ac-qa-reviewer
Quality assurance review for implementations. Use when reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality.
Best use case
ac-qa-reviewer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Quality assurance review for implementations. Use when reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality.
Teams using ac-qa-reviewer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/ac-qa-reviewer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How ac-qa-reviewer Compares
| Feature / Agent | ac-qa-reviewer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Quality assurance review for implementations. Use when reviewing code quality, checking implementation standards, performing QA cycles, or validating feature quality.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
SKILL.md Source
# AC QA Reviewer
Perform quality assurance reviews on feature implementations.
## Purpose
Reviews completed features for code quality, adherence to standards, security issues, and best practices before marking features as complete.
## Quick Start
```python
from scripts.qa_reviewer import QAReviewer
reviewer = QAReviewer(project_dir)
result = await reviewer.review_feature("auth-001")
```
## Review Dimensions
### Code Quality
- Clean code principles
- DRY (Don't Repeat Yourself)
- SOLID principles
- Code complexity metrics
### Security
- Input validation
- SQL injection prevention
- XSS prevention
- Secure authentication
### Performance
- Algorithm efficiency
- Database query optimization
- Memory usage
- Caching opportunities
### Testing
- Test coverage
- Test quality
- Edge case coverage
- Integration tests
### Documentation
- Code comments
- API documentation
- README updates
- Type annotations
## Review Result
```json
{
"feature_id": "auth-001",
"approved": true,
"score": 85,
"dimensions": {
"code_quality": {"score": 90, "issues": []},
"security": {"score": 85, "issues": ["Consider rate limiting"]},
"performance": {"score": 80, "issues": []},
"testing": {"score": 88, "issues": []},
"documentation": {"score": 82, "issues": ["Add docstring to validate_token"]}
},
"blocking_issues": [],
"suggestions": [
"Consider extracting authentication middleware",
"Add rate limiting for login endpoint"
],
"auto_fixable": ["missing_docstring"]
}
```
## QA Workflow
```
1. SCAN → Static analysis of changed files
2. ANALYZE → Check against quality rules
3. SECURITY → Security-specific checks
4. REVIEW → Contextual code review
5. REPORT → Generate review report
6. FIX → Auto-fix simple issues (optional)
7. APPROVE → Mark as QA passed or request changes
```
## Quality Gates
```yaml
gates:
minimum_score: 70
blocking_categories:
- security_critical
- test_failures
required_checks:
- linting_passes
- type_checks_pass
- tests_pass
- coverage_minimum
```
## Auto-Fix Capabilities
The reviewer can automatically fix:
- Missing type hints
- Formatting issues
- Simple code style violations
- Missing docstrings (basic)
## Integration
- Input: Completed features from `ac-task-executor`
- Uses: `ac-code-validator` for static analysis
- Reports to: `ac-state-tracker`
## API Reference
See `scripts/qa_reviewer.py` for full implementation.Related Skills
ascii-design-reviewer
Review Phase 1 ASCII UI designs from a product owner perspective. Analyze user journeys, identify potential issues, ask clarifying questions about requirements and user flows, create Mermaid diagrams (flowcharts, sequence diagrams, state charts), provide detailed system behavior documentation, and document error handling strategies. Use when reviewing ASCII mockups to validate design against actual user needs, understand system workflows, and ensure completeness before moving to implementation.
academic-reviewer
Expert guidance for reviewing academic manuscripts submitted to journals, particularly in political science, economics, and quantitative social sciences. Use when asked to review, critique, or provide feedback on academic papers, research designs, or empirical strategies. Emphasizes methodological rigor, causal identification strategies, and constructive feedback on research design.
quant-plan-reviewer
Use when reviewing implementation plans for quantitative trading systems before execution - catches data leakage, look-ahead bias, scalability risks, and production pitfalls
multi-model-reviewer
協調多個 AI 模型（ChatGPT、Gemini、Codex、QWEN、Claude）進行三角驗證，確保「Specification == Program == Test」一致性。過濾假警報後輸出報告，大幅減少人工介入時間。
ethics-reviewer
This skill should be used when the user mentions "dark patterns", "accessibility", "a11y", "privacy", "tracking", "analytics", "notifications", "user data", "GDPR", "consent", "manipulation", "sustainability", "performance budget", or when building user-facing features that collect data, send notifications, display urgency, or gate access. Addresses ethical constraints in software design — manipulation, accessibility, privacy, and sustainability.
codex-reviewer
Use OpenAI's Codex CLI as an independent code reviewer to provide second opinions on code implementations, architectural decisions, code specifications, and pull requests. Trigger when users request code review, second opinion, independent review, architecture validation, or mention Codex review. Provides unbiased analysis using GPT-5-Codex model through the codex exec command for non-interactive reviews.
code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
banking-domain-reviewer
Code review agent with banking domain knowledge — validates business flows, compliance requirements, double-entry accounting, payment processing, and regulatory patterns in the Firefly Banking Platform
architect-reviewer
Use this agent when you need to evaluate system design decisions, architectural patterns, and technology choices at the macro level.
aidf-reviewer
Code reviewer focused on quality, consistency, and maintainability. Provides constructive, actionable feedback with rationale.
agent-native-reviewer
Use this agent when reviewing code changes to ensure features are agent-native - any action a user can take, an agent can also take, and anything a user can see, an agent can see. Triggers on requests like "agent-native review", "AI accessibility check".
agent-code-reviewer
Expert code reviewer specializing in code quality, security vulnerabilities, and best practices across multiple languages. Masters static analysis, design patterns, and performance optimization with focus on maintainability and technical debt reduction.