feat: anti-skip rule for all review skills (v0.15.6.1)#804
Merged
Conversation
Review skills sometimes skip sections when reviewing strategy or spec plans. This adds an explicit anti-skip rule to CEO (1-11), eng (1-4), design (1-7), and DX (1-8) review skills. Also fixes CEO header from "10 sections" to "11 sections" to match actual count.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
E2E Evals: ✅ PASS14/14 tests passed | $1.82 total cost | 12 parallel runners
12x ubicloud-standard-2 (Docker: pre-baked toolchain + deps) | wall clock ≈ slowest suite |
Main landed v0.15.6.1 (skill prefix self-healing). Bumped our entry to v0.15.6.2 to sit on top. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
joethorngren
added a commit
to joethorngren/jstack
that referenced
this pull request
Apr 6, 2026
Upstream features merged: - GStack Browser with anti-bot stealth (garrytan#695) - Adaptive gating + cross-review dedup for review army (garrytan#760) - Voice-friendly skill triggers for AquaVoice (garrytan#732) - Native OpenClaw skills + ClaHub publishing (garrytan#832) - Declarative multi-host platform (OpenCode, Slate, Cursor, OpenClaw) (garrytan#793) - Interactive /plan-devex-review + DX review skills (garrytan#784, garrytan#796) - Ship re-run verification checks (garrytan#833) - Community security wave — 8 PRs, 4 contributors (garrytan#847) - Security wave 1 — 14 fixes for audit (garrytan#810) - Team-friendly gstack install mode (garrytan#809) - Anti-skip rule for all review skills (garrytan#804) - Various bug fixes and doc updates Conflict resolution strategy: - Branding files (README, CLAUDE.md, CHANGELOG, VERSION, CONTRIBUTING, TODOS): kept jstack - SKILL.md / SKILL.md.tmpl files: took upstream (skill improvements) - Code files (browse/, scripts/, tests, setup, package.json): took upstream - Telemetry files (bin/gstack-telemetry-sync, supabase telemetry-ingest): kept deleted (jstack privacy policy) - New upstream files (hosts/, openclaw/, devex-review/, etc.): accepted as-is Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Review skills sometimes skip sections when reviewing strategy or spec plans, reasoning that "implementation sections don't apply to a strategy doc." This is wrong. Implementation details are where strategy breaks down.
Anti-skip rule added to all 4 review skills:
plan-ceo-review/SKILL.md.tmplplan-eng-review/SKILL.md.tmplplan-design-review/SKILL.md.tmplplan-devex-review/SKILL.md.tmplAlso fixes: CEO review header from "10 sections" to "11 sections" (Section 11 is conditional but exists).
The rule is simple: evaluate every section. If zero findings, say "No issues found" and move on. But you must look.
Pre-Landing Review
No issues found. This is static prompt text in template files, no runtime code.
Test plan
bun testpassesbun run gen:skill-docsregenerates all SKILL.md files🤖 Generated with Claude Code