mrbaeksang/ai-project-audit/project-audit
Claude Code and agent skill by mrbaeksang/ai-project-audit
- community
Checking that the SKILL.md file is still in the repository.
Service-profile-driven project audit. Auto-fires when the user requests audit, review, code review, pre-launch check, security audit, OWASP/SOLID/12-Factor compliance, project skeleton/bootstrap/setup, or any equivalent in any language (e.g., 점검, 감사, 리뷰, 출시 전 검토, 보안 점검, 골조, 셋업). Reads the full 0–10 section checklist from SPEC.md, filters items by grade (🔴🟠🟡🔵⚪) against the user's service profile, and outputs results as ✅❌⚠️⏭️ markers re-sorted by risk. Respond in the user's language.
Install
npx vskill@latest install mrbaeksang/ai-project-audit/project-auditSKILL.md
Project Audit
This skill carries no checklist content of its own. The full checklist (service profile YAML, grade definitions, stage-to-section matching, 0–10 section items) is in `SPEC.md` at the plugin root. Read it when running an audit.
Workflow
0. Get the service profile first
The user's first audit request usually omits the profile. Ask for missing fields in one batch (not drip-fed):
Without the profile, AI defaults to "everything required" or "everything skippable" — both wrong.
1. Match stage to sections
| Stage | Sections | Grade filter | |
|---|---|---|---|
| planning / skeleton | 0 | all | |
| building features | 0, 1, 2, 6 | 🔴 + 🟠 | |
| pre-launch | 0–10 (all) | all | |
| incident | relevant only | all | |
| before adding feature | 1, 2, 4 + relevant | 🔴 + 🟠 |
2. Apply grade filter
For each item, first decide if it applies to this service (based on profile), then check.
- 🔴 Required (always)
- 🟠 Recommended (MAU 1k+ / team 3+ / internet-facing)
- 🟡 Mid-scale (MAU 10k+ / B2B / 99.9% SLA)
- 🔵 Large-scale (MAU 100k+ / microservices / 99.99%)
- ⚪ Optional (skippable with stated reason)
If skipping, output ⏭️ with a one-line reason.
3. Output format
4. Sort ❌ by risk
End the audit with a "fix this first" list:
Combining with karpathy-discipline
When this skill provides patch code for ❌ items, the karpathy-discipline skill applies automatically:
- Surgical patch — only the failing item, not adjacent code
- No 1-use abstractions
- Match existing style
- Mention any related dead code; don't delete it
Language
Respond in the user's language. Item names from SPEC.md may be translated for display; keep # numbers and grade emojis as-is.
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/project-audit/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/mrbaeksang/ai-project-audit/project-audit)