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/vibeeval/vibecosystem --skill project-audit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。
Claude Code CLI commands, flags, headless mode, and automation patterns
OpenAI Codex CLI + Claude Code (Hizir) birlikte kullanim rehberi. Is dagitim pattern'leri, GitHub Actions workflow ornekleri, review dongusu ve iki AI yazilim asistaninin guclu yanlarini birlestiren orchestration stratejileri.
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture)
基于 SOC 职业分类
正在显示 SKILL.md
| name | project-audit |
| description | Security scan, dead code detection, and code quality audit for any project |
| version | 1.0.0 |
| category | quality |
| tags | ["security","dead-code","audit","sast","quality"] |
Automated security + quality scan for any codebase. Generates a report, then optionally auto-fixes safe issues.
# Scan current directory
vibeco audit
# Scan specific path
vibeco audit /path/to/project
# Auto-fix safe issues (console.log removal)
vibeco audit --fix
# JSON output for CI integration
vibeco audit --json
Color-coded report with grade (A+ to F):
Saved to .vibeco-audit.json in project root. Contains all findings for programmatic processing.
Currently auto-fixes:
Does NOT auto-fix (manual review required):
1. vibeco audit -> Scan, generate report
2. Review report -> Understand issues
3. vibeco audit --fix -> Auto-fix safe issues
4. Manual fixes -> Address security findings
5. vibeco audit -> Re-scan to verify
node_modules, dist, .git, vendor, pycache, .next, build, coverage
Test files (*.test.ts, *.spec.js, tests/, mocks/) are excluded from security scanning to avoid false positives.