critique-doc
Hardnosed critic for fact-find, plan-feature, and process/skill documents. Surfaces weak claims, missing evidence, hidden assumptions, feasibility gaps, and unaddressed risks with no glazing.
npx skills add majiayu000/claude-skill-registry --skill critique-doc --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Critique Document (Compact Hardnosed Mode) Critique fact-find, plan-feature, or process/skill documents for decision quality. No compliments, no filler, no vibe-based approval. ## Operating Mode READ-ONLY CRITIQUE Allowed: - Read target document and referenced docs/code/tests - Search repo for verification - Inspect git history for evidence Not allowed: - Editing target document - Code changes - Commits - Creating new docs ## Inputs Required: - Path to target doc Supported targets: - Planning docs (`docs/plans/*-fact-find.md`, `docs/plans/*-plan.md`) - Domain plan docs (for example `docs/cms-plan/*.md`) - Process/skill docs (for example `.claude/skills/*/SKILL.md`) Optional: - Scope: `full` (default) or `focused` - Context: extra constraints to pressure-test - Prior critique reference (for delta scoring) ## Auto-Detection and Schema Mode Detection order: 1. If frontmatter `Type` is `Fact-Find` or `Plan` and structure is consistent, use Section A or B. 2. Else if structure is consistent with planning docs, use Section A or B (filename is supportive, not required). 3. Else use Section C (Process schema mode). If `Type` conflicts with structure: - Route by structure - Downgrade conf
- Operating Mode
- Inputs
- Auto-Detection and Schema Mode
- Tone and Stance
- Materiality and Anti-Pedantry Rules
- Core Method (Required)
- Step 0 - Frame the Decision
- Step 1 - Structural Map
- Step 2 - Claim-Evidence Audit
- Step 2A - Source Conflict Arbitration (Before Scoring)
- Step 3 - Assumption Mining
- Step 4 - Logic Check
- Step 5 - Feasibility and Execution Reality
- Step 6 - Contrarian Attacks
What does the critique-doc skill do?
Hardnosed critic for fact-find, plan-feature, and process/skill documents. Surfaces weak claims, missing evidence, hidden assumptions, feasibility gaps, and unaddressed risks with no glazing.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill critique-doc --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.