Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Validates code against coding standards and best practices. Reports compliance violations and suggests fixes.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Find relevant expert skills based on the code being audited:
| File Type | Expert Skills |
|---|---|
.ts, .tsx | typescript-expert, react-expert |
.py | python-backend-expert |
.go | go-expert |
.java | java-expert |
*.test.* | testing-expert |
Read the relevant skill files to understand best practices:
cat .claude/skills/[skill-name]/SKILL.md
Extract key rules and patterns to check for.
Analyze the target files for violations:
Common checks:
Create a structured compliance report:
## Audit Report
**Target**: src/components/
**Skills Applied**: react-expert, typescript-expert
**Date**: YYYY-MM-DD
### Summary
- **Pass**: 12 rules
- **Warn**: 3 rules
- **Fail**: 2 rules
### Violations
#### FAIL: Avoid using `any` type
- **File**: src/components/UserAuth.tsx:45
- **Issue**: `const user: any = await getUser()`
- **Fix**: Define proper User interface
#### WARN: Use Server Components by default
- **File**: src/components/UserAuth.tsx:1
- **Issue**: Missing 'use client' directive but uses useState
- **Fix**: Add 'use client' or refactor to Server Component
</execution_process>
<best_practices>
</best_practices> </instructions>
<examples> <usage_example> **Audit Request**:Audit src/components/ for TypeScript and React best practices
Response:
## Audit Report: src/components/
### Violations Found
1. **[ERROR]** src/components/User.tsx:23
- Rule: Avoid `any` type
- Code: `const data: any = response.json()`
- Fix: `const data: UserResponse = response.json()`
2. **[WARN]** src/components/Form.tsx:1
- Rule: Prefer Server Components
- Issue: Uses useState without 'use client'
- Fix: Add 'use client' directive at top
### Passed Checks
- Component naming (PascalCase) ✓
- Hook usage patterns ✓
- Import organization ✓
</usage_example> </examples>
Before starting:
cat .claude/context/memory/learnings.md
After completing:
.claude/context/memory/learnings.md.claude/context/memory/issues.md.claude/context/memory/decisions.mdASSUME INTERRUPTION: Your context may reset. If it's not in memory, it didn't happen.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Ensure accessibility in UI components including semantic HTML, ARIA attributes, keyboard navigation, and WCAG 2.2 AA compliance.
中文简介正在准备中。当前显示原文说明。
Use when you want to improve response quality through meta-cognitive reasoning. Applies 15+ reasoning methods to reconsider and refine initial outputs.
中文简介正在准备中。当前显示原文说明。
N-round opposing-stance debates for trade-off analysis. Assigns pro/con roles to agents, runs structured debate rounds with quality scoring, and produces a moderator synthesis with confidence-rated recommendation. Generalizable to architecture, technology, security, and design decisions.
中文简介正在准备中。当前显示原文说明。
Force adversarial code review stance that eliminates confirmation bias — reviewer must find issues or re-analyze
中文简介正在准备中。当前显示原文说明。
Creates specialized AI agents on-demand when no existing agent matches a request. Use when the Router cannot find a suitable agent for a task. Enables self-evolution by generating persistent agents.
中文简介正在准备中。当前显示原文说明。
LLM-as-judge evaluation framework with 5-dimension rubric (accuracy, groundedness, coherence, completeness, helpfulness) for scoring AI-generated content quality with weighted composite scores and evidence citations
中文简介正在准备中。当前显示原文说明。