Review Quality

🌐Community
by heyvhuang · vlatest · Repository

Evaluates text reviews based on clarity, relevance, sentiment, and helpfulness, providing actionable improvement suggestions.

Install on your platform

We auto-selected Claude Code based on this skill’s supported platforms.

1

Run in terminal (recommended)

terminal
claude mcp add review-quality npx -- -y @trustedskills/review-quality
2

Or manually add to ~/.claude/settings.json

~/.claude/settings.json
{
  "mcpServers": {
    "review-quality": {
      "command": "npx",
      "args": [
        "-y",
        "@trustedskills/review-quality"
      ]
    }
  }
}

Requires Claude Code (claude CLI). Run claude --version to verify your install.

About This Skill

What it does

The Review Quality skill provides a unified review process to determine if code changes are ready for merging or production deployment. It combines three perspectives: merge readiness (alignment with requirements, risk assessment, and verification), code maintainability based on Clean Code principles, and documentation consistency between the codebase and associated documentation. This skill aims to streamline reviews and reduce decision fatigue by automatically triaging review lenses.

When to use it

  • As a standard part of the Ship Faster review process – always run this skill first.
  • When evaluating changes that might impact React/Next.js performance.
  • When UI surface changes are introduced, ensuring adherence to Web Interface Guidelines (accessibility, focus management, forms, motion, and content overflow).
  • For reviews where documentation consistency is a key concern.

Key capabilities

  • Unified Review Lens: Combines merge readiness, code maintainability, and documentation consistency into a single review.
  • Auto-Triage: Automatically determines which specialized review lenses to apply based on the diff content.
  • React/Next.js Performance Risk Detection: Identifies changes that may impact React/Next.js performance and suggests running review-react-best-practices.
  • Web Interface Guidelines Audit: Checks UI code against Web Interface Guidelines, providing concise file:line findings.
  • Docs-Only Change Optimization: Focuses the review on documentation consistency and release risk when changes are limited to documentation files.

Example prompts

  • "Review these changes for merge readiness."
  • "Evaluate this pull request's code maintainability."
  • "Check if these UI changes adhere to accessibility guidelines."

Tips & gotchas

  • Input Requirements: For best results, provide BASE_SHA and HEAD_SHA representing the diff being reviewed. Optional inputs like PLAN_OR_REQUIREMENTS path, docs scope, and run_dir can further refine the review.
  • Auto-Triage Limitations: The auto-triage system uses predefined rules to determine which additional reviews to run; these rules are not customizable by the user.
  • Performance Keyword Detection: The React/Next.js performance check relies on keyword detection within the diff, which might not be exhaustive.

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 HubPass
SocketPass
SnykPass

Details

Version
vlatest
License
Author
heyvhuang
Installs
29

🌐 Community

Passed automated security scans.