Skip to content

docs(refs): prompts-integration Phase-E + skills-roster publishing reframe (BRO-1591)#84

Merged
broomva merged 1 commit into
mainfrom
feature/bro-1591-prompts-roster-docs
Jun 29, 2026
Merged

docs(refs): prompts-integration Phase-E + skills-roster publishing reframe (BRO-1591)#84
broomva merged 1 commit into
mainfrom
feature/bro-1591-prompts-roster-docs

Conversation

@broomva

@broomva broomva commented Jun 29, 2026

Copy link
Copy Markdown
Owner

What & why

Finishes the two doc edits that were stashed (stash@{0}) during the BRO-1588 pull so the working tree could be cleaned. Closes BRO-1591.

Changes (2 reference docs, no code)

references/prompts-integration.md — purely additive

  • New ## The evaluation engine (Phase E) — from telemetry to judgment section: the krisis (κρίσις) judge crate, Vigil OTLP-sidecar capture, the store-judgments-not-content privacy invariant, the broomva evals {show,list,tail,rubric validate} CLI, and how it deepens the P6/P11/P13 composition.
  • Refreshed "See also" to the 2026-06-02 design spec + the project/entity tracking nodes.

references/skills-roster.md — surgical reframe (origin's row work untouched)

  • Reframes the publishing standard: a repo-root SKILL.md is standard-valid; the defect is the open upstream CLI bug vercel-labs/skills#1523 (verified still OPEN), not the layout.
  • Adds the monorepo-consolidation canonical fix (BRO-1561) and the skillify advise-not-reject note (BRO-1581 — step 1b WARNs, no longer rejects a standard-valid layout).
  • Fixes the stale banner count 56 → 61 (current roster size after BRO-1586).
  • Kept intact: origin's *(consolidated → …)* / ecosystem-product row annotations and the > Canonical installable roster: banner (the stash predated that work; only the publishing-standard prose was ported).

Validation

  • Full tests/*.test.sh: 24/24 pass (no change to companion-skills.yaml, which is what the roster tests validate).
  • External factual claim verified: skills#1523 state: OPEN.
  • P18: reference docs → markdown (correct audience). P20: doc-only 2-file reframe, below the substantive-code bar; the one external claim was verified instead of a full cross-model gate.

🤖 Generated with Claude Code

…ng reframe (BRO-1591)

Finishes the two doc edits stashed during the BRO-1588 pull.

- prompts-integration.md: add "Phase E — evaluation engine" section (krisis judge
  crate, Vigil OTLP capture, store-judgments-not-content privacy invariant,
  `broomva evals` CLI, P6/P11/P13 composition); refresh See-also to the 2026-06-02
  design spec + project/entity nodes. Purely additive.
- skills-roster.md: reframe the publishing standard — a repo-root SKILL.md is
  standard-valid; the defect is the open upstream CLI bug vercel-labs/skills#1523
  (verified OPEN), not the layout. Add the monorepo-consolidation canonical fix
  (BRO-1561) + the skillify advise-not-reject note (BRO-1581). Fix the stale banner
  count 56 -> 61. Origin's row annotations kept intact.

No changes to companion-skills.yaml. Full tests/*.test.sh: 24/24.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
@coderabbitai

coderabbitai Bot commented Jun 29, 2026

Copy link
Copy Markdown

Warning

Review limit reached

@broomva, we couldn't start this review because you've reached your PR review rate limit.

More reviews will be available in 26 minutes and 18 seconds. Learn how PR review limits work.

Your organization has used up its prepaid credits, and credit purchases are no longer available. Enable the review add-on in the billing tab to keep reviews running — you're only billed for reviews past your plan's rate limits ($0.25/file).

⌛ How to resolve this issue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based credits.

🚦 How do rate limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please see our Fair Usage Limits Policy for further information.

ℹ️ Review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 6b410cb4-3856-49fa-b6a3-65979cb32567

📥 Commits

Reviewing files that changed from the base of the PR and between 2a45c77 and dac3efa.

📒 Files selected for processing (2)
  • references/prompts-integration.md
  • references/skills-roster.md
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch feature/bro-1591-prompts-roster-docs

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands.

@broomva broomva merged commit 1dc8492 into main Jun 29, 2026
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant