docs(refs): prompts-integration Phase-E + skills-roster publishing reframe (BRO-1591)#84
Conversation
…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>
|
Warning Review limit reached
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 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 configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (2)
✨ Finishing Touches🧪 Generate unit tests (beta)
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. Comment |
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## The evaluation engine (Phase E) — from telemetry to judgmentsection: thekrisis(κρίσις) judge crate, Vigil OTLP-sidecar capture, the store-judgments-not-content privacy invariant, thebroomva evals {show,list,tail,rubric validate}CLI, and how it deepens the P6/P11/P13 composition.references/skills-roster.md— surgical reframe (origin's row work untouched)SKILL.mdis standard-valid; the defect is the open upstream CLI bug vercel-labs/skills#1523 (verified still OPEN), not the layout.*(consolidated → …)*/ ecosystem-product row annotations and the> Canonical installable roster:banner (the stash predated that work; only the publishing-standard prose was ported).Validation
tests/*.test.sh: 24/24 pass (no change tocompanion-skills.yaml, which is what the roster tests validate).state: OPEN.🤖 Generated with Claude Code