Review Chamber
Analyzes text inputs like code or writing, providing structured feedback on clarity, style, and potential improvements.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add review-chamber npx -- -y @trustedskills/review-chamber
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"review-chamber": {
"command": "npx",
"args": [
"-y",
"@trustedskills/review-chamber"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The review-chamber skill provides a structured environment for evaluating and refining AI agent outputs. It allows users to define specific criteria, assign weights to those criteria, and then receive feedback on how well an output meets those standards. This facilitates iterative improvement of the AI's performance through targeted adjustments and prompt engineering.
When to use it
- Evaluating draft content: Assess a blog post draft against clarity, accuracy, and tone guidelines before publication.
- Refining code generation: Check generated code for functionality, efficiency, and adherence to coding standards.
- Improving creative writing: Get feedback on story elements like plot coherence, character development, and pacing.
- Validating research summaries: Ensure a summary accurately reflects the key findings of a research paper based on defined criteria.
Key capabilities
- Criteria definition with weighting
- Output evaluation against specified criteria
- Feedback generation based on evaluation results
- Iterative refinement process support
Example prompts
- "Review this email draft for professionalism and clarity, weighting clarity 60% and professionalism 40%."
- "Evaluate the following code snippet for efficiency and readability. Efficiency is more important (70%) than readability (30%)."
- "Assess this short story excerpt based on plot coherence (50%), character development (30%), and pacing (20%)."
Tips & gotchas
The quality of the review depends heavily on clearly defined criteria. Vague or poorly-defined criteria will result in less actionable feedback.
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.