← ClaudeAtlas

skill-reviewlisted

Audits a candidate skill (.github/skills/<name>/SKILL.md) against five gates (spec compliance, content quality, scope fit, safety, currency & coherence). Use when reviewing a new skill draft before commit, evaluating a Mall unit or store skill for adoption, or re-auditing existing skills on a periodic cadence. For instructions, prompts, agents — use the matching per-type review skill.
fabioc-aloha/Alex_ACT_Edition · ★ 0 · AI & Automation · score 75
Install: claude install-skill fabioc-aloha/Alex_ACT_Edition
<!-- intentional divergence from Supervisor: Edition strips Supervisor-only refs (ADR-007, `scripts/brain-qa.cjs` per-script citations, instruction-specific Gate 1 rows since heirs review skills only, and retired-entity examples Supervisor uses in Gate 5 illustrations). Same five gates, same criteria. Audited 2026-05-31. --> # Skill Review Audit a candidate skill against five gates. This brain accepts only what passes all five. For other artifact types: [instruction-review](../instruction-review/SKILL.md), [prompt-review](../prompt-review/SKILL.md), [agent-review](../agent-review/SKILL.md). All four pairs share the same five-gate contract; per-type criteria differ. ## When to Use Three fire contexts: 1. **Author self-audit** — dogfood your own draft before committing. Invoked from [skill-creator](../skill-creator/SKILL.md) Phase 7. 2. **External candidate adoption** — gate before pulling a Mall unit, store skill, or any external artifact into this brain. Decide *whether the artifact is fit* before adopting. 3. **Periodic re-audit** — re-check existing skills during currency-audit or quarterly retraining. Skills that no longer pass the gates revise or retire. This skill carries the judgment checks a brain-qa validator cannot do (mechanical regex/date validation vs. content-quality judgment). Gate 1 partially overlaps with brain-qa where present; Gates 2–4 are judgment-only. ## The Five Gates A candidate must pass **all five** to ship. Failure on any gate = decline or