メニュー
Multi-pass quality audit that rates code across 5 dimensions (security, performance, code quality, UX/DX, competitive analysis). Use when someone says: run judges, be brutal, audit this, is this production ready. Defaults to NEEDS WORK. No inflated scores.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Use when a conversation is getting long, drifting, juggling multiple tasks, re-pasting the same files, or showing stale/confused context — and at the start of any new task. Triggers: long thread, context bloat, topic switch, repeated file uploads, 'why is it forgetting', degraded answers, finished one task and starting another.
Use when a user wants to deconstruct a complex problem, business challenge, product decision, strategy question, career crossroads, or stuck situation by stripping assumptions, identifying first principles, rebuilding options from foundational truths, and choosing one high-leverage action.
Audit role-based access control and permission drift across product surfaces.
Add a new feature to an existing @fabrk/* package following monorepo conventions
Build or rebuild the ADR index and dependency graph in AgentDB
Query AgentDB with semantic routing, hierarchical recall, causal graphs, and context synthesis
| name | brutal-audit |
| description | Multi-pass quality audit that rates code across 5 dimensions (security, performance, code quality, UX/DX, competitive analysis). Use when someone says: run judges, be brutal, audit this, is this production ready. Defaults to NEEDS WORK. No inflated scores. |
Run a 5-pass quality audit on the current codebase or specified files. Be honest. Default stance is "NEEDS WORK" — only give high marks when genuinely earned.
Identify scope: Ask what to audit if not obvious. Default to the entire project in the current working directory.
Run all 5 passes sequentially:
npm audit if applicable)For each pass, output:
## Pass N: [Dimension] — Grade: [C+ to A]
### Issues Found
1. [CRITICAL] Description — file:line
2. [HIGH] Description — file:line
3. [MEDIUM] Description — file:line
4. [LOW] Description — file:line
### What's Actually Good
- Thing that genuinely works well
Then output a summary:
## Overall Verdict
| Dimension | Grade | Issues |
|-----------|-------|--------|
| Security | B- | 3 |
| Performance | C+ | 7 |
| Code Quality | B | 4 |
| UX/DX | C+ | 8 |
| Competitive | B- | 2 |
**Overall: [GRADE]**
**Production Ready: YES / NO / ALMOST**
## Critical Fixes (do these now)
1. ...
2. ...
## High Priority (do these this week)
1. ...
2. ...