review-worklisted

Independent post-implementation review — an agent with no sunk-cost bias checks just-written code or an artifact against its requirements, then resolves the issues found (max 2 rounds). Use to verify a change before shipping, get a second opinion, or check what you missed; auto-triggers for security-sensitive and data-mutation code. Not for code refactoring (use clean-code) or decision analysis (use debate-agents).
hungv47/meta-skills · ★ 9 · Code & Development · score 75

Install: claude install-skill hungv47/meta-skills

# Review Chain — Fresh-Eyes Post-Implementation Quality Independent reviewer + resolver loop for code, artifacts, plans, or shipped work. Reviewer has no implementation context; resolver synthesizes. Routing in [`routing.yaml`](routing.yaml); methodology + "no critic on critic" in [`references/playbook.md`](references/playbook.md). **Core:** What would a senior reviewer with no sunk-cost bias catch? ## Critical Gates — load first 1. **Reviewer has NO access to implementation reasoning** — only the output + requirements. 2. **Resolver sees BOTH original + review** — synthesizes, not patches. 3. **Max 2 loops.** Not clean after 2 cycles → flag user; may be a design problem review can't fix. 4. **Auto-trigger for critical code** — security, auth, crypto, data mutations, money, PII. Don't wait to be asked. 5. **Quality feedback** — repeated misses, critic overrides, post-humanmaxxing regressions feed [`_shared/quality-feedback-protocol.md`](references/_shared/quality-feedback-protocol.md), not just this report. 6. **Noise-filter before report-write.** Every finding passes [`noise-filter.md`](references/noise-filter.md): Layer 1 (real-vs-fake per `procedures/reviewer.md § Verification rules`) then Layer 2 (Accepted / Rejected / Deferred — three report subsections). Accepted clears fix-then-rerun before Verified. ## Before Starting Apply [`references/_shared/before-starting-check.md`](references/_shared/before-starting-check.md). Then: - **Mode** ([`_shared/mode-resolver.md`