Critic Critic — Development agent for Claude Code
Critic for the critic skill.
How to install Critic Critic
Installs to ~/.claude/agents/ys227yeyyey-claude-critic-skill-critic_critic.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/ys227yeyyey/claude-critic-skill/HEAD/agents/critic_critic.md -o ~/.claude/agents/ys227yeyyey-claude-critic-skill-critic_critic.md Restart Claude Code, or start a new session, for it to be picked up.
What Critic Critic does
name: critic_critic description: Critic for the critic skill. Lists the weak points of the Proposer's proposal and rates it on three levels: Strong / Weak / Broken. tools: Read, Grep, Glob model: sonnet
Principles:
- Read the task and the Proposer's reply (ACTION / REASON) received in the prompt. If needed, verify against project files with Read / Grep / Glob.
- List the proposal's weak points concretely (oversights, errors, risks, irreversible operations, etc.). If there are none, s
Alternatives in Development
- Seam Analyzer — Hunts for a missing type at a seam — structure flattened and rebuilt downstream, hand-maintained lists held to 2.2k ★
- Documentation Writer Agent — You are a technical writer who creates clear, accurate, and maintainable documentation 1.3k ★
- Controller Agent — Creates thin, RESTful Rails controllers with strong parameters, proper error handling, and request specs 652 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Critic Coordinator
Judge for the critic skill. Reads the weak points, forms its own verdict, and returns the stricter of its verd
Jtbd Critic
Pre-build review of a feature proposal in prose (not a diff). Lists each job-to-be-done the feature creates —
Spectastic Critic
Adversarial reviewer for a spectastic change proposal. Finds exactly three risks — the most regrettable change
Plan Feature Touch Points
Identifies the specific existing files and modules that will need to be modified or extended for a proposed fe
Candidate
Answers interview questions in first person AS Max, grounded strictly in his real experience. Spawned by /mock
Tracer
For a bug still unexplained after a fix attempt failed: "I already tried fixing this and it is still broken".
Related Skills
Yotta Mirror
Deterministic, local learning-diagnostics skill for AI agents: score sheets plus an item-to-knowledge map beco
Takeclass Recap
Weekly recap of your English practice — sessions, vocabulary, weak points, next focus
AI Answer Fact Checker
Claude Code skill that lists the claims in an AI answer that could be wrong, rates each one's risk, and says e
