Review
Analyzes text content to provide concise summaries, sentiment scores, and key topic identification.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add review npx -- -y @trustedskills/review
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"review": {
"command": "npx",
"args": [
"-y",
"@trustedskills/review"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
The review skill enables AI agents to systematically analyze, critique, and validate outputs against specific criteria. It transforms raw data or generated text into structured feedback by identifying errors, inconsistencies, or areas for improvement based on user-defined rules.
When to use it
- Validating code snippets for syntax errors before deployment.
- Checking written content for tone, clarity, and adherence to style guides.
- Analyzing financial reports or data summaries for logical inconsistencies.
- Reviewing design mockups against accessibility standards or brand guidelines.
Key capabilities
- Performs deep analysis of input content to detect flaws.
- Generates structured critiques based on configurable parameters.
- Highlights specific areas requiring attention or revision.
- Supports iterative refinement loops for continuous improvement.
Example prompts
- "Review this Python script for potential security vulnerabilities and performance bottlenecks."
- "Analyze the attached marketing email draft for tone consistency and call-to-action clarity."
- "Critique this project proposal against our internal rubric for feasibility and budget alignment."
Tips & gotchas
Ensure you provide clear, specific criteria or rubrics when initiating a review to guide the agent's focus. Complex reviews may require breaking down large documents into smaller sections for more accurate analysis.
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.