← ClaudeAtlas

do-plan-critiquelisted

Use when reviewing a plan before build. Triggered by 'critique this plan', 'review the plan', 'war room', or 'do-plan-critique'.
tomcounsell/ai · ★ 18 · AI & Automation · score 74
Install: claude install-skill tomcounsell/ai
# Plan Critique (War Room) ## Repo Context Probe If `docs/sdlc/do-plan-critique.md` exists, read it and honor its declarations; otherwise use the generic defaults described below. The context file is where a repo layers its SDLC automation onto this generic baseline: stage/status markers around the critique, the repo's mandated plan sections, force-FULL doctrine paths, a resume/roster-completion barrier (a crash-resume probe, a frozen roster manifest, a plan-hash guard, and a membership-gate CLI), a verdict-recording substrate the downstream pipeline reads, and a plan-revising lock. When the file is absent (the common case in a foreign repo), this skill runs entirely on `git`, `gh`, and the Agent tool — it dispatches critics in the foreground, waits for each to return its findings, aggregates, and prints a verdict (no repo-specific tooling required). ## What this skill does Critiques a plan document from a frozen roster of expert perspectives (1 (LITE) or 3 (FULL) critics selected by a triage step) plus automated structural validation. Each critic has a defined lens and returns severity-rated findings. The skill aggregates, deduplicates, and produces a verdict: READY TO BUILD, NEEDS REVISION, or MAJOR REWORK. ## When to load sub-files - Spawning war room critics → read [CRITICS.md](CRITICS.md) for critic definitions and prompt templates ## Plan Resolution Resolve the plan document path and issue number from `$ARGUMENTS`. **IMPORTANT:** Always assign `ISSUE_NUMBER` u