5 🟢 ✅ migrate-dotnet9-to-dotnet10; tools: skill, report_intent, grep / ✅ migrate-dotnet9-to-dotnet10; tools: report_intent, skill, view, grep ✅ 0.04 ✅ [162]
assertion-quality Identify low assertion diversity in equality-dominated test suite 3.7/5 → 3.3/5 ⏰ 🔴 ✅ assertion-quality; tools: skill 🟡 0.21 ❌ [163]
assertion-quality Flag assertion-free tests and trivial-only assertions 4.0/5 → 4.3/5 🟢 ✅ assertion-quality; tools: skill, glob / ✅ assertion-quality; tools: skill 🟡 0.21 ❌ [164]
assertion-quality Recognize well-diversified assertion usage 4.0/5 → 4.0/5 ✅ assertion-quality; tools: skill, glob / ✅ assertion-quality; tools: skill 🟡 0.21 ✅ [165]
assertion-quality Identify self-referential assertions in identity and round-trip tests 4.0/5 → 2.0/5 ⏰ 🔴 ✅ assertion-quality; tools: skill, glob 🟡 0.21 ❌ [166]
assertion-quality Decline request to write new tests from scratch 4.0/5 → 3.0/5 ⏰ 🔴 ℹ️ not activated (expected) 🟡 0.21 ❌
assertion-quality Polyglot: evaluate shallow assertions in a Jest/TypeScript OrderService suite 4.7/5 → 5.0/5 🟢 ✅ assertion-quality; tools: skill, glob 🟡 0.21 ✅ [167]
configure-auth Login and account management in a globally interactive app 5.0/5 → 5.0/5 ✅ configure-auth; tools: skill ✅ 0.08 ❌ [168]
configure-auth Multi-tier app with WebAssembly auth 3.0/5 → 4.3/5 🟢 ✅ configure-auth; tools: skill, stop_bash / ✅ configure-auth; tools: skill ✅ 0.08 ✅
nuget-trusted-publishing Set up trusted publishing for a new NuGet library 2.0/5 ⏰ → 2.0/5 ⏰ ✅ nuget-trusted-publishing; tools: skill, view, create / ✅ nuget-trusted-publishing; tools: skill, view ✅ 0.18 ❌ [169]
nuget-trusted-publishing Set up NuGet publishing without mentioning trusted publishing 3.0/5 → 4.0/5 🟢 ✅ nuget-trusted-publishing; tools: skill, report_intent, view ✅ 0.18 ✅ [170]
nuget-trusted-publishing Migrate existing workflow from API key to trusted publishing 2.0/5 ⏰ → 3.0/5 ⏰ 🟢 ✅ nuget-trusted-publishing; tools: skill, report_intent, glob ✅ 0.18 ✅ [171]
template-smart-defaults AOT implies a compatible framework 2.0/5 → 4.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill, bash / ⚠️ NOT ACTIVATED 🟡 0.36 ✅
template-smart-defaults Auth implies HTTPS stays enabled 1.3/5 → 4.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.36 ✅
template-smart-defaults Controllers exclude the minimal-API flag 3.0/5 → 5.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.36 ❌ [172]
template-smart-defaults Never override an explicit user value 2.0/5 → 5.0/5 🟢 ✅ template-smart-defaults; tools: report_intent, skill / ⚠️ NOT ACTIVATED 🟡 0.36 ✅ [173]
dump-collect Configure automatic crash dumps for CoreCLR app on Linux 4.3/5 → 3.7/5 ⏰ 🔴 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view 🟡 0.31 ✅ [174]
dump-collect Set up NativeAOT crash dumps with createdump in Kubernetes 2.7/5 → 3.7/5 ⏰ 🟢 ✅ dump-collect; tools: report_intent, skill, view 🟡 0.31 ❌ [175]
dump-collect Recover crash dump from macOS NativeAOT without createdump 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ⚠️ NOT ACTIVATED 🟡 0.31 ✅ [176]
dump-collect Configure CoreCLR dump collection in Alpine Docker as non-root 3.3/5 → 5.0/5 🟢 ✅ dump-collect; tools: skill, report_intent, view 🟡 0.31 ❌ [177]
dump-collect Advisory: macOS NativeAOT crash dump recovery steps 3.0/5 ⏰ → 3.7/5 ⏰ 🟢 ✅ dump-collect; tools: skill, view 🟡 0.31 ✅ [178]
dump-collect Advisory: CoreCLR Alpine Docker non-root configuration 4.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view 🟡 0.31 ✅ [179]
dump-collect Advisory: NativeAOT Kubernetes dump collection setup 3.0/5 → 5.0/5 🟢 ✅ dump-collect; tools: report_intent, skill, view / ✅ dump-collect; tools: skill, report_intent, view 🟡 0.31 ✅
dump-collect Detect runtime and configure crash dumps for unknown .NET app on Linux 3.7/5 → 3.7/5 ✅ dump-collect; tools: skill, view 🟡 0.31 ❌ [180]
dump-collect Decline dump analysis request 1.7/5 ⏰ → 3.3/5 🟢 ℹ️ not activated (expected) 🟡 0.31 ✅ [181]
support-prerendering Equipment inventory loaded once 4.3/5 → 5.0/5 🟢 ✅ support-prerendering; tools: skill, glob 🟡 0.24 ✅ [182]
support-prerendering Notifications page with live polling 3.7/5 → 3.0/5 🔴 ✅ support-prerendering; tools: skill, bash, edit / ✅ create-blazor-project; support-prerendering; tools: skill, glob, bash, edit 🟡 0.24 ❌ [183]
test-smell-detection Detect multiple test smells in order processing test suite 3.0/5 ⏰ → 2.3/5 ⏰ 🔴 ✅ test-smell-detection; tools: skill 🟡 0.43 ❌ [184]
test-smell-detection Recognize well-written tests with no significant smells 2.0/5 ⏰ → 2.3/5 ⏰ 🟢 ✅ test-smell-detection; tools: skill 🟡 0.43 ❌ [185]
test-smell-detection Recognize integration tests and avoid false positives for external resources 5.0/5 → 2.7/5 ⏰ 🔴 ✅ test-smell-detection; tools: skill 🟡 0.43 ❌
test-smell-detection Decline request to write new tests from scratch 4.3/5 → 5.0/5 🟢 ℹ️ not activated (expected) 🟡 0.43 ❌ [186]
test-smell-detection Polyglot: detect canonical test smells in a JUnit/Java Catalog suite 5.0/5 → 5.0/5 ✅ test-smell-detection; tools: skill / ⚠️ NOT ACTIVATED 🟡 0.43 ❌ [187]
test-smell-detection Distinguish reasoned skips, spare obvious numbers, justify severity 5.0/5 → 5.0/5 ⚠️ NOT ACTIVATED 🟡 0.43 ❌ [188]
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 9) 1.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
mtp-hot-reload Suggest hot reload for failing test in MTP project (SDK 10) 1.0/5 → 3.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
mtp-hot-reload Enable hot reload when package already installed 2.0/5 → 5.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
mtp-hot-reload Suggest launchSettings.json configuration for hot reload 1.0/5 → 4.0/5 🟢 ✅ mtp-hot-reload; tools: skill, create ✅ 0.08 ✅
mtp-hot-reload Use dotnet run not dotnet test for hot reload 2.3/5 → 3.3/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅ [189]
mtp-hot-reload Negative: VSTest project cannot use MTP hot reload 2.0/5 → 2.3/5 🟢 ✅ mtp-hot-reload; tools: skill, bash, create, edit ✅ 0.08 ❌ [190]
mtp-hot-reload Run specific failing test with hot reload filter 1.0/5 → 4.0/5 🟢 ✅ mtp-hot-reload; tools: skill ✅ 0.08 ✅
maui-data-binding Set up compiled bindings with x:DataType on a page 3.0/5 → 4.0/5 🟢 ✅ maui-data-binding; tools: skill ✅ 0.12 ✅ [191]
maui-data-binding Implement MVVM ViewModel with ObservableObject 4.7/5 → 5.0/5 🟢 ✅ maui-data-binding; tools: report_intent, skill ✅ 0.12 ❌ [192]
maui-data-binding Create and use an IValueConverter 5.0/5 → 5.0/5 ✅ maui-data-binding; tools: report_intent, skill ✅ 0.12 ❌ [193]
maui-data-binding Diagnose missing BindingContext and non-compiled bindings 3.0/5 → 4.0/5 🟢 ✅ maui-data-binding; tools: report_intent, skill / ✅ maui-data-binding; tools: skill ✅ 0.12 ✅

[1] ⚠️ High run-to-run variance (CV=65%) — consider re-running with --runs 5
[2] ⚠️ High run-to-run variance (CV=145%) — consider re-running with --runs 5
[3] ⚠️ High run-to-run variance (CV=173%) — consider re-running with --runs 5
[4] ⚠️ High run-to-run variance (CV=115%) — consider re-running with --runs 5
[5] (Isolated) Quality unchanged but weighted score is -3.6% due to: tokens (70781 → 113432), time (27.3s → 33.8s)
[6] ⚠️ High run-to-run variance (CV=121%) — consider re-running with --runs 5
[7] ⚠️ High run-to-run variance (CV=52%) — consider re-running with --runs 5
[8] ⚠️ High run-to-run variance (CV=19037%) — consider re-running with --runs 5
[9] ⚠️ High run-to-run variance (CV=108%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -1.7% due to: judgment
[10] ⚠️ High run-to-run variance (CV=208%) — consider re-running with --runs 5
[11] ⚠️ High run-to-run variance (CV=237%) — consider re-running with --runs 5
[12] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[13] ⚠️ High run-to-run variance (CV=180%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.8% due to: tokens (60718 → 78006)
[14] ⚠️ High run-to-run variance (CV=264%) — consider re-running with --runs 5
[15] (Isolated) Quality unchanged but weighted score is -16.4% due to: judgment, tokens (68446 → 101250), time (71.9s → 111.6s), tool calls (8 → 10)
[16] (Plugin) Quality unchanged but weighted score is -3.6% due to: time (90.5s → 160.5s), tokens (117022 → 155242)
[17] ⚠️ High run-to-run variance (CV=98%) — consider re-running with --runs 5
[18] ⚠️ High run-to-run variance (CV=106%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -1.1% due to: tokens (86460 → 104779), tool calls (9 → 11)
[19] ⚠️ High run-to-run variance (CV=222%) — consider re-running with --runs 5
[20] ⚠️ High run-to-run variance (CV=81%) — consider re-running with --runs 5
[21] ⚠️ High run-to-run variance (CV=84%) — consider re-running with --runs 5
[22] ⚠️ High run-to-run variance (CV=77%) — consider re-running with --runs 5
[23] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[24] ⚠️ High run-to-run variance (CV=84%) — consider re-running with --runs 5
[25] ⚠️ High run-to-run variance (CV=1911%) — consider re-running with --runs 5
[26] ⚠️ High run-to-run variance (CV=607%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.3% due to: tokens (25254 → 34611), time (23.6s → 37.2s)
[27] ⚠️ High run-to-run variance (CV=63%) — consider re-running with --runs 5
[28] (Plugin) Quality unchanged but weighted score is -7.0% due to: tokens (25475 → 55099), tool calls (2 → 3), time (51.5s → 67.2s)
[29] ⚠️ High run-to-run variance (CV=85%) — consider re-running with --runs 5
[30] ⚠️ High run-to-run variance (CV=75%) — consider re-running with --runs 5
[31] ⚠️ High run-to-run variance (CV=193%) — consider re-running with --runs 5
[32] ⚠️ High run-to-run variance (CV=296%) — consider re-running with --runs 5
[33] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.0% due to: tokens (12657 → 17257), quality
[34] ⚠️ High run-to-run variance (CV=65%) — consider re-running with --runs 5
[35] ⚠️ High run-to-run variance (CV=98%) — consider re-running with --runs 5
[36] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[37] ⚠️ High run-to-run variance (CV=436%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -32.2% due to: judgment, quality, tokens (49757 → 72943), tool calls (5 → 6)
[38] (Plugin) Quality unchanged but weighted score is -1.9% due to: tokens (25554 → 34967)
[39] ⚠️ High run-to-run variance (CV=324%) — consider re-running with --runs 5
[40] ⚠️ High run-to-run variance (CV=251%) — consider re-running with --runs 5
[41] ⚠️ High run-to-run variance (CV=113%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -6.2% due to: judgment, tokens (29794 → 59075), quality, tool calls (5 → 7)
[42] (Isolated) Quality improved but weighted score is -8.4% due to: tokens (12754 → 28433), tool calls (0 → 1), time (24.8s → 33.6s)
[43] ⚠️ High run-to-run variance (CV=74%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -21.3% due to: completion (✓ → ✗), tokens (12704 → 31986), tool calls (0 → 1), time (25.0s → 52.0s)
[44] ⚠️ High run-to-run variance (CV=696%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -5.8% due to: tokens (28274 → 57476), time (47.1s → 85.0s), tool calls (3 → 5)
[45] ⚠️ High run-to-run variance (CV=133%) — consider re-running with --runs 5
[46] ⚠️ High run-to-run variance (CV=70%) — consider re-running with --runs 5
[47] ⚠️ High run-to-run variance (CV=76%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -3.5% due to: tokens (183945 → 280319), time (223.9s → 288.1s)
[48] ⚠️ High run-to-run variance (CV=84%) — consider re-running with --runs 5
[49] ⚠️ High run-to-run variance (CV=161%) — consider re-running with --runs 5
[50] ⚠️ High run-to-run variance (CV=152%) — consider re-running with --runs 5
[51] ⚠️ High run-to-run variance (CV=121%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -1.8% due to: tokens (26172 → 47252)
[52] ⚠️ High run-to-run variance (CV=64%) — consider re-running with --runs 5
[53] ⚠️ High run-to-run variance (CV=239%) — consider re-running with --runs 5
[54] ⚠️ High run-to-run variance (CV=50%) — consider re-running with --runs 5
[55] (Plugin) Quality unchanged but weighted score is -8.1% due to: tokens (69040 → 186244), time (32.6s → 72.6s), tool calls (8 → 10)
[56] ⚠️ High run-to-run variance (CV=396%) — consider re-running with --runs 5
[57] ⚠️ High run-to-run variance (CV=51%) — consider re-running with --runs 5
[58] ⚠️ High run-to-run variance (CV=134%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -24.6% due to: judgment, tokens (76653 → 235216), quality, time (81.1s → 145.9s), tool calls (8 → 13)
[59] (Isolated) Quality unchanged but weighted score is -2.4% due to: tokens (12746 → 21409)
[60] ⚠️ High run-to-run variance (CV=159%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -4.2% due to: tokens (34370 → 64168)
[61] ⚠️ High run-to-run variance (CV=101%) — consider re-running with --runs 5
[62] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5
[63] ⚠️ High run-to-run variance (CV=87%) — consider re-running with --runs 5
[64] ⚠️ High run-to-run variance (CV=183%) — consider re-running with --runs 5
[65] ⚠️ High run-to-run variance (CV=276%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -17.2% due to: judgment, quality, tokens (29992 → 40582)
[66] ⚠️ High run-to-run variance (CV=194%) — consider re-running with --runs 5
[67] (Plugin) Quality unchanged but weighted score is -8.7% due to: tokens (13691 → 32987), tool calls (0 → 1), time (38.8s → 73.1s)
[68] ⚠️ High run-to-run variance (CV=148%) — consider re-running with --runs 5
[69] ⚠️ High run-to-run variance (CV=33370%) — consider re-running with --runs 5
[70] ⚠️ High run-to-run variance (CV=569%) — consider re-running with --runs 5. (Isolated) Quality dropped but weighted score is +25.0% due to: completion (✗ → ✓)
[71] ⚠️ High run-to-run variance (CV=60%) — consider re-running with --runs 5
[72] ⚠️ High run-to-run variance (CV=109%) — consider re-running with --runs 5
[73] ⚠️ High run-to-run variance (CV=104%) — consider re-running with --runs 5
[74] ⚠️ High run-to-run variance (CV=268%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -62.6% due to: judgment, quality, tokens (14124 → 53940), tool calls (0 → 3), time (43.5s → 63.5s)
[75] (Isolated) Quality improved but weighted score is -8.1% due to: tokens (13203 → 50367), tool calls (0 → 4), time (56.8s → 70.2s)
[76] ⚠️ High run-to-run variance (CV=65%) — consider re-running with --runs 5
[77] ⚠️ High run-to-run variance (CV=141%) — consider re-running with --runs 5
[78] ⚠️ High run-to-run variance (CV=133%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -6.4% due to: tokens (12709 → 32988), tool calls (0 → 1), time (11.0s → 27.6s)
[79] ⚠️ High run-to-run variance (CV=69%) — consider re-running with --runs 5
[80] ⚠️ High run-to-run variance (CV=153%) — consider re-running with --runs 5
[81] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[82] ⚠️ High run-to-run variance (CV=97%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.6% due to: tokens (12718 → 17384)
[83] ⚠️ High run-to-run variance (CV=5535%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -8.8% due to: quality, tokens (174358 → 287265), time (182.6s → 246.4s), tool calls (14 → 18)
[84] ⚠️ High run-to-run variance (CV=388%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -3.3% due to: tokens (12604 → 18930), time (22.7s → 30.1s)
[85] ⚠️ High run-to-run variance (CV=269%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -2.8% due to: tokens (12657 → 17299), quality
[86] ⚠️ High run-to-run variance (CV=299%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -21.2% due to: judgment, tokens (12846 → 31008), tool calls (0 → 1), time (15.1s → 25.1s)
[87] ⚠️ High run-to-run variance (CV=97%) — consider re-running with --runs 5
[88] ⚠️ High run-to-run variance (CV=83%) — consider re-running with --runs 5
[89] ⚠️ High run-to-run variance (CV=1300%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -8.2% due to: tokens (12913 → 32744), tool calls (0 → 2), time (40.2s → 51.2s)
[90] (Isolated) Quality unchanged but weighted score is -22.0% due to: judgment, tokens (12834 → 39437), tool calls (0 → 2), time (21.9s → 61.9s)
[91] ⚠️ High run-to-run variance (CV=260%) — consider re-running with --runs 5
[92] ⚠️ High run-to-run variance (CV=57%) — consider re-running with --runs 5
[93] ⚠️ High run-to-run variance (CV=101%) — consider re-running with --runs 5
[94] ⚠️ High run-to-run variance (CV=778%) — consider re-running with --runs 5
[95] ⚠️ High run-to-run variance (CV=177%) — consider re-running with --runs 5
[96] ⚠️ High run-to-run variance (CV=330%) — consider re-running with --runs 5
[97] ⚠️ High run-to-run variance (CV=257%) — consider re-running with --runs 5
[98] ⚠️ High run-to-run variance (CV=1007%) — consider re-running with --runs 5
[99] ⚠️ High run-to-run variance (CV=525%) — consider re-running with --runs 5
[100] (Isolated) Quality unchanged but weighted score is -3.3% due to: tokens (96131 → 139499), time (47.9s → 60.6s)
[101] ⚠️ High run-to-run variance (CV=463%) — consider re-running with --runs 5
[102] ⚠️ High run-to-run variance (CV=244%) — consider re-running with --runs 5
[103] ⚠️ High run-to-run variance (CV=140%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -7.5% due to: tokens (12822 → 33380), tool calls (0 → 2)
[104] ⚠️ High run-to-run variance (CV=1310%) — consider re-running with --runs 5
[105] ⚠️ High run-to-run variance (CV=82%) — consider re-running with --runs 5
[106] ⚠️ High run-to-run variance (CV=132%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -8.7% due to: tokens (12810 → 33446), tool calls (0 → 1), time (30.3s → 44.7s)
[107] ⚠️ High run-to-run variance (CV=87%) — consider re-running with --runs 5
[108] ⚠️ High run-to-run variance (CV=76%) — consider re-running with --runs 5
[109] ⚠️ High run-to-run variance (CV=52%) — consider re-running with --runs 5
[110] ⚠️ High run-to-run variance (CV=4592%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -20.0% due to: judgment, quality, tokens (46184 → 55707), tool calls (5 → 6)
[111] ⚠️ High run-to-run variance (CV=432%) — consider re-running with --runs 5
[112] ⚠️ High run-to-run variance (CV=79%) — consider re-running with --runs 5
[113] ⚠️ High run-to-run variance (CV=346%) — consider re-running with --runs 5
[114] ⚠️ High run-to-run variance (CV=350%) — consider re-running with --runs 5
[115] ⚠️ High run-to-run variance (CV=435%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.8% due to: tokens (45123 → 90645), tool calls (3 → 6), time (45.6s → 74.5s)
[116] ⚠️ High run-to-run variance (CV=245%) — consider re-running with --runs 5
[117] ⚠️ High run-to-run variance (CV=185%) — consider re-running with --runs 5
[118] ⚠️ High run-to-run variance (CV=87%) — consider re-running with --runs 5
[119] ⚠️ High run-to-run variance (CV=64%) — consider re-running with --runs 5
[120] ⚠️ High run-to-run variance (CV=687%) — consider re-running with --runs 5
[121] ⚠️ High run-to-run variance (CV=77%) — consider re-running with --runs 5
[122] ⚠️ High run-to-run variance (CV=69%) — consider re-running with --runs 5
[123] ⚠️ High run-to-run variance (CV=193%) — consider re-running with --runs 5
[124] ⚠️ High run-to-run variance (CV=134%) — consider re-running with --runs 5
[125] ⚠️ High run-to-run variance (CV=152%) — consider re-running with --runs 5
[126] ⚠️ High run-to-run variance (CV=180%) — consider re-running with --runs 5
[127] (Isolated) Quality unchanged but weighted score is -7.3% due to: tokens (26335 → 45018), time (40.3s → 82.0s), tool calls (2 → 3)
[128] ⚠️ High run-to-run variance (CV=61%) — consider re-running with --runs 5
[129] ⚠️ High run-to-run variance (CV=231%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -66.0% due to: judgment, quality, tokens (27332 → 83186), tool calls (2 → 7), time (78.4s → 205.3s)
[130] ⚠️ High run-to-run variance (CV=106%) — consider re-running with --runs 5
[131] ⚠️ High run-to-run variance (CV=88%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -22.1% due to: judgment, tokens (26608 → 49591), quality, tool calls (2 → 3), time (31.9s → 38.4s)
[132] ⚠️ High run-to-run variance (CV=94%) — consider re-running with --runs 5
[133] ⚠️ High run-to-run variance (CV=349%) — consider re-running with --runs 5
[134] (Plugin) Quality unchanged but weighted score is -7.3% due to: tokens (92518 → 179756), time (104.4s → 156.1s), quality
[135] ⚠️ High run-to-run variance (CV=139%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -3.5% due to: tokens (89828 → 121490), time (100.0s → 146.2s), tool calls (8 → 10)
[136] ⚠️ High run-to-run variance (CV=299%) — consider re-running with --runs 5
[137] ⚠️ High run-to-run variance (CV=372%) — consider re-running with --runs 5
[138] ⚠️ High run-to-run variance (CV=310%) — consider re-running with --runs 5
[139] ⚠️ High run-to-run variance (CV=178%) — consider re-running with --runs 5
[140] ⚠️ High run-to-run variance (CV=148%) — consider re-running with --runs 5
[141] ⚠️ High run-to-run variance (CV=56%) — consider re-running with --runs 5
[142] ⚠️ High run-to-run variance (CV=73%) — consider re-running with --runs 5
[143] ⚠️ High run-to-run variance (CV=96%) — consider re-running with --runs 5
[144] ⚠️ High run-to-run variance (CV=124%) — consider re-running with --runs 5
[145] ⚠️ High run-to-run variance (CV=104%) — consider re-running with --runs 5
[146] ⚠️ High run-to-run variance (CV=230%) — consider re-running with --runs 5
[147] ⚠️ High run-to-run variance (CV=51%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -3.8% due to: judgment
[148] ⚠️ High run-to-run variance (CV=200%) — consider re-running with --runs 5
[149] (Plugin) Quality unchanged but weighted score is -0.4% due to: tokens (50962 → 72561)
[150] (Isolated) Quality unchanged but weighted score is -16.4% due to: quality, tokens (14119 → 88789), tool calls (0 → 5), time (64.1s → 87.9s)
[151] (Plugin) Quality improved but weighted score is -9.6% due to: tokens (13538 → 57802), tool calls (0 → 3), time (45.4s → 84.2s)
[152] ⚠️ High run-to-run variance (CV=117%) — consider re-running with --runs 5
[153] ⚠️ High run-to-run variance (CV=70%) — consider re-running with --runs 5
[154] ⚠️ High run-to-run variance (CV=68%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -5.2% due to: tokens (32056 → 58482), tool calls (2 → 3), time (40.4s → 51.2s)
[155] ⚠️ High run-to-run variance (CV=111%) — consider re-running with --runs 5
[156] ⚠️ High run-to-run variance (CV=59%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -14.2% due to: judgment, quality
[157] ⚠️ High run-to-run variance (CV=93%) — consider re-running with --runs 5
[158] ⚠️ High run-to-run variance (CV=54%) — consider re-running with --runs 5
[159] ⚠️ High run-to-run variance (CV=138%) — consider re-running with --runs 5
[160] ⚠️ High run-to-run variance (CV=78%) — consider re-running with --runs 5
[161] ⚠️ High run-to-run variance (CV=164%) — consider re-running with --runs 5
[162] ⚠️ High run-to-run variance (CV=1055%) — consider re-running with --runs 5
[163] ⚠️ High run-to-run variance (CV=67%) — consider re-running with --runs 5
[164] ⚠️ High run-to-run variance (CV=450%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -2.2% due to: tokens (26562 → 62053), tool calls (2 → 5), time (51.1s → 124.0s)
[165] ⚠️ High run-to-run variance (CV=72%) — consider re-running with --runs 5
[166] ⚠️ High run-to-run variance (CV=53%) — consider re-running with --runs 5
[167] ⚠️ High run-to-run variance (CV=1008%) — consider re-running with --runs 5
[168] ⚠️ High run-to-run variance (CV=185%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -0.5% due to: efficiency metrics
[169] ⚠️ High run-to-run variance (CV=140%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -40.8% due to: judgment, quality, tool calls (5 → 7), tokens (43205 → 51701)
[170] ⚠️ High run-to-run variance (CV=997%) — consider re-running with --runs 5
[171] ⚠️ High run-to-run variance (CV=134%) — consider re-running with --runs 5
[172] (Plugin) Quality unchanged but weighted score is -3.0% due to: time (12.3s → 28.5s)
[173] ⚠️ High run-to-run variance (CV=90%) — consider re-running with --runs 5
[174] ⚠️ High run-to-run variance (CV=170%) — consider re-running with --runs 5
[175] ⚠️ High run-to-run variance (CV=3718%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -55.4% due to: quality, judgment, tokens (13207 → 42532), tool calls (0 → 4), time (34.7s → 88.1s)
[176] ⚠️ High run-to-run variance (CV=11656%) — consider re-running with --runs 5. (Plugin) Quality dropped but weighted score is +20.6% due to: efficiency metrics
[177] ⚠️ High run-to-run variance (CV=320%) — consider re-running with --runs 5. (Plugin) Quality improved but weighted score is -8.7% due to: tokens (12849 → 38875), quality, tool calls (0 → 3), time (22.1s → 110.5s)
[178] ⚠️ High run-to-run variance (CV=1857%) — consider re-running with --runs 5
[179] ⚠️ High run-to-run variance (CV=64%) — consider re-running with --runs 5
[180] ⚠️ High run-to-run variance (CV=89%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -13.1% due to: tokens (26214 → 70061), quality, tool calls (2 → 5), time (41.7s → 81.8s)
[181] ⚠️ High run-to-run variance (CV=195%) — consider re-running with --runs 5
[182] ⚠️ High run-to-run variance (CV=65%) — consider re-running with --runs 5
[183] ⚠️ High run-to-run variance (CV=170%) — consider re-running with --runs 5
[184] ⚠️ High run-to-run variance (CV=108%) — consider re-running with --runs 5
[185] ⚠️ High run-to-run variance (CV=143%) — consider re-running with --runs 5
[186] ⚠️ High run-to-run variance (CV=170%) — consider re-running with --runs 5
[187] ⚠️ High run-to-run variance (CV=70%) — consider re-running with --runs 5. (Plugin) Quality unchanged but weighted score is -1.9% due to: tokens (28050 → 37614)
[188] ⚠️ High run-to-run variance (CV=90%) — consider re-running with --runs 5. (Isolated) Quality unchanged but weighted score is -4.0% due to: quality, time (37.1s → 48.2s)
[189] ⚠️ High run-to-run variance (CV=105%) — consider re-running with --runs 5
[190] ⚠️ High run-to-run variance (CV=537%) — consider re-running with --runs 5. (Isolated) Quality improved but weighted score is -56.7% due to: judgment, quality, tokens (53879 → 181309), tool calls (4 → 12), time (70.0s → 104.7s)
[191] ⚠️ High run-to-run variance (CV=67%) — consider re-running with --runs 5
[192] ⚠️ High run-to-run variance (CV=127%) — consider re-running with --runs 5
[193] (Plugin) Quality unchanged but weighted score is -9.0% due to: tokens (12837 → 33419), tool calls (0 → 1), time (27.0s → 43.2s)

⏰ timeout — run(s) hit the (30s, 60s, 120s, 160s, 180s, 240s, 300s, 360s, 600s, 1050s) scenario timeout limit; scoring may be impacted by aborting model execution before it could produce its full output (increase via timeout in eval.yaml)

Model: claude-opus-4.6 | Judge: claude-opus-4.6

🔍 Full Results - additional metrics and failure investigation steps

To investigate failures, paste this to your AI coding agent:

For PR 854 in dotnet/skills, download eval artifacts with gh run download 28828967608 --repo dotnet/skills --pattern "skill-validator-results-*" --dir ./eval-results, then fetch https://raw.githubusercontent.com/dotnet/skills/a2845b56d2bd28cad93f95090fa34a4c6c149478/eng/skill-validator/src/docs/InvestigatingResults.md and follow it to analyze the results.json files. Diagnose each failure, suggest fixes to the eval.yaml and skill content, and tell me what to fix first.

▶ Sessions Visualisation -- interactive replay of all evaluation sessions
📊 Session Analytics (preview) -- aggregated metrics across evaluation sessions

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

Copilot code review Copilot Copilot left review comments
@AbhitejJohn AbhitejJohn AbhitejJohn approved these changes
@JanKrivanek JanKrivanek Awaiting requested review from JanKrivanek JanKrivanek is a code owner
@ViktorHofer ViktorHofer Awaiting requested review from ViktorHofer ViktorHofer is a code owner
@YuliiaKovalova YuliiaKovalova Awaiting requested review from YuliiaKovalova YuliiaKovalova is a code owner
@Redth Redth Awaiting requested review from Redth Redth is a code owner
@jfversluis jfversluis Awaiting requested review from jfversluis jfversluis is a code owner
@artl93 artl93 Awaiting requested review from artl93 artl93 is a code owner
@marklio marklio Awaiting requested review from marklio marklio is a code owner
@brianrob brianrob Awaiting requested review from brianrob brianrob is a code owner
@noahfalk noahfalk Awaiting requested review from noahfalk noahfalk is a code owner
@agocke agocke Awaiting requested review from agocke agocke is a code owner
@leslierichardson95 leslierichardson95 Awaiting requested review from leslierichardson95 leslierichardson95 is a code owner
@lewing lewing Awaiting requested review from lewing lewing is a code owner
@webreidi webreidi Awaiting requested review from webreidi webreidi is a code owner

Assignees

No one assigned

Labels

pr-state/ready-for-eval PR is mergeable and awaiting evaluation

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@adityamandaleeka @AbhitejJohn