← ClaudeAtlas

review-fulllisted

Pre-release cross-domain review with go/no-go recommendation. Use for release gates, major milestones, or when multiple domains changed and you need a single assessment.
mayankmankhand/llm-peer-review · ★ 7 · AI & Automation · score 74
Install: claude install-skill mayankmankhand/llm-peer-review
# Full Review - Pre-Release Check Mile wide, inch deep. Cross-domain release readiness, not a deep specialist review. **Use this when:** Pre-release gate, major milestone check, or when multiple domains changed significantly and you need a single go/no-go assessment. **Don't use this when:** You need deep review of one area - use /review-code, /review-commands, /review-plan, /review-ux, or /review-browser instead. This command will recommend which specialist review to run if it finds areas needing deeper attention. ## Critical Rules <rules> 1. **THE REVIEW PHASE REPORTS ONLY** - Reviewing never edits files; findings and a go/no-go recommendation are its product. After the report, the same run continues into the auto loop (rule 2), which is what applies fixes 2. **Audit, then auto-fix, with pages** - Release-readiness findings are audited before the report per M2 in `.claude/skills/shared/hitl-loop.md`, so the report shows survivors only plus an Audited out log for the kills. They do not then wait for a human "fix it": after the report, survivors are auto-fixed and re-verified, and each finding exits as page, digest, or log per `.claude/skills/shared/hitl-loop.md` (pages only per M1). The release decision itself stays with the user: releases and version bumps are always-ask (M9). Saying "report only" keeps a run report-first (M10) 3. **Explain simply** - Use plain English, avoid jargon 4. **Don't duplicate specialist reviews** - Prioritize cross-domain issues, release blo