idea-analogist
想法群聊室 — 类比者角色。被 idea-team 主编排器调用,或用户单独说"类比一下"、"别的行业有没有"、"yes-and 扩展"、"X 让你想到什么"、"跨界启示"时触发。**专门做跨界类比 + yes-and 扩展——不评判、不挑刺、不要求事实证据**。Do NOT use when 用户要数据(用…
Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.
$ npx -y skills add majiayu000/spellbook --skill project-health-auditor --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/project-health-auditorContext preview
The summary Claude sees to decide when to auto-load this skill.
Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure.
name: project-health-auditor description: Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing project structure. allowed-tools: Read, Grep, Glob, Bash
> Inspired by [claude-code-plugins-plus](https://github.com/jeremylongshore/claude-code-plugins-plus)
Analyze codebase health across multiple dimensions: code quality, dependencies, security, testing, documentation, and architecture.
# Count lines per file (identify large files) find src -name "*.ts" -o -name "*.js" | xargs wc -l | sort -n # Find long functions (over 50 lines) # Check for deeply nested code # Identify duplicate code patterns
| Smell | Indicator | Action | |-------|-----------|--------| | Long files | >500 lines | Split into modules | | Long functions | >50 lines | Extract methods | | Deep nesting | >4 levels | Flatten logic | | Many parameters | >5 params | Use objects | | Duplicate code | Similar blocks | Extract shared | | Dead code | Unused exports | Remove | | Magic numbers | Hardcoded values | Use constants |
## Code Quality Audit - [ ] No files over 500 lines - [ ] No functions over 50 lines - [ ] No nesting deeper than 4 levels - [ ] No functions with >5 parameters - [ ] No obvious code duplication - [ ] No dead/unused code - [ ] Consistent naming conventions - [ ] Proper error handling
# Check outdated packages (npm) npm outdated # Check for vulnerabilities npm audit # Analyze bundle size npx webpack-bundle-analyzer # Check unused dependencies npx depcheck
| Metric | Healthy | Warning | Critical | |--------|---------|---------|----------| | Outdated (major) | 0 | 1-3 | >3 | | Outdated (minor) | <5 | 5-10 | >10 | | Vulnerabilities | 0 | Low/Med | High/Crit | | Unused deps | 0 | 1-3 | >3 | | Bundle size | <500KB | 500KB-1MB | >1MB |
## Dependencies Audit - [ ] No critical vulnerabilities - [ ] No high vulnerabilities - [ ] <3 major version updates pending - [ ] No unused dependencies - [ ] Lock file in sync - [ ] Bundle size reasonable
# Check for secrets in code grep -r "password\|secret\|api_key\|token" --include="*.ts" --include="*.js" # Check for hardcoded credentials grep -r "Bearer \|Basic " --include="*.ts" # Check .env is gitignored cat .gitignore | grep ".env"
| Check | Concern | Solution | |-------|---------|----------| | Secrets in code | Credential exposure | Use env vars | | .env committed | Secret leak | Add to .gitignore | | SQL strings | SQL injection | Use parameterized queries | | User input in HTML | XSS | Sanitize/escape | | Outdated deps | Known vulns | Update regularly | | No rate limiting | DoS | Add rate limits | | No input validation | Injection | Validate all inputs |
## Security Audit - [ ] No hardcoded secrets - [ ] .env files gitignored - [ ] Dependencies scanned for vulns - [ ] Input validation in place - [ ] Output encoding for XSS - [ ] SQL injection prevention - [ ] Authentication implemented - [ ] Authorization checks exist
# Run tests with coverage (npm/jest) npm test -- --coverage # Run tests with coverage (pytest) pytest --cov=src --cov-report=html
| Metric | Good | Acceptable | Poor | |--------|------|------------|------| | Line coverage | >80% | 60-80% | <60% | | Branch coverage | >70% | 50-70% | <50% | | Function coverage | >80% | 60-80% | <60% |
## Testing Audit - [ ] Unit tests exist - [ ] Integration tests exist - [ ] Line coverage >60% - [ ] Critical paths tested - [ ] Edge cases covered - [ ] Tests run in CI - [ ] Test execution <5 min - [ ] No flaky tests
# Check for README ls README.md # Check for API docs ls docs/ || ls documentation/ # Check for inline docs (JSDoc, docstrings) grep -r "@param\|@returns\|Args:\|Returns:" src/
| Doc Type | Purpose | Required | |----------|---------|----------| | README.md | Project overview | Always | | CONTRIBUTING.md | Contribution guide | Open source | | API docs | Endpoint reference | APIs | | Code comments | Complex logic | As needed | | Architecture docs | System design | Large projects | | CHANGELOG.md | Version history | Libraries |
## Documentation Audit - [ ] README exists and current - [ ] Installation instructions - [ ] Usage examples - [ ] API documentation - [ ] Contributing guide - [ ] License specified - [ ] Complex code documented
| Aspect | Check | Concern | |--------|-------|---------| | Coupling | Import chains | Tight coupling | | Cohesion | Module size | God modules | | Layers | Directory structure | Layer violations | | Dependencies | Package.json | Circular deps | | Config | Hardcoded values | Environment issues |
## Architecture Smells - Circular dependencies - God classes/modules - Feature envy (cross-module reaching) - Shotgun surgery (changes touch many files) - Inappropriate intimacy (modules know too much)
## Architecture Audit - [ ] Clear module boundaries - [ ] No circular dependencies - [ ] Proper layer separation - [ ] Configuration externalized - [ ] Environment-specific settings - [ ] Scalability considered - [ ] Single responsibility
# Project Health Report **Project:** [Name] **Date:** [Date] **Auditor:** Claude ## Summary | Category | Score | Status | |----------|-------|--------| | Code Quality | X/10 |
Cross-runtime skills for Claude Code, Codex, and multi-agent workflows.
Repo: majiayu000/spellbook
想法群聊室 — 类比者角色。被 idea-team 主编排器调用,或用户单独说"类比一下"、"别的行业有没有"、"yes-and 扩展"、"X 让你想到什么"、"跨界启示"时触发。**专门做跨界类比 + yes-and 扩展——不评判、不挑刺、不要求事实证据**。Do NOT use when 用户要数据(用…
想法群聊室 — 反方角色。被 idea-team 主编排器调用,或用户单独说"反方意见"、"挑这个想法的刺"、"为什么会失败"、"找漏洞 / 反例"、"devil's advocate"时触发。**专门挑漏洞、找隐藏假设、给反例——不安慰、不"也许可以这样"、不全盘否定**。Do NOT use when…
想法群聊室 — 调研员角色。被 idea-team 主编排器调用,或用户单独说"调研一下 X"、"X 的现状/竞品/数据"、"找 2026 数据"、"事实底"时触发。**用 WebSearch 拉真实 2026 数据、列竞品、引来源——只给事实,不评判,不建议**。Do NOT use when…
想法群聊室主持人 — 把一句话想法丢给多角色 AI 团队(调研员/反方/类比者)做查漏补缺。每个角色有自己的 voice,他们互相 @ 接话;你随时插话。**这是创意扩展工具,不打分、不否决、不堵路**。Use when 用户说"组个团队聊一下"、"开会讨论这个想法"、"找几个角度看看"、"群聊一下 X"、"team…
端到端产品教练 — 把一句话想法走到 PRD + 可点击 HTML 原型。会顶嘴、强制砍功能、用 Nielsen + Norman 做友好性硬检。Use when user 说"我有一个想法"、"想做一个产品"、"做 MVP"、"写 PRD"、"做用户友好的产品",或调用插件命令…
Mobile app UI design expert for iOS and Android. Use when designing app interfaces, creating design systems, ensuring accessibility, or following platform…