[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M73A7YN0X8STVAMJMX1BENDB":3,"skill-same:01M73A7YN0X8STVAMJMX1BENDB":68},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":16,"sourceHtmlUrl":17,"categories":18,"keywords":19,"publishedAt":20,"linkOnly":21,"markdownContent":22,"markdownBody":23,"frontMatter":24,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M73A7YN0X8STVAMJMX1BENDB","code-quality",null,"two-stage review (spec compliance first, then code quality), refactoring, and quality improvement. Use when reviewing code, eliminating code smells, reducing technical debt, refactoring methods, running self-critique loops, or improving maintainability and readability.","bg-szy\u002FTOP-SKILLS","bg-szy","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F106576190?v=4","01M73A4E8KPV67SFXRY8XZGNBX","ShuZhiyong","01M73A4E96MQ294MHM74TZBVQD",6,"MIT","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fagent-skills\u002Fcode-quality\u002FLICENSE.txt","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fagent-skills\u002Fcode-quality\u002FSKILL.md",[],[],"2026-11-11 15:11:14",false,"---\nname: code-quality\nversion: \"2.0\"\nlast_updated: 2026-09-08\ntags: [code, quality, workflow, planning, delivery]\ndescription: \"two-stage review (spec compliance first, then code quality), refactoring, and quality improvement. Use when reviewing code, eliminating code smells, reducing technical debt, refactoring methods, running self-critique loops, or improving maintainability and readability.\"\n---\n# Code Quality Management\n\nComprehensive skill for improving code quality through two-stage review (spec compliance first, then code quality), surgical refactoring, and self-evaluation loops.\n\n- Leverage native parallel subagent dispatch and 200k+ context windows where available.\n\n\n\n## Activation Conditions\n\nUse symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.\n\n**two-stage review (spec compliance first, then code quality):**\n- Performing two-stage reviews (spec compliance first, then code quality), analyzing pull requests\n- Checking code quality, security auditing, performance reviews\n- Examining code for bugs, vulnerabilities, best practices violations\n- \"Review code\", \"check for issues\", \"audit code\", \"analyze PR\"\n\n**Refactoring:**\n- Code is hard to understand or maintain\n- Functions\u002Fclasses are too large, code smells need addressing\n- Adding features is difficult due to code structure\n- User asks \"clean up this code\", \"refactor this\", \"improve this\"\n\n**Self-Evaluation:**\n- Implementing self-critique and reflection loops for agent outputs\n- Building evaluator-optimizer pipelines for quality-critical generation\n- Creating test-driven code refinement workflows\n- Designing rubric-based or LLM-as-judge evaluation systems\n- Adding iterative improvement to agent outputs (code, reports, analysis)\n- Measuring and improving agent response quality\n\n## Part 1: two-stage review (spec compliance first, then code quality)\n\n### Review Priorities\n\nWhen performing a two-stage review (spec compliance first, then code quality), prioritize issues in this order:\n\n#### 🔴 CRITICAL (Block merge)\n- **Security**: Vulnerabilities, exposed secrets, authentication\u002Fauthorization issues\n- **Correctness**: Logic errors, data corruption risks, race conditions\n- **Breaking Changes**: API contract changes without versioning\n- **Data Loss**: Risk of data loss or corruption\n\n#### 🟡 IMPORTANT (Requires discussion)\n- **Code Quality**: Severe violations of SOLID principles, excessive duplication\n- **Test Coverage**: Missing tests for critical paths or new functionality\n- **Performance**: Obvious performance bottlenecks (N+1 queries, memory leaks)\n- **Architecture**: Significant deviations from established patterns\n\n#### 🟢 SUGGESTION (Non-blocking improvements)\n- **Readability**: Poor naming, complex logic that could be simplified\n- **Optimization**: Performance improvements without functional impact\n- **Best Practices**: Minor deviations from conventions\n- **Documentation**: Missing or incomplete comments\u002Fdocumentation\n\n### Review Principles\n\n1. **Be specific**: Reference exact lines, files, and provide concrete examples\n2. **Provide context**: Explain WHY something is an issue and potential impact\n3. **Suggest solutions**: Show corrected code when applicable, not just what's wrong\n4. **Be constructive**: Focus on improving code, not criticizing the author\n5. **Recognize good practices**: Acknowledge well-written code and smart solutions\n6. **Be pragmatic**: Not every suggestion needs immediate implementation\n7. **Group related comments**: Avoid multiple comments about the same topic\n\n## Part 2: Refactoring\n\n### The Golden Rules\n\n1. **Behavior is preserved** - Refactoring doesn't change what code does, only how\n2. **Small steps** - Make tiny changes, test after each\n3. **Version control is your friend** - Commit before and after each safe state\n4. **Tests are essential** - Without tests, you're not refactoring, you're editing\n5. **One thing at a time** - Don't mix refactoring with feature changes\n\n### When NOT to Refactor\n\n- Code that works and won't change again (if it ain't broke...)\n- Critical production code without tests (add tests first)\n- When you're under a tight deadline\n- \"Just because\" - need a clear purpose\n\n### Refactoring Techniques\n\n#### Extract Method\n```javascript\n\u002F\u002F Before\nfunction processOrder(order) {\n    if (order.status === 'pending') {\n        \u002F\u002F 20 lines of validation logic\n        \u002F\u002F 15 lines of calculation logic\n        \u002F\u002F 10 lines of notification logic\n    }\n}\n\n\u002F\u002F After\nfunction processOrder(order) {\n    if (order.status === 'pending') {\n        validateOrder(order);\n        calculateTotals(order);\n        sendNotification(order);\n    }\n}\n```\n\n#### Rename Variable\u002FFunction\nUse meaningful names that describe purpose:\n```javascript\n\u002F\u002F Before\nconst d = new Date();\nprocess(v, u);\n\n\u002F\u002F After\nconst currentDate = new Date();\nprocessValidation(validatedValue, userId);\n```\n\n#### Extract Class\n```javascript\n\u002F\u002F Before\nfunction calculateCartTotal(cart, user, shippingMethod, taxRate) {\n    \u002F\u002F Complex logic mixing user details, cart items, shipping, tax\n}\n\n\u002F\u002F After\nclass OrderCalculator {\n    constructor(cart, user) {\n        this.cart = cart;\n        this.user = user;\n    }\n\n    calculate(shippingMethod, taxRate) {\n        const subtotal = this.calculateSubtotal();\n        const shipping = this.calculateShipping(shippingMethod);\n        const tax = this.calculateTax(taxRate);\n        return subtotal + shipping + tax;\n    }\n}\n```\n\n### Common Code Smells and Fixes\n\n#### Long Method\n**Problem**: Methods longer than 30-50 lines\n**Fix**: Extract smaller, focused methods\n\n#### Duplicate Code\n**Problem**: Same logic in multiple places\n**Fix**: Extract to shared function\u002Fmethod\n\n#### Large Class\n**Problem**: Classes with too many responsibilities\n**Fix**: Extract smaller, focused classes\n\n#### Magic Numbers\n**Problem**: Unnamed numeric literals\n```javascript\n\u002F\u002F Before\nif (status > 3) { ... }\n\n\u002F\u002F After\nconst MAX_PENDING_DURATION_DAYS = 3;\nif (status > MAX_PENDING_DURATION_DAYS) { ... }\n```\n\n#### Feature Envy\n**Problem**: Method uses data from another class more than its own\n**Fix**: Move method to class it's envious of\n\n---\n\n## Part 3: Self-Evaluation Patterns\n\n### Pattern 1: Basic Reflection\n\nAgent evaluates and improves its own output through self-critique.\n\n```python\ndef reflect_and_refine(task: str, criteria: list[str], max_iterations: int = 3) -> str:\n    \"\"\"Generate with reflection loop.\"\"\"\n    output = llm(f\"Complete this task:\\n{task}\")\n\n    for i in range(max_iterations):\n        # Self-critique\n        critique = llm(f\"\"\"\n        Evaluate this output against criteria: {criteria}\n        Output: {output}\n        Rate each: PASS\u002FFAIL with feedback as JSON.\n        \"\"\")\n\n        critique_data = json.loads(critique)\n        all_pass = all(c[\"status\"] == \"PASS\" for c in critique_data.values())\n        if all_pass:\n            return output\n\n        # Refine based on critique\n        failed = {k: v[\"feedback\"] for k, v in critique_data.items() if v[\"status\"] == \"FAIL\"}\n        output = llm(f\"Improve to address: {failed}\\nOriginal: {output}\")\n\n    return output\n```\n\n**Key insight**: Use structured JSON output for reliable parsing of critique results.\n\n### Pattern 2: Evaluator-Optimizer\n\nSeparate generation and evaluation into distinct components for clearer responsibilities.\n\n```python\nclass EvaluatorOptimizer:\n    def __init__(self, score_threshold: float = 0.8):\n        self.score_threshold = score_threshold\n\n    def generate(self, task: str) -> str:\n        return llm(f\"Complete: {task}\")\n\n    def evaluate(self, output: str, task: str) -> dict:\n        return json.loads(llm(f\"\"\"\n        Evaluate output for task: {task}\n        Output: {output}\n        Return JSON: {{\"overall_score\": 0-1, \"dimensions\": {{\"accuracy\": ..., \"clarity\": ...}}}\n        \"\"\"))\n\n    def optimize(self, output: str, feedback: dict) -> str:\n        return llm(f\"Improve based on feedback: {feedback}\\nOutput: {output}\")\n\n    def run(self, task: str, max_iterations: int = 3) -> str:\n        output = self.generate(task)\n        for _ in range(max_iterations):\n            evaluation = self.evaluate(output, task)\n            if evaluation[\"overall_score\"] >= self.score_threshold:\n                break\n            output = self.optimize(output, evaluation)\n        return output\n```\n\n### Pattern 3: Code-Specific Reflection\n\nTest-driven refinement loop for code generation.\n\n```python\nclass CodeReflector:\n    def reflect_and_fix(self, spec: str, max_iterations: int = 3) -> str:\n        code = llm(f\"Write Python code for: {spec}\")\n        tests = llm(f\"Generate pytest tests for: {spec}\\nCode: {code}\")\n\n        for _ in range(max_iterations):\n            result = run_tests(code, tests)\n            if result[\"success\"]:\n                return code\n            code = llm(f\"Fix error: {result['error']}\\nCode: {code}\")\n        return code\n```\n\n### Evaluation Strategies\n\n#### Outcome-Based\nEvaluate whether output achieves expected result.\n\n```python\ndef evaluate_outcome(task: str, output: str, expected: str) -> str:\n    return llm(f\"Does output achieve expected outcome? Task: {task}, Expected: {expected}, Output: {output}\")\n```\n\n#### LLM-as-Judge\nUse LLM to compare and rank outputs.\n\n```python\ndef llm_judge(output_a: str, output_b: str, criteria: str) -> str:\n    return llm(f\"Compare outputs A and B for {criteria}. Which is better and why?\")\n```\n\n#### Rubric-Based\nScore outputs against weighted dimensions.\n\n```python\nRUBRIC = {\n    \"accuracy\": {\"weight\": 0.4},\n    \"clarity\": {\"weight\": 0.3},\n    \"completeness\": {\"weight\": 0.3}\n}\n\ndef evaluate_with_rubric(output: str, rubric: dict) -> float:\n    scores = json.loads(llm(f\"Rate 1-5 for each dimension: {list(rubric.keys())}\\nOutput: {output}\"))\n    return sum(scores[d] * rubric[d][\"weight\"] for d in rubric) \u002F 5\n```\n\n---\n\n\u003C!-- MCP:START -->\n\n\u003C!-- PORTABILITY:START -->\n## Cross-Client Portability\n\nThis skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.\n\n- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the\n  workflow in project instructions when folder discovery is unavailable.\n- Claude Code: keep the folder in a local skills directory or a compatible plugin source.\n- Codex: install or sync the folder into\n  `$CODEX_HOME\u002Fskills\u002Fcode-quality` and restart Codex after major changes.\n\n\u003C!-- PORTABILITY:END -->\n\n## MCP Availability And Fallback\n\nPreferred MCP Server: None required\n\n- Fallback prompt: \"Use the Code Quality Management skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding.\"\n- Do not claim an MCP operation was used when the active host does not expose it.\n- Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.\n\n\u003C!-- MCP:END -->\n\n## Anti-Patterns\n\n- Starting work before the plan or gate is clear: Execution drifts when success criteria are implied instead of explicit.\n- Treating verification as optional cleanup: The last mile is where regressions and missing updates are usually hiding.\n- Mixing planning, implementation, and release work in one jump: You lose the causal chain that explains why a change is safe.\n\n## Verification Protocol\n\nBefore claiming \"skill applied successfully\":\n\n1. Pass\u002Ffail: The Code Quality workflow starts from explicit success criteria, constraints, and stop conditions.\n2. Pass\u002Ffail: Required evidence is collected before any completion, approval, or readiness claim.\n3. Pass\u002Ffail: The next action follows the documented gate order without skipping review or verification steps.\n4. Pressure-test scenario: Apply the workflow under time pressure with one failing check and one tempting shortcut.\n5. Success metric: Zero rationalizations; blocked, failed, or unverified work is reported as such.\n\n## Multi-Language Review Examples\n\n### Python\n```python\n# Before\ndef approve(order, notifier):\n    if order.total > 1000:\n        notifier.send(order.customer_email, order.total)\n    return order.total\n\n# After\ndef calculate_total(order: Order) -> int:\n    return order.total\n\ndef notify_high_value_order(order: Order, notifier: Notifier) -> None:\n    if order.total > HIGH_VALUE_THRESHOLD:\n        notifier.send(order.customer_email, order.total)\n```\n\n### C#\n```csharp\n\u002F\u002F Before\npublic decimal Process(Order order)\n{\n    if (order.Total > 1000) _email.Send(order.CustomerEmail, order.Total);\n    return order.Total;\n}\n\n\u002F\u002F After\npublic decimal CalculateTotal(Order order) => order.Total;\n\npublic void NotifyHighValueCustomer(Order order)\n{\n    if (order.Total > HighValueThreshold)\n    {\n        _email.Send(order.CustomerEmail, order.Total);\n    }\n}\n```\n\n### Java\n```java\n\u002F\u002F Before\nBigDecimal process(Order order) {\n    if (order.total().compareTo(THRESHOLD) > 0) {\n        email.send(order.customerEmail(), order.total());\n    }\n    return order.total();\n}\n\n\u002F\u002F After\nBigDecimal calculateTotal(Order order) {\n    return order.total();\n}\n\nvoid notifyHighValueCustomer(Order order) {\n    if (order.total().compareTo(THRESHOLD) > 0) {\n        email.send(order.customerEmail(), order.total());\n    }\n}\n```\n\n### Go\n```go\n\u002F\u002F Before\nfunc Process(order Order, notifier Notifier) int {\n    if order.Total > highValueThreshold {\n        notifier.Send(order.CustomerEmail, order.Total)\n    }\n    return order.Total\n}\n\n\u002F\u002F After\nfunc CalculateTotal(order Order) int {\n    return order.Total\n}\n\nfunc NotifyHighValueCustomer(order Order, notifier Notifier) {\n    if order.Total > highValueThreshold {\n        notifier.Send(order.CustomerEmail, order.Total)\n    }\n}\n```\n\n## AI-Generated Code Specific Checks\n\n- Hallucinated APIs or options: Verify every imported type, method, CLI flag, and config field against the real dependency version before trusting the sample.\n- Inconsistent style drift: AI often mixes naming, file structure, or error-handling styles from different codebases, so compare the output against local conventions before merging.\n- Over-engineering for a simple requirement: Generated code commonly adds abstractions, wrappers, or extension points that the current task does not need.\n- Hidden edge-case gaps: AI can produce convincing happy-path logic while skipping null handling, retries, authorization checks, or cleanup paths.\n\n## Automated Tooling Integration\n\n### ESLint and Prettier\n```json\n{\n  \"scripts\": {\n    \"lint\": \"eslint . --ext .js,.jsx,.ts,.tsx --max-warnings=0\",\n    \"format\": \"prettier --write .\",\n    \"format:check\": \"prettier --check .\"\n  }\n}\n```\n\n### SonarQube Scan\n```yaml\n- name: SonarQube scan\n  run: |\n    sonar-scanner \\\n      -Dsonar.projectKey=my-app \\\n      -Dsonar.sources=src \\\n      -Dsonar.tests=tests \\\n      -Dsonar.javascript.lcov.reportPaths=coverage\u002Flcov.info\n```\n\n### CI Quality Gates\n\nUse CI quality gates to enforce linting, formatting, test coverage, and static-analysis thresholds before review or merge.\n\n```yaml\njobs:\n  quality:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v4\n      - uses: actions\u002Fsetup-node@v4\n        with:\n          node-version: 22\n      - run: npm ci\n      - run: npm run lint\n      - run: npm run format:check\n      - run: npm test -- --coverage\n      - run: sonar-scanner\n```\n\nUse the gate to fail fast on lint errors, formatting drift, coverage regressions, and maintainability warnings before review starts.\n\n## Best Practices\n\n### For two-stage reviews (spec compliance first, then code quality)\n- Focus on code behavior, not personal style preferences\n- Provide actionable feedback with examples\n- Balance critique with recognition of good work\n- Consider project context and constraints\n\n### For Refactoring\n- Always have tests before refactoring\n- Commit frequently to maintain safety\n- Keep changes small and verifiable\n- Document non-obvious refactoring decisions\n\n### For Self-Evaluation\n- Define clear, measurable evaluation criteria upfront\n- Set iteration limits (3-5) to prevent infinite loops\n- Add convergence detection if scores aren't improving\n- Log full iteration trajectory for debugging and analysis\n- Use structured output (JSON) for reliable parsing\n\n---\n\n## Quality Improvement Checklist\n\n### two-stage review (spec compliance first, then code quality) Checklist\n```markdown\n## two-stage review (spec compliance first, then code quality) Assessment\n\n### Functionality\n- [ ] Logic is correct and achieves intended purpose\n- [ ] Edge cases are handled appropriately\n- [ ] Error handling is comprehensive\n- [ ] No obvious bugs or race conditions\n\n### Code Quality\n- [ ] Code is readable and maintainable\n- [ ] Naming is descriptive and consistent\n- [ ] Functions\u002Fclasses have single responsibility\n- [ ] No unnecessary complexity or obfuscation\n\n### Architecture\n- [ ] Follows established project patterns\n- [ ] Appropriate use of design patterns\n- [ ] Proper separation of concerns\n- [ ] No tight coupling or hidden dependencies\n```\n\n### Refactoring Checklist\n```markdown\n## Refactoring Safety Checklist\n\n### Pre-Refactoring\n- [ ] Tests exist and pass\n- [ ] Version control branch is clean\n- [ ] Understand current behavior thoroughly\n\n### During Refactoring\n- [ ] Making small, incremental changes\n- [ ] Running tests after each change\n- [ ] Committing each working intermediate state\n- [ ] Preserving external behavior\n\n### Post-Refactoring\n- [ ] All tests still pass\n- [ ] Code is simpler and clearer\n- [ ] No new bugs introduced\n- [ ] Documentation updated if needed\n```\n\n### Self-Evaluation Checklist\n```markdown\n## Evaluation Implementation Checklist\n\n### Setup\n- [ ] Define evaluation criteria\u002Frubric\n- [ ] Set score threshold for \"good enough\"\n- [ ] Configure max iterations (default: 3)\n\n### Implementation\n- [ ] Implement generate() function\n- [ ] Implement evaluate() function with structured output\n- [ ] Implement optimize() function\n- [ ] Wire up to refinement loop\n\n### Safety\n- [ ] Add convergence detection\n- [ ] Log all iterations for debugging\n- [ ] Handle evaluation parse failures gracefully\n\n---\n\n## References & Resources\n\n### Documentation\n- [Refactoring Catalog](.\u002Freferences\u002Frefactoring-catalog.md) — 12 refactoring techniques with before\u002Fafter code examples and pitfalls\n- [Code Smells](.\u002Freferences\u002Fcode-smells.md) — 17 code smells organized by category with detection signals and remedies\n\n### Scripts\n- [Review Checklist](.\u002Fscripts\u002Freview-checklist.py) — Python script for automated static analysis of JS\u002FTS files\n\n### Examples\n- [Refactoring Walkthrough](.\u002Fexamples\u002Frefactoring-walkthrough.md) — Step-by-step React component refactoring from 160 lines to clean architecture\n\n---\n\n## Related Skills\n\n- [development-workflow](..\u002Fdevelopment-workflow\u002FSKILL.md): Use it when the workflow also needs planning, quality gates, and delivery tracking.\n- [systematic-debugging](..\u002Fsystematic-debugging\u002FSKILL.md): Use it when the workflow also needs root-cause debugging before proposing fixes.\n- [test-driven-development](..\u002Ftest-driven-development\u002FSKILL.md): Use it when the workflow also needs test-first implementation and regression safety.\n- [verification-before-completion](..\u002Fverification-before-completion\u002FSKILL.md): Use it when the workflow also needs final evidence checks before claiming completion.\n","# Code Quality Management\n\nComprehensive skill for improving code quality through two-stage review (spec compliance first, then code quality), surgical refactoring, and self-evaluation loops.\n\n- Leverage native parallel subagent dispatch and 200k+ context windows where available.\n\n\n\n## Activation Conditions\n\nUse symptom -> action triggers: when one matches, apply this skill and verify with the protocol below.\n\n**two-stage review (spec compliance first, then code quality):**\n- Performing two-stage reviews (spec compliance first, then code quality), analyzing pull requests\n- Checking code quality, security auditing, performance reviews\n- Examining code for bugs, vulnerabilities, best practices violations\n- \"Review code\", \"check for issues\", \"audit code\", \"analyze PR\"\n\n**Refactoring:**\n- Code is hard to understand or maintain\n- Functions\u002Fclasses are too large, code smells need addressing\n- Adding features is difficult due to code structure\n- User asks \"clean up this code\", \"refactor this\", \"improve this\"\n\n**Self-Evaluation:**\n- Implementing self-critique and reflection loops for agent outputs\n- Building evaluator-optimizer pipelines for quality-critical generation\n- Creating test-driven code refinement workflows\n- Designing rubric-based or LLM-as-judge evaluation systems\n- Adding iterative improvement to agent outputs (code, reports, analysis)\n- Measuring and improving agent response quality\n\n## Part 1: two-stage review (spec compliance first, then code quality)\n\n### Review Priorities\n\nWhen performing a two-stage review (spec compliance first, then code quality), prioritize issues in this order:\n\n#### 🔴 CRITICAL (Block merge)\n- **Security**: Vulnerabilities, exposed secrets, authentication\u002Fauthorization issues\n- **Correctness**: Logic errors, data corruption risks, race conditions\n- **Breaking Changes**: API contract changes without versioning\n- **Data Loss**: Risk of data loss or corruption\n\n#### 🟡 IMPORTANT (Requires discussion)\n- **Code Quality**: Severe violations of SOLID principles, excessive duplication\n- **Test Coverage**: Missing tests for critical paths or new functionality\n- **Performance**: Obvious performance bottlenecks (N+1 queries, memory leaks)\n- **Architecture**: Significant deviations from established patterns\n\n#### 🟢 SUGGESTION (Non-blocking improvements)\n- **Readability**: Poor naming, complex logic that could be simplified\n- **Optimization**: Performance improvements without functional impact\n- **Best Practices**: Minor deviations from conventions\n- **Documentation**: Missing or incomplete comments\u002Fdocumentation\n\n### Review Principles\n\n1. **Be specific**: Reference exact lines, files, and provide concrete examples\n2. **Provide context**: Explain WHY something is an issue and potential impact\n3. **Suggest solutions**: Show corrected code when applicable, not just what's wrong\n4. **Be constructive**: Focus on improving code, not criticizing the author\n5. **Recognize good practices**: Acknowledge well-written code and smart solutions\n6. **Be pragmatic**: Not every suggestion needs immediate implementation\n7. **Group related comments**: Avoid multiple comments about the same topic\n\n## Part 2: Refactoring\n\n### The Golden Rules\n\n1. **Behavior is preserved** - Refactoring doesn't change what code does, only how\n2. **Small steps** - Make tiny changes, test after each\n3. **Version control is your friend** - Commit before and after each safe state\n4. **Tests are essential** - Without tests, you're not refactoring, you're editing\n5. **One thing at a time** - Don't mix refactoring with feature changes\n\n### When NOT to Refactor\n\n- Code that works and won't change again (if it ain't broke...)\n- Critical production code without tests (add tests first)\n- When you're under a tight deadline\n- \"Just because\" - need a clear purpose\n\n### Refactoring Techniques\n\n#### Extract Method\n```javascript\n\u002F\u002F Before\nfunction processOrder(order) {\n    if (order.status === 'pending') {\n        \u002F\u002F 20 lines of validation logic\n        \u002F\u002F 15 lines of calculation logic\n        \u002F\u002F 10 lines of notification logic\n    }\n}\n\n\u002F\u002F After\nfunction processOrder(order) {\n    if (order.status === 'pending') {\n        validateOrder(order);\n        calculateTotals(order);\n        sendNotification(order);\n    }\n}\n```\n\n#### Rename Variable\u002FFunction\nUse meaningful names that describe purpose:\n```javascript\n\u002F\u002F Before\nconst d = new Date();\nprocess(v, u);\n\n\u002F\u002F After\nconst currentDate = new Date();\nprocessValidation(validatedValue, userId);\n```\n\n#### Extract Class\n```javascript\n\u002F\u002F Before\nfunction calculateCartTotal(cart, user, shippingMethod, taxRate) {\n    \u002F\u002F Complex logic mixing user details, cart items, shipping, tax\n}\n\n\u002F\u002F After\nclass OrderCalculator {\n    constructor(cart, user) {\n        this.cart = cart;\n        this.user = user;\n    }\n\n    calculate(shippingMethod, taxRate) {\n        const subtotal = this.calculateSubtotal();\n        const shipping = this.calculateShipping(shippingMethod);\n        const tax = this.calculateTax(taxRate);\n        return subtotal + shipping + tax;\n    }\n}\n```\n\n### Common Code Smells and Fixes\n\n#### Long Method\n**Problem**: Methods longer than 30-50 lines\n**Fix**: Extract smaller, focused methods\n\n#### Duplicate Code\n**Problem**: Same logic in multiple places\n**Fix**: Extract to shared function\u002Fmethod\n\n#### Large Class\n**Problem**: Classes with too many responsibilities\n**Fix**: Extract smaller, focused classes\n\n#### Magic Numbers\n**Problem**: Unnamed numeric literals\n```javascript\n\u002F\u002F Before\nif (status > 3) { ... }\n\n\u002F\u002F After\nconst MAX_PENDING_DURATION_DAYS = 3;\nif (status > MAX_PENDING_DURATION_DAYS) { ... }\n```\n\n#### Feature Envy\n**Problem**: Method uses data from another class more than its own\n**Fix**: Move method to class it's envious of\n\n---\n\n## Part 3: Self-Evaluation Patterns\n\n### Pattern 1: Basic Reflection\n\nAgent evaluates and improves its own output through self-critique.\n\n```python\ndef reflect_and_refine(task: str, criteria: list[str], max_iterations: int = 3) -> str:\n    \"\"\"Generate with reflection loop.\"\"\"\n    output = llm(f\"Complete this task:\\n{task}\")\n\n    for i in range(max_iterations):\n        # Self-critique\n        critique = llm(f\"\"\"\n        Evaluate this output against criteria: {criteria}\n        Output: {output}\n        Rate each: PASS\u002FFAIL with feedback as JSON.\n        \"\"\")\n\n        critique_data = json.loads(critique)\n        all_pass = all(c[\"status\"] == \"PASS\" for c in critique_data.values())\n        if all_pass:\n            return output\n\n        # Refine based on critique\n        failed = {k: v[\"feedback\"] for k, v in critique_data.items() if v[\"status\"] == \"FAIL\"}\n        output = llm(f\"Improve to address: {failed}\\nOriginal: {output}\")\n\n    return output\n```\n\n**Key insight**: Use structured JSON output for reliable parsing of critique results.\n\n### Pattern 2: Evaluator-Optimizer\n\nSeparate generation and evaluation into distinct components for clearer responsibilities.\n\n```python\nclass EvaluatorOptimizer:\n    def __init__(self, score_threshold: float = 0.8):\n        self.score_threshold = score_threshold\n\n    def generate(self, task: str) -> str:\n        return llm(f\"Complete: {task}\")\n\n    def evaluate(self, output: str, task: str) -> dict:\n        return json.loads(llm(f\"\"\"\n        Evaluate output for task: {task}\n        Output: {output}\n        Return JSON: {{\"overall_score\": 0-1, \"dimensions\": {{\"accuracy\": ..., \"clarity\": ...}}}\n        \"\"\"))\n\n    def optimize(self, output: str, feedback: dict) -> str:\n        return llm(f\"Improve based on feedback: {feedback}\\nOutput: {output}\")\n\n    def run(self, task: str, max_iterations: int = 3) -> str:\n        output = self.generate(task)\n        for _ in range(max_iterations):\n            evaluation = self.evaluate(output, task)\n            if evaluation[\"overall_score\"] >= self.score_threshold:\n                break\n            output = self.optimize(output, evaluation)\n        return output\n```\n\n### Pattern 3: Code-Specific Reflection\n\nTest-driven refinement loop for code generation.\n\n```python\nclass CodeReflector:\n    def reflect_and_fix(self, spec: str, max_iterations: int = 3) -> str:\n        code = llm(f\"Write Python code for: {spec}\")\n        tests = llm(f\"Generate pytest tests for: {spec}\\nCode: {code}\")\n\n        for _ in range(max_iterations):\n            result = run_tests(code, tests)\n            if result[\"success\"]:\n                return code\n            code = llm(f\"Fix error: {result['error']}\\nCode: {code}\")\n        return code\n```\n\n### Evaluation Strategies\n\n#### Outcome-Based\nEvaluate whether output achieves expected result.\n\n```python\ndef evaluate_outcome(task: str, output: str, expected: str) -> str:\n    return llm(f\"Does output achieve expected outcome? Task: {task}, Expected: {expected}, Output: {output}\")\n```\n\n#### LLM-as-Judge\nUse LLM to compare and rank outputs.\n\n```python\ndef llm_judge(output_a: str, output_b: str, criteria: str) -> str:\n    return llm(f\"Compare outputs A and B for {criteria}. Which is better and why?\")\n```\n\n#### Rubric-Based\nScore outputs against weighted dimensions.\n\n```python\nRUBRIC = {\n    \"accuracy\": {\"weight\": 0.4},\n    \"clarity\": {\"weight\": 0.3},\n    \"completeness\": {\"weight\": 0.3}\n}\n\ndef evaluate_with_rubric(output: str, rubric: dict) -> float:\n    scores = json.loads(llm(f\"Rate 1-5 for each dimension: {list(rubric.keys())}\\nOutput: {output}\"))\n    return sum(scores[d] * rubric[d][\"weight\"] for d in rubric) \u002F 5\n```\n\n---\n\n\u003C!-- MCP:START -->\n\n\u003C!-- PORTABILITY:START -->\n## Cross-Client Portability\n\nThis skill is written to stay usable across GitHub Copilot, Claude Code, and Codex.\n\n- GitHub Copilot: keep the folder in a Copilot-visible skill path or wrap the\n  workflow in project instructions when folder discovery is unavailable.\n- Claude Code: keep the folder in a local skills directory or a compatible plugin source.\n- Codex: install or sync the folder into\n  `$CODEX_HOME\u002Fskills\u002Fcode-quality` and restart Codex after major changes.\n\n\u003C!-- PORTABILITY:END -->\n\n## MCP Availability And Fallback\n\nPreferred MCP Server: None required\n\n- Fallback prompt: \"Use the Code Quality Management skill without MCP. Rely on its local instructions, bundled resources, standard shell or editor tools, and direct verification. Show the evidence used before concluding.\"\n- Do not claim an MCP operation was used when the active host does not expose it.\n- Treat local files, tests, rendered outputs, logs, or screenshots as the fallback evidence path.\n\n\u003C!-- MCP:END -->\n\n## Anti-Patterns\n\n- Starting work before the plan or gate is clear: Execution drifts when success criteria are implied instead of explicit.\n- Treating verification as optional cleanup: The last mile is where regressions and missing updates are usually hiding.\n- Mixing planning, implementation, and release work in one jump: You lose the causal chain that explains why a change is safe.\n\n## Verification Protocol\n\nBefore claiming \"skill applied successfully\":\n\n1. Pass\u002Ffail: The Code Quality workflow starts from explicit success criteria, constraints, and stop conditions.\n2. Pass\u002Ffail: Required evidence is collected before any completion, approval, or readiness claim.\n3. Pass\u002Ffail: The next action follows the documented gate order without skipping review or verification steps.\n4. Pressure-test scenario: Apply the workflow under time pressure with one failing check and one tempting shortcut.\n5. Success metric: Zero rationalizations; blocked, failed, or unverified work is reported as such.\n\n## Multi-Language Review Examples\n\n### Python\n```python\n# Before\ndef approve(order, notifier):\n    if order.total > 1000:\n        notifier.send(order.customer_email, order.total)\n    return order.total\n\n# After\ndef calculate_total(order: Order) -> int:\n    return order.total\n\ndef notify_high_value_order(order: Order, notifier: Notifier) -> None:\n    if order.total > HIGH_VALUE_THRESHOLD:\n        notifier.send(order.customer_email, order.total)\n```\n\n### C#\n```csharp\n\u002F\u002F Before\npublic decimal Process(Order order)\n{\n    if (order.Total > 1000) _email.Send(order.CustomerEmail, order.Total);\n    return order.Total;\n}\n\n\u002F\u002F After\npublic decimal CalculateTotal(Order order) => order.Total;\n\npublic void NotifyHighValueCustomer(Order order)\n{\n    if (order.Total > HighValueThreshold)\n    {\n        _email.Send(order.CustomerEmail, order.Total);\n    }\n}\n```\n\n### Java\n```java\n\u002F\u002F Before\nBigDecimal process(Order order) {\n    if (order.total().compareTo(THRESHOLD) > 0) {\n        email.send(order.customerEmail(), order.total());\n    }\n    return order.total();\n}\n\n\u002F\u002F After\nBigDecimal calculateTotal(Order order) {\n    return order.total();\n}\n\nvoid notifyHighValueCustomer(Order order) {\n    if (order.total().compareTo(THRESHOLD) > 0) {\n        email.send(order.customerEmail(), order.total());\n    }\n}\n```\n\n### Go\n```go\n\u002F\u002F Before\nfunc Process(order Order, notifier Notifier) int {\n    if order.Total > highValueThreshold {\n        notifier.Send(order.CustomerEmail, order.Total)\n    }\n    return order.Total\n}\n\n\u002F\u002F After\nfunc CalculateTotal(order Order) int {\n    return order.Total\n}\n\nfunc NotifyHighValueCustomer(order Order, notifier Notifier) {\n    if order.Total > highValueThreshold {\n        notifier.Send(order.CustomerEmail, order.Total)\n    }\n}\n```\n\n## AI-Generated Code Specific Checks\n\n- Hallucinated APIs or options: Verify every imported type, method, CLI flag, and config field against the real dependency version before trusting the sample.\n- Inconsistent style drift: AI often mixes naming, file structure, or error-handling styles from different codebases, so compare the output against local conventions before merging.\n- Over-engineering for a simple requirement: Generated code commonly adds abstractions, wrappers, or extension points that the current task does not need.\n- Hidden edge-case gaps: AI can produce convincing happy-path logic while skipping null handling, retries, authorization checks, or cleanup paths.\n\n## Automated Tooling Integration\n\n### ESLint and Prettier\n```json\n{\n  \"scripts\": {\n    \"lint\": \"eslint . --ext .js,.jsx,.ts,.tsx --max-warnings=0\",\n    \"format\": \"prettier --write .\",\n    \"format:check\": \"prettier --check .\"\n  }\n}\n```\n\n### SonarQube Scan\n```yaml\n- name: SonarQube scan\n  run: |\n    sonar-scanner \\\n      -Dsonar.projectKey=my-app \\\n      -Dsonar.sources=src \\\n      -Dsonar.tests=tests \\\n      -Dsonar.javascript.lcov.reportPaths=coverage\u002Flcov.info\n```\n\n### CI Quality Gates\n\nUse CI quality gates to enforce linting, formatting, test coverage, and static-analysis thresholds before review or merge.\n\n```yaml\njobs:\n  quality:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v4\n      - uses: actions\u002Fsetup-node@v4\n        with:\n          node-version: 22\n      - run: npm ci\n      - run: npm run lint\n      - run: npm run format:check\n      - run: npm test -- --coverage\n      - run: sonar-scanner\n```\n\nUse the gate to fail fast on lint errors, formatting drift, coverage regressions, and maintainability warnings before review starts.\n\n## Best Practices\n\n### For two-stage reviews (spec compliance first, then code quality)\n- Focus on code behavior, not personal style preferences\n- Provide actionable feedback with examples\n- Balance critique with recognition of good work\n- Consider project context and constraints\n\n### For Refactoring\n- Always have tests before refactoring\n- Commit frequently to maintain safety\n- Keep changes small and verifiable\n- Document non-obvious refactoring decisions\n\n### For Self-Evaluation\n- Define clear, measurable evaluation criteria upfront\n- Set iteration limits (3-5) to prevent infinite loops\n- Add convergence detection if scores aren't improving\n- Log full iteration trajectory for debugging and analysis\n- Use structured output (JSON) for reliable parsing\n\n---\n\n## Quality Improvement Checklist\n\n### two-stage review (spec compliance first, then code quality) Checklist\n```markdown\n## two-stage review (spec compliance first, then code quality) Assessment\n\n### Functionality\n- [ ] Logic is correct and achieves intended purpose\n- [ ] Edge cases are handled appropriately\n- [ ] Error handling is comprehensive\n- [ ] No obvious bugs or race conditions\n\n### Code Quality\n- [ ] Code is readable and maintainable\n- [ ] Naming is descriptive and consistent\n- [ ] Functions\u002Fclasses have single responsibility\n- [ ] No unnecessary complexity or obfuscation\n\n### Architecture\n- [ ] Follows established project patterns\n- [ ] Appropriate use of design patterns\n- [ ] Proper separation of concerns\n- [ ] No tight coupling or hidden dependencies\n```\n\n### Refactoring Checklist\n```markdown\n## Refactoring Safety Checklist\n\n### Pre-Refactoring\n- [ ] Tests exist and pass\n- [ ] Version control branch is clean\n- [ ] Understand current behavior thoroughly\n\n### During Refactoring\n- [ ] Making small, incremental changes\n- [ ] Running tests after each change\n- [ ] Committing each working intermediate state\n- [ ] Preserving external behavior\n\n### Post-Refactoring\n- [ ] All tests still pass\n- [ ] Code is simpler and clearer\n- [ ] No new bugs introduced\n- [ ] Documentation updated if needed\n```\n\n### Self-Evaluation Checklist\n```markdown\n## Evaluation Implementation Checklist\n\n### Setup\n- [ ] Define evaluation criteria\u002Frubric\n- [ ] Set score threshold for \"good enough\"\n- [ ] Configure max iterations (default: 3)\n\n### Implementation\n- [ ] Implement generate() function\n- [ ] Implement evaluate() function with structured output\n- [ ] Implement optimize() function\n- [ ] Wire up to refinement loop\n\n### Safety\n- [ ] Add convergence detection\n- [ ] Log all iterations for debugging\n- [ ] Handle evaluation parse failures gracefully\n\n---\n\n## References & Resources\n\n### Documentation\n- [Refactoring Catalog](.\u002Freferences\u002Frefactoring-catalog.md) — 12 refactoring techniques with before\u002Fafter code examples and pitfalls\n- [Code Smells](.\u002Freferences\u002Fcode-smells.md) — 17 code smells organized by category with detection signals and remedies\n\n### Scripts\n- [Review Checklist](.\u002Fscripts\u002Freview-checklist.py) — Python script for automated static analysis of JS\u002FTS files\n\n### Examples\n- [Refactoring Walkthrough](.\u002Fexamples\u002Frefactoring-walkthrough.md) — Step-by-step React component refactoring from 160 lines to clean architecture\n\n---\n\n## Related Skills\n\n- [development-workflow](..\u002Fdevelopment-workflow\u002FSKILL.md): Use it when the workflow also needs planning, quality gates, and delivery tracking.\n- [systematic-debugging](..\u002Fsystematic-debugging\u002FSKILL.md): Use it when the workflow also needs root-cause debugging before proposing fixes.\n- [test-driven-development](..\u002Ftest-driven-development\u002FSKILL.md): Use it when the workflow also needs test-first implementation and regression safety.\n- [verification-before-completion](..\u002Fverification-before-completion\u002FSKILL.md): Use it when the workflow also needs final evidence checks before claiming completion.\n",{"name":5,"tags":25,"version":31,"description":7,"last_updated":32},[26,27,28,29,30],"code","quality","workflow","planning","delivery","2.0",1788825600000,"master","fd76f882a04e445e899d5cfb2732f2105ea054ee","skills\u002Fagent-skills\u002Fcode-quality",0,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS","https:\u002F\u002Fbg-szy.github.io\u002FTOP-SKILLS\u002F","https:\u002F\u002Fgithub.com\u002Fbg-szy","https:\u002F\u002Fwww.ecust.edu.cn\u002F","a student of East China University of Science and Technology","2026-11-15 03:38:02",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add bg-szy\u002FTOP-SKILLS --skill code-quality",{"tool":49,"command":50},"bunx","bunx skills add bg-szy\u002FTOP-SKILLS --skill code-quality",{"tool":52,"command":53},"pnpm","pnpm dlx skills add bg-szy\u002FTOP-SKILLS --skill code-quality","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fagent-skills\u002Fcode-quality\u002FSKILL.md",true,[57,63],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"CHANGELOG.md","REFERENCE","参考文档",6674,"https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fagent-skills\u002Fcode-quality\u002FCHANGELOG.md",{"path":64,"resourceType":65,"resourceTypeDesc":66,"sizeBytes":67,"sourceHtmlUrl":16},"LICENSE.txt","LICENSE","许可证",1069,[69,77,84,91,98,105],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":76},"01M7DXW9N826PKXK174PVW3038","serpmaven","Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fserpmaven\u002FSKILL.md",[],[],"2026-11-15 14:19:17",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":76},"01M7DXVHSTWDV65475QEQ915M7","revnu-landing-page-audit","Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: \"audit my landing page\", \"why isn't this page converting\", \"review my homepage\", \"my ads get clicks but no signups\", \"people bounce from the pricing page\", \"CRO review\", \"improve conversion rate\", \"is my hero section clear\", \"roast my landing page\", \"rewrite my headline\", \"what's wrong with this page\", \"landing page feedback\", \"make the signup page convert better\". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-landing-page-audit\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":76},"01M7DXV8X2D7B3VTD4HHYYHTGR","revnu-growth-context","Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents\u002Frevnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says \"set up our marketing context\", \"who is our ideal customer\", \"write our ICP\", \"describe the product for marketing\", \"positioning doc\", \"what's our brand voice\", \"remember this about our customers\", \"log what we tried\", \"what have we learned from marketing\", \"we changed pricing, update the context\", \"update our growth notes\", \"summarize the business for the agent\", \"import my product-marketing.md\", \"start a growth doc\", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-growth-context\u002FSKILL.md",[],[],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":97,"publishedAt":76},"01M7DXV0DGJ1G0A60PAHC6J3C5","revnu-get-listed","Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: \"best X\" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says \"get us listed\", \"which directories should we submit to\", \"how do we get into best-of lists\", \"why does ChatGPT recommend competitors and not us\", \"get mentioned in AI answers\", \"submit to awesome lists\", \"get on G2\", \"where are our competitors listed\", \"pitch listicle authors\", \"find backlink opportunities\", \"launch directories\", \"get into roundups\", \"Product Hunt alternatives\", \"where should we be listed\", \"get cited by Perplexity\". Never submits, pays or posts without a yes. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-get-listed\u002FSKILL.md",[],[],{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":76},"01M7DXTSPMGT9D6DSS0HP9BSTA","revnu-ai-readiness-audit","Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks \"is my site ready for AI search\", \"audit my site for AI answers\", \"AEO audit\", \"GEO audit\", \"why doesn't ChatGPT quote our pricing\", \"make our pages citable by AI\", \"do I need llms.txt\", \"does schema help with ChatGPT\", \"check our structured data\", \"is our content visible without JavaScript\", \"AI SEO audit\", \"optimize our homepage for AI answers\", \"LLM SEO check\", \"why does AI get our product wrong\", \"fix our site for AI Overviews\". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Frevnu-ai-readiness-audit\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":109,"categories":110,"keywords":111,"publishedAt":76},"01M7DXSZHCVTRS620GC3S97JZV","proxy-troubleshooting","Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.","https:\u002F\u002Fgithub.com\u002Fbg-szy\u002FTOP-SKILLS\u002Fblob\u002Fmaster\u002Fskills\u002Fmarketplace\u002Fproxy-troubleshooting\u002FSKILL.md",[],[]]