brutal-review
Use when user wants brutally honest feedback on business ideas, plans, pitches, or strategies. Triggers on "brutal feedback", "honest review", "devil's advocate", "red team", "tear apart", "critique", "what's wrong with this", "find holes in", "challenge this idea", or requests for harsh/critical evaluation.
npx skills add majiayu000/claude-skill-registry --skill brutal-review --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.
# BRUTAL Review ## Overview Parallel critical analysis using three distinct critic personas at escalating intensity, followed by synthesis with meta-analysis. Each persona uses a different analytical framework to ensure comprehensive coverage. ## Quick Reference | Code | Persona | Intensity | Framework | |------|---------|-----------|-----------| | `da` | Devil's Advocate | Mild | Assumption Autopsy + Bias Scan + Inversion + Steelman | | `rt` | Red Team | Medium | Attack Surface Mapping + Threat Sweep + Adversary Sims + Pre-Mortem | | `gr` | Gordon Ramsay | Intense | Plate Inspection Scores + Bollocking Triplets + Non-Negotiable Fixes | | _(none)_ | All three | Full | Parallel dispatch + synthesis + meta-analysis | ## When NOT to Use - Factual or data-driven assessments (this is opinion-based critique) - When user wants encouragement or validation - Technical code review (use code review tools instead) - When the idea is already in execution and needs operational help, not critique ## Persona Selector $ARGUMENTS may optionally start with a persona code (`da`, `rt`, or `gr`). Parse the first token: - **If first token is a persona code:** Run only that agent. Strip the code from $ARG
- Overview
- Quick Reference
- When NOT to Use
- Persona Selector
- Workflow
- Dispatch
- Synthesis (all-three mode only)
- If Sub-Agent Fails
- Common Mistakes
What does the brutal-review skill do?
Use when user wants brutally honest feedback on business ideas, plans, pitches, or strategies. Triggers on "brutal feedback", "honest review", "devil's advocate", "red team", "tear apart", "critique", "what's wrong with this", "find holes in", "challenge this idea", or requests for harsh/critical evaluation.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill brutal-review --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.