Critique
The Critique skill analyzes text for clarity, tone, and potential weaknesses, helping users refine their writing for better impact.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add critique npx -- -y @trustedskills/critique
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"critique": {
"command": "npx",
"args": [
"-y",
"@trustedskills/critique"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill enables AI agents to perform structured, multi-perspective evaluations of user-generated content. It transforms raw feedback into actionable insights by analyzing text against specific criteria or personas.
When to use it
- Reviewing draft code for logic errors and style consistency before merging.
- Evaluating marketing copy for tone, clarity, and alignment with brand guidelines.
- Assessing student essays or project proposals against a rubric.
- Simulating peer review sessions to identify blind spots in reasoning.
Key capabilities
- Generates detailed critiques based on customizable constraints.
- Adopts specific personas (e.g., senior developer, editor) for targeted feedback.
- Breaks down complex inputs into structured analysis points.
- Highlights strengths and weaknesses with constructive suggestions.
Example prompts
- "Critique this Python script focusing on memory efficiency and error handling."
- "Act as a harsh literary critic and analyze the themes in this short story draft."
- "Review my project proposal for clarity, feasibility, and missing stakeholder requirements."
Tips & gotchas
Provide clear context about the input's purpose before asking for a critique to ensure relevant feedback. If the output is too generic, explicitly define the criteria or persona you want the agent to adopt.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.