基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/LEEI1337/phantom-neural-cortex --skill code-quality-check命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Stage, commit, and push git changes with conventional commit messages. Use when user wants to commit and push changes, mentions pushing to remote, or asks to save and push their work. Also activates when user says "push changes", "commit and push", "push this", "push to github", or similar git workflow requests.
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews. Activates on phrases like "implement this feedback", "address review comments", "fix review issues", "apply these suggestions", or when user pastes reviewer notes.
Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass. Activates on phrases like "fix the tests", "tests are failing", "make the test suite green", "run tests and fix failures", or "tests aren't passing".
| name | code-quality-check |
| description | Automated code quality verification checklist |
| trigger | auto |
Run this checklist before committing code:
[S] Single Responsibility - Each class/function does ONE thing
[O] Open/Closed - Extend without modifying
[L] Liskov Substitution - Subtypes are substitutable
[I] Interface Segregation - Small, focused interfaces
[D] Dependency Inversion - Depend on abstractions
✓ Names reveal intent
✓ Functions < 20 lines
✓ Max 3 parameters (use objects if more)
✓ No magic numbers/strings
✓ DRY - No duplication
✓ Comments explain WHY not WHAT
✓ All errors caught and handled
✓ No silent failures
✓ Meaningful error messages
✓ Proper logging
✓ Cleanup in finally blocks
✓ No N+1 queries
✓ Proper indexing
✓ Caching where appropriate
✓ Lazy loading for heavy ops
✓ No memory leaks
✓ Input validated
✓ Output sanitized
✓ No SQL injection vectors
✓ No XSS vulnerabilities
✓ Secrets in env vars
✓ Dependencies updated
✓ Unit tests written
✓ Edge cases covered
✓ Mocks used for external deps
✓ Tests are fast (< 1s each)
✓ Coverage > 80%
✓ Public APIs documented
✓ Complex logic explained
✓ README updated
✓ Examples provided
# Run before commit:
1. grep -r "TODO\|FIXME\|XXX\|HACK" .
2. Check for console.log / print statements
3. Verify no commented-out code blocks
4. Check for hardcoded credentials
5. Run linter
6. Run tests