Code Health Check Skill for Claude
Perform a comprehensive code health check on a directory. Use when the user asks to analyze code quality, find issues, or get a health report.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/huangjia2019/claude-code-engineering --skill code-health-checkThe instruction itself
9 sections, as written by the authorCode Health Check
Analyze the codebase at $ARGUMENTS and produce a structured health report.
Checks to Perform
1. File Organization
- Are files reasonably sized? (Flag files > 200 lines)
- Is the directory structure logical?
- Any files that look misplaced?
2. Error Handling
- Are async operations wrapped in try/catch?
- Are errors propagated correctly (not swallowed)?
- Is there a global error handler?
3. Security Basics
- Any hardcoded secrets, API keys, or passwords?
- Any use of
eval()or similar dangerous functions? - Are user inputs validated before use?
4. Code Quality
- Any obvious code duplication (similar blocks in multiple files)?
- Any unused variables or imports?
- Are function signatures reasonable (not too many parameters)?
5. Dependency Hygiene
- Are all imported modules actually used?
- Any circular dependencies?
Severity Levels
Use these to categorize issues:
| Severity | Meaning | Example |
|----------|---------|---------|
| CRITICAL | Must fix immediately | Hardcoded secrets, SQL injection |
| WARNING | Should fix soon | Missing error handling, large files |
| INFO | Nice to improve | Minor duplication, naming conventions |
Output Format
Return a structured report in this exact format:
# Code Health Report: {directory}
## Overall Score: {A/B/C/D/F}
## Summary
- Files analyzed: {count}
- Issues found: {critical} critical, {warning} warnings, {info} info
## Critical Issues
{list each with file:line and description}
## Warnings
{list each with file:line and description}
## Info
{list each with file:line and description}
## Recommendations
{top 3 actionable recommendations}
Other skills for the same job
different authors, same section of the catalogue
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.
GitHub CLI (gh) comprehensive reference for repositories, issues, pull requests, Actions, projects, releases, gists, codespaces, organizations, extensions, and all GitHub operations from the command line.
GitHub CLI - manage repositories, issues, pull requests, actions, releases, and more from the command line.
You are a code refactoring expert specializing in clean code principles, SOLID design patterns, and modern software engineering best practices. Analyze and refactor the provided code to improve its quality, maintainability, and performance.
You are a technical debt expert specializing in identifying, quantifying, and prioritizing technical debt in software projects. Analyze the codebase to uncover debt, assess its impact, and create acti
How to use it
Take huangjia2019/code-health-check from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.