[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BPCRT20R5QC0NFSQJQV615":3,"skill-same:01M7BPCRT20R5QC0NFSQJQV615":56},{"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":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":33,"commitSha":34,"skillDirectory":35,"forksCount":36,"repositoryHtmlUrl":37,"repositoryHomepageUrl":38,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":55},"01M7BPCRT20R5QC0NFSQJQV615","Verification & Quality Assurance",null,"Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fmcp\u002F.claude\u002Fskills\u002Fverification-quality\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"Verification & Quality Assurance\"\ndescription: \"Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability.\"\nversion: \"2.0.0\"\ncategory: \"quality-assurance\"\ntags: [\"verification\", \"truth-scoring\", \"quality\", \"rollback\", \"metrics\", \"ci-cd\"]\n---\n\n# Verification & Quality Assurance Skill\n\n## What This Skill Does\n\nThis skill provides a comprehensive verification and quality assurance system that ensures code quality and correctness through:\n\n- **Truth Scoring**: Real-time reliability metrics (0.0-1.0 scale) for code, agents, and tasks\n- **Verification Checks**: Automated code correctness, security, and best practices validation\n- **Automatic Rollback**: Instant reversion of changes that fail verification (default threshold: 0.95)\n- **Quality Metrics**: Statistical analysis with trends, confidence intervals, and improvement tracking\n- **CI\u002FCD Integration**: Export capabilities for continuous integration pipelines\n- **Real-time Monitoring**: Live dashboards and watch modes for ongoing verification\n\n## Prerequisites\n\n- Claude Flow installed (`npx claude-flow@alpha`)\n- Git repository (for rollback features)\n- Node.js 18+ (for dashboard features)\n\n## Quick Start\n\n```bash\n# View current truth scores\nnpx claude-flow@alpha truth\n\n# Run verification check\nnpx claude-flow@alpha verify check\n\n# Verify specific file with custom threshold\nnpx claude-flow@alpha verify check --file src\u002Fapp.js --threshold 0.98\n\n# Rollback last failed verification\nnpx claude-flow@alpha verify rollback --last-good\n```\n\n---\n\n## Complete Guide\n\n### Truth Scoring System\n\n#### View Truth Metrics\n\nDisplay comprehensive quality and reliability metrics for your codebase and agent tasks.\n\n**Basic Usage:**\n```bash\n# View current truth scores (default: table format)\nnpx claude-flow@alpha truth\n\n# View scores for specific time period\nnpx claude-flow@alpha truth --period 7d\n\n# View scores for specific agent\nnpx claude-flow@alpha truth --agent coder --period 24h\n\n# Find files\u002Ftasks below threshold\nnpx claude-flow@alpha truth --threshold 0.8\n```\n\n**Output Formats:**\n```bash\n# Table format (default)\nnpx claude-flow@alpha truth --format table\n\n# JSON for programmatic access\nnpx claude-flow@alpha truth --format json\n\n# CSV for spreadsheet analysis\nnpx claude-flow@alpha truth --format csv\n\n# HTML report with visualizations\nnpx claude-flow@alpha truth --format html --export report.html\n```\n\n**Real-time Monitoring:**\n```bash\n# Watch mode with live updates\nnpx claude-flow@alpha truth --watch\n\n# Export metrics automatically\nnpx claude-flow@alpha truth --export .claude-flow\u002Fmetrics\u002Ftruth-$(date +%Y%m%d).json\n```\n\n#### Truth Score Dashboard\n\nExample dashboard output:\n```\n📊 Truth Metrics Dashboard\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nOverall Truth Score: 0.947 ✅\nTrend: ↗️ +2.3% (7d)\n\nTop Performers:\n  verification-agent   0.982 ⭐\n  code-analyzer       0.971 ⭐\n  test-generator      0.958 ✅\n\nNeeds Attention:\n  refactor-agent      0.821 ⚠️\n  docs-generator      0.794 ⚠️\n\nRecent Tasks:\n  task-456  0.991 ✅  \"Implement auth\"\n  task-455  0.967 ✅  \"Add tests\"\n  task-454  0.743 ❌  \"Refactor API\"\n```\n\n#### Metrics Explained\n\n**Truth Scores (0.0-1.0):**\n- `1.0-0.95`: Excellent ⭐ (production-ready)\n- `0.94-0.85`: Good ✅ (acceptable quality)\n- `0.84-0.75`: Warning ⚠️ (needs attention)\n- `\u003C0.75`: Critical ❌ (requires immediate action)\n\n**Trend Indicators:**\n- ↗️ Improving (positive trend)\n- → Stable (consistent performance)\n- ↘️ Declining (quality regression detected)\n\n**Statistics:**\n- **Mean Score**: Average truth score across all measurements\n- **Median Score**: Middle value (less affected by outliers)\n- **Standard Deviation**: Consistency of scores (lower = more consistent)\n- **Confidence Interval**: Statistical reliability of measurements\n\n### Verification Checks\n\n#### Run Verification\n\nExecute comprehensive verification checks on code, tasks, or agent outputs.\n\n**File Verification:**\n```bash\n# Verify single file\nnpx claude-flow@alpha verify check --file src\u002Fapp.js\n\n# Verify directory recursively\nnpx claude-flow@alpha verify check --directory src\u002F\n\n# Verify with auto-fix enabled\nnpx claude-flow@alpha verify check --file src\u002Futils.js --auto-fix\n\n# Verify current working directory\nnpx claude-flow@alpha verify check\n```\n\n**Task Verification:**\n```bash\n# Verify specific task output\nnpx claude-flow@alpha verify check --task task-123\n\n# Verify with custom threshold\nnpx claude-flow@alpha verify check --task task-456 --threshold 0.99\n\n# Verbose output for debugging\nnpx claude-flow@alpha verify check --task task-789 --verbose\n```\n\n**Batch Verification:**\n```bash\n# Verify multiple files in parallel\nnpx claude-flow@alpha verify batch --files \"*.js\" --parallel\n\n# Verify with pattern matching\nnpx claude-flow@alpha verify batch --pattern \"src\u002F**\u002F*.ts\"\n\n# Integration test suite\nnpx claude-flow@alpha verify integration --test-suite full\n```\n\n#### Verification Criteria\n\nThe verification system evaluates:\n\n1. **Code Correctness**\n   - Syntax validation\n   - Type checking (TypeScript)\n   - Logic flow analysis\n   - Error handling completeness\n\n2. **Best Practices**\n   - Code style adherence\n   - SOLID principles\n   - Design patterns usage\n   - Modularity and reusability\n\n3. **Security**\n   - Vulnerability scanning\n   - Secret detection\n   - Input validation\n   - Authentication\u002Fauthorization checks\n\n4. **Performance**\n   - Algorithmic complexity\n   - Memory usage patterns\n   - Database query optimization\n   - Bundle size impact\n\n5. **Documentation**\n   - JSDoc\u002FTypeDoc completeness\n   - README accuracy\n   - API documentation\n   - Code comments quality\n\n#### JSON Output for CI\u002FCD\n\n```bash\n# Get structured JSON output\nnpx claude-flow@alpha verify check --json > verification.json\n\n# Example JSON structure:\n{\n  \"overallScore\": 0.947,\n  \"passed\": true,\n  \"threshold\": 0.95,\n  \"checks\": [\n    {\n      \"name\": \"code-correctness\",\n      \"score\": 0.98,\n      \"passed\": true\n    },\n    {\n      \"name\": \"security\",\n      \"score\": 0.91,\n      \"passed\": false,\n      \"issues\": [...]\n    }\n  ]\n}\n```\n\n### Automatic Rollback\n\n#### Rollback Failed Changes\n\nAutomatically revert changes that fail verification checks.\n\n**Basic Rollback:**\n```bash\n# Rollback to last known good state\nnpx claude-flow@alpha verify rollback --last-good\n\n# Rollback to specific commit\nnpx claude-flow@alpha verify rollback --to-commit abc123\n\n# Interactive rollback with preview\nnpx claude-flow@alpha verify rollback --interactive\n```\n\n**Smart Rollback:**\n```bash\n# Rollback only failed files (preserve good changes)\nnpx claude-flow@alpha verify rollback --selective\n\n# Rollback with automatic backup\nnpx claude-flow@alpha verify rollback --backup-first\n\n# Dry-run mode (preview without executing)\nnpx claude-flow@alpha verify rollback --dry-run\n```\n\n**Rollback Performance:**\n- Git-based rollback: \u003C1 second\n- Selective file rollback: \u003C500ms\n- Backup creation: Automatic before rollback\n\n### Verification Reports\n\n#### Generate Reports\n\nCreate detailed verification reports with metrics and visualizations.\n\n**Report Formats:**\n```bash\n# JSON report\nnpx claude-flow@alpha verify report --format json\n\n# HTML report with charts\nnpx claude-flow@alpha verify report --export metrics.html --format html\n\n# CSV for data analysis\nnpx claude-flow@alpha verify report --format csv --export metrics.csv\n\n# Markdown summary\nnpx claude-flow@alpha verify report --format markdown\n```\n\n**Time-based Reports:**\n```bash\n# Last 24 hours\nnpx claude-flow@alpha verify report --period 24h\n\n# Last 7 days\nnpx claude-flow@alpha verify report --period 7d\n\n# Last 30 days with trends\nnpx claude-flow@alpha verify report --period 30d --include-trends\n\n# Custom date range\nnpx claude-flow@alpha verify report --from 2025-01-01 --to 2025-01-31\n```\n\n**Report Content:**\n- Overall truth scores\n- Per-agent performance metrics\n- Task completion quality\n- Verification pass\u002Ffail rates\n- Rollback frequency\n- Quality improvement trends\n- Statistical confidence intervals\n\n### Interactive Dashboard\n\n#### Launch Dashboard\n\nRun interactive web-based verification dashboard with real-time updates.\n\n```bash\n# Launch dashboard on default port (3000)\nnpx claude-flow@alpha verify dashboard\n\n# Custom port\nnpx claude-flow@alpha verify dashboard --port 8080\n\n# Export dashboard data\nnpx claude-flow@alpha verify dashboard --export\n\n# Dashboard with auto-refresh\nnpx claude-flow@alpha verify dashboard --refresh 5s\n```\n\n**Dashboard Features:**\n- Real-time truth score updates (WebSocket)\n- Interactive charts and graphs\n- Agent performance comparison\n- Task history timeline\n- Rollback history viewer\n- Export to PDF\u002FHTML\n- Filter by time period\u002Fagent\u002Fscore\n\n### Configuration\n\n#### Default Configuration\n\nSet verification preferences in `.claude-flow\u002Fconfig.json`:\n\n```json\n{\n  \"verification\": {\n    \"threshold\": 0.95,\n    \"autoRollback\": true,\n    \"gitIntegration\": true,\n    \"hooks\": {\n      \"preCommit\": true,\n      \"preTask\": true,\n      \"postEdit\": true\n    },\n    \"checks\": {\n      \"codeCorrectness\": true,\n      \"security\": true,\n      \"performance\": true,\n      \"documentation\": true,\n      \"bestPractices\": true\n    }\n  },\n  \"truth\": {\n    \"defaultFormat\": \"table\",\n    \"defaultPeriod\": \"24h\",\n    \"warningThreshold\": 0.85,\n    \"criticalThreshold\": 0.75,\n    \"autoExport\": {\n      \"enabled\": true,\n      \"path\": \".claude-flow\u002Fmetrics\u002Ftruth-daily.json\"\n    }\n  }\n}\n```\n\n#### Threshold Configuration\n\n**Adjust verification strictness:**\n```bash\n# Strict mode (99% accuracy required)\nnpx claude-flow@alpha verify check --threshold 0.99\n\n# Lenient mode (90% acceptable)\nnpx claude-flow@alpha verify check --threshold 0.90\n\n# Set default threshold\nnpx claude-flow@alpha config set verification.threshold 0.98\n```\n\n**Per-environment thresholds:**\n```json\n{\n  \"verification\": {\n    \"thresholds\": {\n      \"production\": 0.99,\n      \"staging\": 0.95,\n      \"development\": 0.90\n    }\n  }\n}\n```\n\n### Integration Examples\n\n#### CI\u002FCD Integration\n\n**GitHub Actions:**\n```yaml\nname: Quality Verification\n\non: [push, pull_request]\n\njobs:\n  verify:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v3\n\n      - name: Install Dependencies\n        run: npm install\n\n      - name: Run Verification\n        run: |\n          npx claude-flow@alpha verify check --json > verification.json\n\n      - name: Check Truth Score\n        run: |\n          score=$(jq '.overallScore' verification.json)\n          if (( $(echo \"$score \u003C 0.95\" | bc -l) )); then\n            echo \"Truth score too low: $score\"\n            exit 1\n          fi\n\n      - name: Upload Report\n        uses: actions\u002Fupload-artifact@v3\n        with:\n          name: verification-report\n          path: verification.json\n```\n\n**GitLab CI:**\n```yaml\nverify:\n  stage: test\n  script:\n    - npx claude-flow@alpha verify check --threshold 0.95 --json > verification.json\n    - |\n      score=$(jq '.overallScore' verification.json)\n      if [ $(echo \"$score \u003C 0.95\" | bc) -eq 1 ]; then\n        echo \"Verification failed with score: $score\"\n        exit 1\n      fi\n  artifacts:\n    paths:\n      - verification.json\n    reports:\n      junit: verification.json\n```\n\n#### Swarm Integration\n\nRun verification automatically during swarm operations:\n\n```bash\n# Swarm with verification enabled\nnpx claude-flow@alpha swarm --verify --threshold 0.98\n\n# Hive Mind with auto-rollback\nnpx claude-flow@alpha hive-mind --verify --rollback-on-fail\n\n# Training pipeline with verification\nnpx claude-flow@alpha train --verify --threshold 0.99\n```\n\n#### Pair Programming Integration\n\nEnable real-time verification during collaborative development:\n\n```bash\n# Pair with verification\nnpx claude-flow@alpha pair --verify --real-time\n\n# Pair with custom threshold\nnpx claude-flow@alpha pair --verify --threshold 0.97 --auto-fix\n```\n\n### Advanced Workflows\n\n#### Continuous Verification\n\nMonitor codebase continuously during development:\n\n```bash\n# Watch directory for changes\nnpx claude-flow@alpha verify watch --directory src\u002F\n\n# Watch with auto-fix\nnpx claude-flow@alpha verify watch --directory src\u002F --auto-fix\n\n# Watch with notifications\nnpx claude-flow@alpha verify watch --notify --threshold 0.95\n```\n\n#### Monitoring Integration\n\nSend metrics to external monitoring systems:\n\n```bash\n# Export to Prometheus\nnpx claude-flow@alpha truth --format json | \\\n  curl -X POST https:\u002F\u002Fpushgateway.example.com\u002Fmetrics\u002Fjob\u002Fclaude-flow \\\n  -d @-\n\n# Send to DataDog\nnpx claude-flow@alpha verify report --format json | \\\n  curl -X POST \"https:\u002F\u002Fapi.datadoghq.com\u002Fapi\u002Fv1\u002Fseries?api_key=${DD_API_KEY}\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d @-\n\n# Custom webhook\nnpx claude-flow@alpha truth --format json | \\\n  curl -X POST https:\u002F\u002Fmetrics.example.com\u002Fapi\u002Ftruth \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d @-\n```\n\n#### Pre-commit Hooks\n\nAutomatically verify before commits:\n\n```bash\n# Install pre-commit hook\nnpx claude-flow@alpha verify install-hook --pre-commit\n\n# .git\u002Fhooks\u002Fpre-commit example:\n#!\u002Fbin\u002Fbash\nnpx claude-flow@alpha verify check --threshold 0.95 --json > \u002Ftmp\u002Fverify.json\n\nscore=$(jq '.overallScore' \u002Ftmp\u002Fverify.json)\nif (( $(echo \"$score \u003C 0.95\" | bc -l) )); then\n  echo \"❌ Verification failed with score: $score\"\n  echo \"Run 'npx claude-flow@alpha verify check --verbose' for details\"\n  exit 1\nfi\n\necho \"✅ Verification passed with score: $score\"\n```\n\n### Performance Metrics\n\n**Verification Speed:**\n- Single file check: \u003C100ms\n- Directory scan: \u003C500ms (per 100 files)\n- Full codebase analysis: \u003C5s (typical project)\n- Truth score calculation: \u003C50ms\n\n**Rollback Speed:**\n- Git-based rollback: \u003C1s\n- Selective file rollback: \u003C500ms\n- Backup creation: \u003C2s\n\n**Dashboard Performance:**\n- Initial load: \u003C1s\n- Real-time updates: \u003C100ms latency (WebSocket)\n- Chart rendering: 60 FPS\n\n### Troubleshooting\n\n#### Common Issues\n\n**Low Truth Scores:**\n```bash\n# Get detailed breakdown\nnpx claude-flow@alpha truth --verbose --threshold 0.0\n\n# Check specific criteria\nnpx claude-flow@alpha verify check --verbose\n\n# View agent-specific issues\nnpx claude-flow@alpha truth --agent \u003Cagent-name> --format json\n```\n\n**Rollback Failures:**\n```bash\n# Check git status\ngit status\n\n# View rollback history\nnpx claude-flow@alpha verify rollback --history\n\n# Manual rollback\ngit reset --hard HEAD~1\n```\n\n**Verification Timeouts:**\n```bash\n# Increase timeout\nnpx claude-flow@alpha verify check --timeout 60s\n\n# Verify in batches\nnpx claude-flow@alpha verify batch --batch-size 10\n```\n\n### Exit Codes\n\nVerification commands return standard exit codes:\n\n- `0`: Verification passed (score ≥ threshold)\n- `1`: Verification failed (score \u003C threshold)\n- `2`: Error during verification (invalid input, system error)\n\n### Related Commands\n\n- `npx claude-flow@alpha pair` - Collaborative development with verification\n- `npx claude-flow@alpha train` - Training with verification feedback\n- `npx claude-flow@alpha swarm` - Multi-agent coordination with quality checks\n- `npx claude-flow@alpha report` - Generate comprehensive project reports\n\n### Best Practices\n\n1. **Set Appropriate Thresholds**: Use 0.99 for critical code, 0.95 for standard, 0.90 for experimental\n2. **Enable Auto-rollback**: Prevent bad code from persisting\n3. **Monitor Trends**: Track improvement over time, not just current scores\n4. **Integrate with CI\u002FCD**: Make verification part of your pipeline\n5. **Use Watch Mode**: Get immediate feedback during development\n6. **Export Metrics**: Track quality metrics in your monitoring system\n7. **Review Rollbacks**: Understand why changes were rejected\n8. **Train Agents**: Use verification feedback to improve agent performance\n\n### Additional Resources\n\n- Truth Scoring Algorithm: See `\u002Fdocs\u002Ftruth-scoring.md`\n- Verification Criteria: See `\u002Fdocs\u002Fverification-criteria.md`\n- Integration Examples: See `\u002Fexamples\u002Fverification\u002F`\n- API Reference: See `\u002Fdocs\u002Fapi\u002Fverification.md`\n","# Verification & Quality Assurance Skill\n\n## What This Skill Does\n\nThis skill provides a comprehensive verification and quality assurance system that ensures code quality and correctness through:\n\n- **Truth Scoring**: Real-time reliability metrics (0.0-1.0 scale) for code, agents, and tasks\n- **Verification Checks**: Automated code correctness, security, and best practices validation\n- **Automatic Rollback**: Instant reversion of changes that fail verification (default threshold: 0.95)\n- **Quality Metrics**: Statistical analysis with trends, confidence intervals, and improvement tracking\n- **CI\u002FCD Integration**: Export capabilities for continuous integration pipelines\n- **Real-time Monitoring**: Live dashboards and watch modes for ongoing verification\n\n## Prerequisites\n\n- Claude Flow installed (`npx claude-flow@alpha`)\n- Git repository (for rollback features)\n- Node.js 18+ (for dashboard features)\n\n## Quick Start\n\n```bash\n# View current truth scores\nnpx claude-flow@alpha truth\n\n# Run verification check\nnpx claude-flow@alpha verify check\n\n# Verify specific file with custom threshold\nnpx claude-flow@alpha verify check --file src\u002Fapp.js --threshold 0.98\n\n# Rollback last failed verification\nnpx claude-flow@alpha verify rollback --last-good\n```\n\n---\n\n## Complete Guide\n\n### Truth Scoring System\n\n#### View Truth Metrics\n\nDisplay comprehensive quality and reliability metrics for your codebase and agent tasks.\n\n**Basic Usage:**\n```bash\n# View current truth scores (default: table format)\nnpx claude-flow@alpha truth\n\n# View scores for specific time period\nnpx claude-flow@alpha truth --period 7d\n\n# View scores for specific agent\nnpx claude-flow@alpha truth --agent coder --period 24h\n\n# Find files\u002Ftasks below threshold\nnpx claude-flow@alpha truth --threshold 0.8\n```\n\n**Output Formats:**\n```bash\n# Table format (default)\nnpx claude-flow@alpha truth --format table\n\n# JSON for programmatic access\nnpx claude-flow@alpha truth --format json\n\n# CSV for spreadsheet analysis\nnpx claude-flow@alpha truth --format csv\n\n# HTML report with visualizations\nnpx claude-flow@alpha truth --format html --export report.html\n```\n\n**Real-time Monitoring:**\n```bash\n# Watch mode with live updates\nnpx claude-flow@alpha truth --watch\n\n# Export metrics automatically\nnpx claude-flow@alpha truth --export .claude-flow\u002Fmetrics\u002Ftruth-$(date +%Y%m%d).json\n```\n\n#### Truth Score Dashboard\n\nExample dashboard output:\n```\n📊 Truth Metrics Dashboard\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n\nOverall Truth Score: 0.947 ✅\nTrend: ↗️ +2.3% (7d)\n\nTop Performers:\n  verification-agent   0.982 ⭐\n  code-analyzer       0.971 ⭐\n  test-generator      0.958 ✅\n\nNeeds Attention:\n  refactor-agent      0.821 ⚠️\n  docs-generator      0.794 ⚠️\n\nRecent Tasks:\n  task-456  0.991 ✅  \"Implement auth\"\n  task-455  0.967 ✅  \"Add tests\"\n  task-454  0.743 ❌  \"Refactor API\"\n```\n\n#### Metrics Explained\n\n**Truth Scores (0.0-1.0):**\n- `1.0-0.95`: Excellent ⭐ (production-ready)\n- `0.94-0.85`: Good ✅ (acceptable quality)\n- `0.84-0.75`: Warning ⚠️ (needs attention)\n- `\u003C0.75`: Critical ❌ (requires immediate action)\n\n**Trend Indicators:**\n- ↗️ Improving (positive trend)\n- → Stable (consistent performance)\n- ↘️ Declining (quality regression detected)\n\n**Statistics:**\n- **Mean Score**: Average truth score across all measurements\n- **Median Score**: Middle value (less affected by outliers)\n- **Standard Deviation**: Consistency of scores (lower = more consistent)\n- **Confidence Interval**: Statistical reliability of measurements\n\n### Verification Checks\n\n#### Run Verification\n\nExecute comprehensive verification checks on code, tasks, or agent outputs.\n\n**File Verification:**\n```bash\n# Verify single file\nnpx claude-flow@alpha verify check --file src\u002Fapp.js\n\n# Verify directory recursively\nnpx claude-flow@alpha verify check --directory src\u002F\n\n# Verify with auto-fix enabled\nnpx claude-flow@alpha verify check --file src\u002Futils.js --auto-fix\n\n# Verify current working directory\nnpx claude-flow@alpha verify check\n```\n\n**Task Verification:**\n```bash\n# Verify specific task output\nnpx claude-flow@alpha verify check --task task-123\n\n# Verify with custom threshold\nnpx claude-flow@alpha verify check --task task-456 --threshold 0.99\n\n# Verbose output for debugging\nnpx claude-flow@alpha verify check --task task-789 --verbose\n```\n\n**Batch Verification:**\n```bash\n# Verify multiple files in parallel\nnpx claude-flow@alpha verify batch --files \"*.js\" --parallel\n\n# Verify with pattern matching\nnpx claude-flow@alpha verify batch --pattern \"src\u002F**\u002F*.ts\"\n\n# Integration test suite\nnpx claude-flow@alpha verify integration --test-suite full\n```\n\n#### Verification Criteria\n\nThe verification system evaluates:\n\n1. **Code Correctness**\n   - Syntax validation\n   - Type checking (TypeScript)\n   - Logic flow analysis\n   - Error handling completeness\n\n2. **Best Practices**\n   - Code style adherence\n   - SOLID principles\n   - Design patterns usage\n   - Modularity and reusability\n\n3. **Security**\n   - Vulnerability scanning\n   - Secret detection\n   - Input validation\n   - Authentication\u002Fauthorization checks\n\n4. **Performance**\n   - Algorithmic complexity\n   - Memory usage patterns\n   - Database query optimization\n   - Bundle size impact\n\n5. **Documentation**\n   - JSDoc\u002FTypeDoc completeness\n   - README accuracy\n   - API documentation\n   - Code comments quality\n\n#### JSON Output for CI\u002FCD\n\n```bash\n# Get structured JSON output\nnpx claude-flow@alpha verify check --json > verification.json\n\n# Example JSON structure:\n{\n  \"overallScore\": 0.947,\n  \"passed\": true,\n  \"threshold\": 0.95,\n  \"checks\": [\n    {\n      \"name\": \"code-correctness\",\n      \"score\": 0.98,\n      \"passed\": true\n    },\n    {\n      \"name\": \"security\",\n      \"score\": 0.91,\n      \"passed\": false,\n      \"issues\": [...]\n    }\n  ]\n}\n```\n\n### Automatic Rollback\n\n#### Rollback Failed Changes\n\nAutomatically revert changes that fail verification checks.\n\n**Basic Rollback:**\n```bash\n# Rollback to last known good state\nnpx claude-flow@alpha verify rollback --last-good\n\n# Rollback to specific commit\nnpx claude-flow@alpha verify rollback --to-commit abc123\n\n# Interactive rollback with preview\nnpx claude-flow@alpha verify rollback --interactive\n```\n\n**Smart Rollback:**\n```bash\n# Rollback only failed files (preserve good changes)\nnpx claude-flow@alpha verify rollback --selective\n\n# Rollback with automatic backup\nnpx claude-flow@alpha verify rollback --backup-first\n\n# Dry-run mode (preview without executing)\nnpx claude-flow@alpha verify rollback --dry-run\n```\n\n**Rollback Performance:**\n- Git-based rollback: \u003C1 second\n- Selective file rollback: \u003C500ms\n- Backup creation: Automatic before rollback\n\n### Verification Reports\n\n#### Generate Reports\n\nCreate detailed verification reports with metrics and visualizations.\n\n**Report Formats:**\n```bash\n# JSON report\nnpx claude-flow@alpha verify report --format json\n\n# HTML report with charts\nnpx claude-flow@alpha verify report --export metrics.html --format html\n\n# CSV for data analysis\nnpx claude-flow@alpha verify report --format csv --export metrics.csv\n\n# Markdown summary\nnpx claude-flow@alpha verify report --format markdown\n```\n\n**Time-based Reports:**\n```bash\n# Last 24 hours\nnpx claude-flow@alpha verify report --period 24h\n\n# Last 7 days\nnpx claude-flow@alpha verify report --period 7d\n\n# Last 30 days with trends\nnpx claude-flow@alpha verify report --period 30d --include-trends\n\n# Custom date range\nnpx claude-flow@alpha verify report --from 2025-01-01 --to 2025-01-31\n```\n\n**Report Content:**\n- Overall truth scores\n- Per-agent performance metrics\n- Task completion quality\n- Verification pass\u002Ffail rates\n- Rollback frequency\n- Quality improvement trends\n- Statistical confidence intervals\n\n### Interactive Dashboard\n\n#### Launch Dashboard\n\nRun interactive web-based verification dashboard with real-time updates.\n\n```bash\n# Launch dashboard on default port (3000)\nnpx claude-flow@alpha verify dashboard\n\n# Custom port\nnpx claude-flow@alpha verify dashboard --port 8080\n\n# Export dashboard data\nnpx claude-flow@alpha verify dashboard --export\n\n# Dashboard with auto-refresh\nnpx claude-flow@alpha verify dashboard --refresh 5s\n```\n\n**Dashboard Features:**\n- Real-time truth score updates (WebSocket)\n- Interactive charts and graphs\n- Agent performance comparison\n- Task history timeline\n- Rollback history viewer\n- Export to PDF\u002FHTML\n- Filter by time period\u002Fagent\u002Fscore\n\n### Configuration\n\n#### Default Configuration\n\nSet verification preferences in `.claude-flow\u002Fconfig.json`:\n\n```json\n{\n  \"verification\": {\n    \"threshold\": 0.95,\n    \"autoRollback\": true,\n    \"gitIntegration\": true,\n    \"hooks\": {\n      \"preCommit\": true,\n      \"preTask\": true,\n      \"postEdit\": true\n    },\n    \"checks\": {\n      \"codeCorrectness\": true,\n      \"security\": true,\n      \"performance\": true,\n      \"documentation\": true,\n      \"bestPractices\": true\n    }\n  },\n  \"truth\": {\n    \"defaultFormat\": \"table\",\n    \"defaultPeriod\": \"24h\",\n    \"warningThreshold\": 0.85,\n    \"criticalThreshold\": 0.75,\n    \"autoExport\": {\n      \"enabled\": true,\n      \"path\": \".claude-flow\u002Fmetrics\u002Ftruth-daily.json\"\n    }\n  }\n}\n```\n\n#### Threshold Configuration\n\n**Adjust verification strictness:**\n```bash\n# Strict mode (99% accuracy required)\nnpx claude-flow@alpha verify check --threshold 0.99\n\n# Lenient mode (90% acceptable)\nnpx claude-flow@alpha verify check --threshold 0.90\n\n# Set default threshold\nnpx claude-flow@alpha config set verification.threshold 0.98\n```\n\n**Per-environment thresholds:**\n```json\n{\n  \"verification\": {\n    \"thresholds\": {\n      \"production\": 0.99,\n      \"staging\": 0.95,\n      \"development\": 0.90\n    }\n  }\n}\n```\n\n### Integration Examples\n\n#### CI\u002FCD Integration\n\n**GitHub Actions:**\n```yaml\nname: Quality Verification\n\non: [push, pull_request]\n\njobs:\n  verify:\n    runs-on: ubuntu-latest\n    steps:\n      - uses: actions\u002Fcheckout@v3\n\n      - name: Install Dependencies\n        run: npm install\n\n      - name: Run Verification\n        run: |\n          npx claude-flow@alpha verify check --json > verification.json\n\n      - name: Check Truth Score\n        run: |\n          score=$(jq '.overallScore' verification.json)\n          if (( $(echo \"$score \u003C 0.95\" | bc -l) )); then\n            echo \"Truth score too low: $score\"\n            exit 1\n          fi\n\n      - name: Upload Report\n        uses: actions\u002Fupload-artifact@v3\n        with:\n          name: verification-report\n          path: verification.json\n```\n\n**GitLab CI:**\n```yaml\nverify:\n  stage: test\n  script:\n    - npx claude-flow@alpha verify check --threshold 0.95 --json > verification.json\n    - |\n      score=$(jq '.overallScore' verification.json)\n      if [ $(echo \"$score \u003C 0.95\" | bc) -eq 1 ]; then\n        echo \"Verification failed with score: $score\"\n        exit 1\n      fi\n  artifacts:\n    paths:\n      - verification.json\n    reports:\n      junit: verification.json\n```\n\n#### Swarm Integration\n\nRun verification automatically during swarm operations:\n\n```bash\n# Swarm with verification enabled\nnpx claude-flow@alpha swarm --verify --threshold 0.98\n\n# Hive Mind with auto-rollback\nnpx claude-flow@alpha hive-mind --verify --rollback-on-fail\n\n# Training pipeline with verification\nnpx claude-flow@alpha train --verify --threshold 0.99\n```\n\n#### Pair Programming Integration\n\nEnable real-time verification during collaborative development:\n\n```bash\n# Pair with verification\nnpx claude-flow@alpha pair --verify --real-time\n\n# Pair with custom threshold\nnpx claude-flow@alpha pair --verify --threshold 0.97 --auto-fix\n```\n\n### Advanced Workflows\n\n#### Continuous Verification\n\nMonitor codebase continuously during development:\n\n```bash\n# Watch directory for changes\nnpx claude-flow@alpha verify watch --directory src\u002F\n\n# Watch with auto-fix\nnpx claude-flow@alpha verify watch --directory src\u002F --auto-fix\n\n# Watch with notifications\nnpx claude-flow@alpha verify watch --notify --threshold 0.95\n```\n\n#### Monitoring Integration\n\nSend metrics to external monitoring systems:\n\n```bash\n# Export to Prometheus\nnpx claude-flow@alpha truth --format json | \\\n  curl -X POST https:\u002F\u002Fpushgateway.example.com\u002Fmetrics\u002Fjob\u002Fclaude-flow \\\n  -d @-\n\n# Send to DataDog\nnpx claude-flow@alpha verify report --format json | \\\n  curl -X POST \"https:\u002F\u002Fapi.datadoghq.com\u002Fapi\u002Fv1\u002Fseries?api_key=${DD_API_KEY}\" \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d @-\n\n# Custom webhook\nnpx claude-flow@alpha truth --format json | \\\n  curl -X POST https:\u002F\u002Fmetrics.example.com\u002Fapi\u002Ftruth \\\n  -H \"Content-Type: application\u002Fjson\" \\\n  -d @-\n```\n\n#### Pre-commit Hooks\n\nAutomatically verify before commits:\n\n```bash\n# Install pre-commit hook\nnpx claude-flow@alpha verify install-hook --pre-commit\n\n# .git\u002Fhooks\u002Fpre-commit example:\n#!\u002Fbin\u002Fbash\nnpx claude-flow@alpha verify check --threshold 0.95 --json > \u002Ftmp\u002Fverify.json\n\nscore=$(jq '.overallScore' \u002Ftmp\u002Fverify.json)\nif (( $(echo \"$score \u003C 0.95\" | bc -l) )); then\n  echo \"❌ Verification failed with score: $score\"\n  echo \"Run 'npx claude-flow@alpha verify check --verbose' for details\"\n  exit 1\nfi\n\necho \"✅ Verification passed with score: $score\"\n```\n\n### Performance Metrics\n\n**Verification Speed:**\n- Single file check: \u003C100ms\n- Directory scan: \u003C500ms (per 100 files)\n- Full codebase analysis: \u003C5s (typical project)\n- Truth score calculation: \u003C50ms\n\n**Rollback Speed:**\n- Git-based rollback: \u003C1s\n- Selective file rollback: \u003C500ms\n- Backup creation: \u003C2s\n\n**Dashboard Performance:**\n- Initial load: \u003C1s\n- Real-time updates: \u003C100ms latency (WebSocket)\n- Chart rendering: 60 FPS\n\n### Troubleshooting\n\n#### Common Issues\n\n**Low Truth Scores:**\n```bash\n# Get detailed breakdown\nnpx claude-flow@alpha truth --verbose --threshold 0.0\n\n# Check specific criteria\nnpx claude-flow@alpha verify check --verbose\n\n# View agent-specific issues\nnpx claude-flow@alpha truth --agent \u003Cagent-name> --format json\n```\n\n**Rollback Failures:**\n```bash\n# Check git status\ngit status\n\n# View rollback history\nnpx claude-flow@alpha verify rollback --history\n\n# Manual rollback\ngit reset --hard HEAD~1\n```\n\n**Verification Timeouts:**\n```bash\n# Increase timeout\nnpx claude-flow@alpha verify check --timeout 60s\n\n# Verify in batches\nnpx claude-flow@alpha verify batch --batch-size 10\n```\n\n### Exit Codes\n\nVerification commands return standard exit codes:\n\n- `0`: Verification passed (score ≥ threshold)\n- `1`: Verification failed (score \u003C threshold)\n- `2`: Error during verification (invalid input, system error)\n\n### Related Commands\n\n- `npx claude-flow@alpha pair` - Collaborative development with verification\n- `npx claude-flow@alpha train` - Training with verification feedback\n- `npx claude-flow@alpha swarm` - Multi-agent coordination with quality checks\n- `npx claude-flow@alpha report` - Generate comprehensive project reports\n\n### Best Practices\n\n1. **Set Appropriate Thresholds**: Use 0.99 for critical code, 0.95 for standard, 0.90 for experimental\n2. **Enable Auto-rollback**: Prevent bad code from persisting\n3. **Monitor Trends**: Track improvement over time, not just current scores\n4. **Integrate with CI\u002FCD**: Make verification part of your pipeline\n5. **Use Watch Mode**: Get immediate feedback during development\n6. **Export Metrics**: Track quality metrics in your monitoring system\n7. **Review Rollbacks**: Understand why changes were rejected\n8. **Train Agents**: Use verification feedback to improve agent performance\n\n### Additional Resources\n\n- Truth Scoring Algorithm: See `\u002Fdocs\u002Ftruth-scoring.md`\n- Verification Criteria: See `\u002Fdocs\u002Fverification-criteria.md`\n- Integration Examples: See `\u002Fexamples\u002Fverification\u002F`\n- API Reference: See `\u002Fdocs\u002Fapi\u002Fverification.md`\n",{"name":5,"tags":24,"version":31,"category":32,"description":7},[25,26,27,28,29,30],"verification","truth-scoring","quality","rollback","metrics","ci-cd","2.0.0","quality-assurance","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fmcp\u002F.claude\u002Fskills\u002Fverification-quality",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":54},[44,47,50],{"tool":45,"command":46},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"Verification & Quality Assurance\"",{"tool":48,"command":49},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"Verification & Quality Assurance\"",{"tool":51,"command":52},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"Verification & Quality Assurance\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fmcp\u002F.claude\u002Fskills\u002Fverification-quality\u002FSKILL.md",true,[],[57,64,71,78,85,92],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]