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.
Scanned 5/27/2026
Install via CLI
openskills install huangjia2019/claude-code-engineering---
name: code-health-check
description: 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.
context: fork
agent: general-purpose
allowed-tools:
- Read
- Grep
- Glob
---
# Code 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:
```markdown
# 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}
```
No comments yet. Be the first to comment!
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Ultra-compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", "/review", or invokes /caveman-review. Auto-triggers when reviewing pull requests.
Remove unused code from this project with ultrawork mode, LSP-verified safety, atomic commits. Triggers: remove dead code, dead code, cleanup, remove unused.
Verification loop for Django projects: migrations, linting, tests with coverage, security scans, and deployment readiness checks before release or PR.
一个全面的 Claude Code 会话验证系统。