Agent skill · Testing & QA

critique

Adversarial stress test of an idea. Find fatal flaws, hidden assumptions, dependencies, and failure modes. Use after evaluate to break the idea before committing.

majiayu000github.com/majiayu000GitHub ↗
claude-coderead-onlyMIT
Install
npx skills add majiayu000/claude-skill-registry --skill critique-cyberswat-claude-plugin-analys --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 3 KB
Bundled scripts: none
Allowed tools: ReadWebFetchWebSearchGrepGlob
Path: skills/analysis/critique-cyberswat-claude-plugin-analys/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Critique Your job is to break this. Be adversarial. Find the fatal flaws, not minor issues. **Start by reviewing the evaluate output.** Focus your critique on the least scrutinized assumptions, especially those flagged in the Contrarian perspective and any assumptions that multiple perspectives share without questioning. ## Persona If a persona or role is specified, such as "as a security engineer", adopt that expertise lens: - Surface assumptions that persona would challenge - Identify dependencies that persona knows are fragile - Focus on failure modes that persona has seen before - Assess hidden costs through that persona's experience The critique should feel like it comes from a domain expert who has seen things fail. ## Focus For each issue found, assign a severity level: - **Fatal**: This alone could cause the entire approach to fail. Must be addressed before proceeding. - **Serious**: Significant risk that could derail success if not mitigated. Needs a plan. - **Notable**: Worth knowing about but manageable. Should be monitored. Organize findings by these categories: ### Fatal Flaws Issues that could cause complete failure. If none exist, explicitly state that none were fo

What's inside
Steps it walks through
  1. Persona
  2. Focus
  3. Fatal Flaws
  4. Serious Risks
  5. Notable Issues
  6. Pre Mortem
  7. Cross Domain Concerns
  8. Cross Domain Concerns: [X] Perspective
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the critique skill do?

Adversarial stress test of an idea. Find fatal flaws, hidden assumptions, dependencies, and failure modes. Use after evaluate to break the idea before committing.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill critique-cyberswat-claude-plugin-analys --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.

Keep going