[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EDD5XDFM767CP7GXWT00VM":3,"skill-same:01M7EDD5XDFM767CP7GXWT00VM":52},{"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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":45},"01M7EDD5XDFM767CP7GXWT00VM","skill-extract",null,"Reverse-engineer design systems, tokens, and components from live products or screenshots","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fskill-extract\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: skill-extract\ndescription: \"Reverse-engineer design systems, tokens, and components from live products or screenshots\"\ndisable-model-invocation: true\n---\n\n> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Extract Skill - Implementation Guide\n\n## Overview\n\nThe `extract` skill provides comprehensive reverse-engineering capabilities for design systems and product architectures. It transforms undocumented codebases into structured, implementation-ready documentation.\n\n## Capabilities\n\n### Design System Extraction\n- **Token Extraction**: Colors, typography, spacing, shadows from code or CSS\n- **Component Analysis**: Props, variants, usage patterns across React\u002FVue\u002FSvelte\n- **Pattern Detection**: Layout patterns, design rules, accessibility guidelines\n- **Storybook Generation**: Auto-generated stories with variants and controls\n\n### Product Architecture Extraction\n- **Service Detection**: Microservice boundaries, modules, domain boundaries\n- **API Mapping**: REST, GraphQL, tRPC, gRPC endpoint cataloging\n- **Data Modeling**: ORM schema extraction (Prisma, TypeORM, Sequelize)\n- **Feature Inventory**: Route-based and domain-based feature detection\n- **C4 Diagrams**: Automated architecture visualization (Mermaid)\n\n## Technical Implementation\n\n### Token Extraction Pipeline\n\n**Priority Order** (High to Low Confidence):\n1. **Code-Defined** (95%): `theme.ts`, `tokens.json`, Tailwind config\n2. **CSS Variables** (90%): `:root` declarations\n3. **Computed Styles** (60%): DOM analysis\n4. **Inferred** (40-60%): Color clustering, scale detection\n\n**Color Clustering Algorithm**:\n- Uses CIEDE2000 for perceptually-accurate color distance\n- K-means++ initialization for stable clustering\n- Default k=8 clusters for primary palettes\n- ΔE \u003C 2 threshold for duplicate detection\n\n### Component Analysis\n\n**Detection Strategies**:\n- AST parsing for TypeScript\u002FJavaScript\n- Prop extraction from interfaces and PropTypes\n- Variant detection from union types\n- Usage tracking across codebase\n\n**Supported Frameworks**:\n- React (functional, class, hooks)\n- Vue (SFC, Composition API, Options API)\n- Svelte (script\u002Ftemplate separation)\n\n### Architecture Detection\n\n**Service Boundary Heuristics**:\n- Package.json in subdirectories\n- Independent deployment configs\n- Team ownership boundaries\n- Communication pattern analysis\n\n**API Endpoint Detection**:\n- Decorator-based routing (NestJS, routing-controllers)\n- Express\u002FFastify route definitions\n- GraphQL resolver classes\n- tRPC router procedures\n- Protocol Buffer (.proto) files\n\n## Multi-AI Orchestration\n\nWhen enabled, the extract feature uses multiple AI providers for higher accuracy:\n\n**Provider Roles**:\n- **Claude**: Synthesis, conflict resolution, documentation\n- **Codex**: Code-level analysis, type extraction, architecture\n- **Antigravity**: Pattern recognition, alternative interpretations, UX insights\n\n**Consensus Mechanism**:\n- Threshold: extraction quality gates require the configured consensus threshold (default 67%); when no numeric vote data exists, the quorum resolver selects the strongest matching proposal from up to 3 provider perspectives and logs disagreements.\n- Disagreements logged in `90_evidence\u002Fdisagreements.md`\n- Confidence scores attached to all outputs\n\n## Output Structure\n\n```\noctopus-extract\u002F\n└── project-name\u002F\n    └── timestamp\u002F\n        ├── README.md                   # Navigation and summary\n        ├── metadata.json               # Extraction parameters\n        │\n        ├── 00_intent\u002F\n        │   ├── answers.json            # User intent responses\n        │   ├── intent-contract.md      # Human-readable summary\n        │   └── detection-report.md     # Stack auto-detection results\n        │\n        ├── 10_design\u002F\n        │   ├── tokens.json             # W3C Design Tokens format\n        │   ├── tokens.css              # CSS custom properties\n        │   ├── tokens.md               # Human-readable token docs\n        │   ├── components.csv          # Component inventory (tabular)\n        │   ├── components.json         # Structured component data\n        │   ├── patterns.md             # Layout and design patterns\n        │   └── storybook\u002F              # Storybook scaffold (optional)\n        │       ├── .storybook\u002F\n        │       └── stories\u002F\n        │\n        ├── 20_product\u002F\n        │   ├── product-overview.md     # What, who, key journeys\n        │   ├── feature-inventory.md    # Features by domain\n        │   ├── architecture.md         # C4 text description\n        │   ├── architecture.mmd        # Mermaid C4 diagrams\n        │   ├── PRD.md                  # AI-agent executable PRD\n        │   ├── user-stories.md         # Gherkin-style scenarios\n        │   ├── api-contracts.md        # Endpoint specifications\n        │   ├── data-model.md           # Entity relationships\n        │   └── implementation-plan.md  # Phased milestones\n        │\n        └── 90_evidence\u002F\n            ├── quality-report.md       # Coverage and confidence metrics\n            ├── disagreements.md        # Multi-AI conflicts\n            ├── extraction-log.md       # Timestamped progress log\n            └── references.json         # File paths per claim\n```\n\n## Quality Gates\n\nAutomated validation ensures extraction quality:\n\n1. **Token Coverage**: Fail if 0 tokens in design mode\n2. **Component Coverage**: Warn if \u003C 50% of component files detected\n3. **Architecture Completeness**: Warn if no services detected in product mode\n4. **Multi-AI Consensus**: Fail if agreement is below the configured consensus threshold (default 67%) on key outputs\n\n## Usage Patterns\n\n### Basic Extraction\n```bash\n\u002Focto:extract .\u002Fmy-app\n```\n\n### Design-Only Extraction\n```bash\n\u002Focto:extract .\u002Fmy-app --mode design --storybook true\n```\n\n### Deep Analysis with Multi-AI\n```bash\n\u002Focto:extract .\u002Fmy-app --depth deep --multi-ai force\n```\n\n### URL Extraction\n```bash\n\u002Focto:extract https:\u002F\u002Fexample.com --mode design --depth quick\n```\n\n## Integration with Other Skills\n\n- **\u002Focto:review**: Review extracted outputs for quality\n- **\u002Focto:deliver**: Validate extraction completeness\n- **\u002Focto:docs**: Generate additional documentation from extractions\n\n## Error Handling\n\nCommon error codes:\n- `ERR-001`: Invalid input (path\u002FURL not found)\n- `ERR-002`: Network timeout (URL extraction)\n- `ERR-003`: Permission denied\n- `ERR-004`: Out of memory (use `--depth quick`)\n- `VAL-001`: Validation failed (no tokens detected)\n- `VAL-004`: Low multi-AI consensus\n\n## Performance Targets\n\n| Depth | Time Target | Coverage Target |\n|-------|-------------|-----------------|\n| Quick | \u003C 2 min | 70% coverage, basic analysis |\n| Standard | 2-5 min | 85% coverage, comprehensive |\n| Deep | 5-15 min | 95% coverage, multi-AI validation |\n\n## Research Sources\n\nThis skill is informed by research on:\n- [Tokens Studio](https:\u002F\u002Ftokens.studio\u002F) - Design token automation\n- [Superposition](https:\u002F\u002Fsuperposition.design\u002F) - Token extraction from websites\n- [W3C Design Tokens](https:\u002F\u002Fwww.designtokens.org\u002F) - Token format standard\n- [C4 Model](https:\u002F\u002Fc4model.com\u002F) - Architecture diagramming\n- Modern reverse-engineering practices (2026)\n\n## Implementation Status\n\n**Current Version**: 1.0.0 (Skeleton)\n\n**Implemented**:\n- ✅ Command structure\n- ✅ CLI argument parsing\n- ✅ Output directory setup\n- ✅ Metadata generation\n- ✅ Multi-AI detection\n\n**In Progress**:\n- 🚧 Token extraction pipeline\n- 🚧 Component analysis engine\n- 🚧 Architecture detection\n- 🚧 PRD generation\n- 🚧 Quality gates\n\n**Planned**:\n- ⏳ Storybook scaffold generation\n- ⏳ C4 diagram generation\n- ⏳ URL extraction mode\n- ⏳ CSS inference algorithms\n\n## Contributing\n\nSee implementation plan in project documentation.\n\nImplementation phases:\n1. Foundation & CLI (Week 1)\n2. Auto-Detection Engine (Week 2)\n3. Design Extraction (Week 3-4)\n4. Product Extraction (Week 5-6)\n5. Multi-AI Orchestration (Week 7)\n6. Quality Gates (Week 8)\n7. Testing & Documentation (Week 10)\n\n\n*This skill implements the design specified in PRD v2.0 (AI-Executable)*\n","> **Host: Codex CLI** — This skill was designed for Claude Code and adapted for Codex.\n> Cross-reference commands use installed skill names in Codex rather than `\u002Focto:*` slash commands.\n> Use the active Codex shell and subagent tools. Do not claim a provider, model, or host subagent is available until the current session exposes it.\n> For host tool equivalents, see `skills\u002Fblocks\u002Fcodex-host-adapter.md`.\n\n\n# Extract Skill - Implementation Guide\n\n## Overview\n\nThe `extract` skill provides comprehensive reverse-engineering capabilities for design systems and product architectures. It transforms undocumented codebases into structured, implementation-ready documentation.\n\n## Capabilities\n\n### Design System Extraction\n- **Token Extraction**: Colors, typography, spacing, shadows from code or CSS\n- **Component Analysis**: Props, variants, usage patterns across React\u002FVue\u002FSvelte\n- **Pattern Detection**: Layout patterns, design rules, accessibility guidelines\n- **Storybook Generation**: Auto-generated stories with variants and controls\n\n### Product Architecture Extraction\n- **Service Detection**: Microservice boundaries, modules, domain boundaries\n- **API Mapping**: REST, GraphQL, tRPC, gRPC endpoint cataloging\n- **Data Modeling**: ORM schema extraction (Prisma, TypeORM, Sequelize)\n- **Feature Inventory**: Route-based and domain-based feature detection\n- **C4 Diagrams**: Automated architecture visualization (Mermaid)\n\n## Technical Implementation\n\n### Token Extraction Pipeline\n\n**Priority Order** (High to Low Confidence):\n1. **Code-Defined** (95%): `theme.ts`, `tokens.json`, Tailwind config\n2. **CSS Variables** (90%): `:root` declarations\n3. **Computed Styles** (60%): DOM analysis\n4. **Inferred** (40-60%): Color clustering, scale detection\n\n**Color Clustering Algorithm**:\n- Uses CIEDE2000 for perceptually-accurate color distance\n- K-means++ initialization for stable clustering\n- Default k=8 clusters for primary palettes\n- ΔE \u003C 2 threshold for duplicate detection\n\n### Component Analysis\n\n**Detection Strategies**:\n- AST parsing for TypeScript\u002FJavaScript\n- Prop extraction from interfaces and PropTypes\n- Variant detection from union types\n- Usage tracking across codebase\n\n**Supported Frameworks**:\n- React (functional, class, hooks)\n- Vue (SFC, Composition API, Options API)\n- Svelte (script\u002Ftemplate separation)\n\n### Architecture Detection\n\n**Service Boundary Heuristics**:\n- Package.json in subdirectories\n- Independent deployment configs\n- Team ownership boundaries\n- Communication pattern analysis\n\n**API Endpoint Detection**:\n- Decorator-based routing (NestJS, routing-controllers)\n- Express\u002FFastify route definitions\n- GraphQL resolver classes\n- tRPC router procedures\n- Protocol Buffer (.proto) files\n\n## Multi-AI Orchestration\n\nWhen enabled, the extract feature uses multiple AI providers for higher accuracy:\n\n**Provider Roles**:\n- **Claude**: Synthesis, conflict resolution, documentation\n- **Codex**: Code-level analysis, type extraction, architecture\n- **Antigravity**: Pattern recognition, alternative interpretations, UX insights\n\n**Consensus Mechanism**:\n- Threshold: extraction quality gates require the configured consensus threshold (default 67%); when no numeric vote data exists, the quorum resolver selects the strongest matching proposal from up to 3 provider perspectives and logs disagreements.\n- Disagreements logged in `90_evidence\u002Fdisagreements.md`\n- Confidence scores attached to all outputs\n\n## Output Structure\n\n```\noctopus-extract\u002F\n└── project-name\u002F\n    └── timestamp\u002F\n        ├── README.md                   # Navigation and summary\n        ├── metadata.json               # Extraction parameters\n        │\n        ├── 00_intent\u002F\n        │   ├── answers.json            # User intent responses\n        │   ├── intent-contract.md      # Human-readable summary\n        │   └── detection-report.md     # Stack auto-detection results\n        │\n        ├── 10_design\u002F\n        │   ├── tokens.json             # W3C Design Tokens format\n        │   ├── tokens.css              # CSS custom properties\n        │   ├── tokens.md               # Human-readable token docs\n        │   ├── components.csv          # Component inventory (tabular)\n        │   ├── components.json         # Structured component data\n        │   ├── patterns.md             # Layout and design patterns\n        │   └── storybook\u002F              # Storybook scaffold (optional)\n        │       ├── .storybook\u002F\n        │       └── stories\u002F\n        │\n        ├── 20_product\u002F\n        │   ├── product-overview.md     # What, who, key journeys\n        │   ├── feature-inventory.md    # Features by domain\n        │   ├── architecture.md         # C4 text description\n        │   ├── architecture.mmd        # Mermaid C4 diagrams\n        │   ├── PRD.md                  # AI-agent executable PRD\n        │   ├── user-stories.md         # Gherkin-style scenarios\n        │   ├── api-contracts.md        # Endpoint specifications\n        │   ├── data-model.md           # Entity relationships\n        │   └── implementation-plan.md  # Phased milestones\n        │\n        └── 90_evidence\u002F\n            ├── quality-report.md       # Coverage and confidence metrics\n            ├── disagreements.md        # Multi-AI conflicts\n            ├── extraction-log.md       # Timestamped progress log\n            └── references.json         # File paths per claim\n```\n\n## Quality Gates\n\nAutomated validation ensures extraction quality:\n\n1. **Token Coverage**: Fail if 0 tokens in design mode\n2. **Component Coverage**: Warn if \u003C 50% of component files detected\n3. **Architecture Completeness**: Warn if no services detected in product mode\n4. **Multi-AI Consensus**: Fail if agreement is below the configured consensus threshold (default 67%) on key outputs\n\n## Usage Patterns\n\n### Basic Extraction\n```bash\n\u002Focto:extract .\u002Fmy-app\n```\n\n### Design-Only Extraction\n```bash\n\u002Focto:extract .\u002Fmy-app --mode design --storybook true\n```\n\n### Deep Analysis with Multi-AI\n```bash\n\u002Focto:extract .\u002Fmy-app --depth deep --multi-ai force\n```\n\n### URL Extraction\n```bash\n\u002Focto:extract https:\u002F\u002Fexample.com --mode design --depth quick\n```\n\n## Integration with Other Skills\n\n- **\u002Focto:review**: Review extracted outputs for quality\n- **\u002Focto:deliver**: Validate extraction completeness\n- **\u002Focto:docs**: Generate additional documentation from extractions\n\n## Error Handling\n\nCommon error codes:\n- `ERR-001`: Invalid input (path\u002FURL not found)\n- `ERR-002`: Network timeout (URL extraction)\n- `ERR-003`: Permission denied\n- `ERR-004`: Out of memory (use `--depth quick`)\n- `VAL-001`: Validation failed (no tokens detected)\n- `VAL-004`: Low multi-AI consensus\n\n## Performance Targets\n\n| Depth | Time Target | Coverage Target |\n|-------|-------------|-----------------|\n| Quick | \u003C 2 min | 70% coverage, basic analysis |\n| Standard | 2-5 min | 85% coverage, comprehensive |\n| Deep | 5-15 min | 95% coverage, multi-AI validation |\n\n## Research Sources\n\nThis skill is informed by research on:\n- [Tokens Studio](https:\u002F\u002Ftokens.studio\u002F) - Design token automation\n- [Superposition](https:\u002F\u002Fsuperposition.design\u002F) - Token extraction from websites\n- [W3C Design Tokens](https:\u002F\u002Fwww.designtokens.org\u002F) - Token format standard\n- [C4 Model](https:\u002F\u002Fc4model.com\u002F) - Architecture diagramming\n- Modern reverse-engineering practices (2026)\n\n## Implementation Status\n\n**Current Version**: 1.0.0 (Skeleton)\n\n**Implemented**:\n- ✅ Command structure\n- ✅ CLI argument parsing\n- ✅ Output directory setup\n- ✅ Metadata generation\n- ✅ Multi-AI detection\n\n**In Progress**:\n- 🚧 Token extraction pipeline\n- 🚧 Component analysis engine\n- 🚧 Architecture detection\n- 🚧 PRD generation\n- 🚧 Quality gates\n\n**Planned**:\n- ⏳ Storybook scaffold generation\n- ⏳ C4 diagram generation\n- ⏳ URL extraction mode\n- ⏳ CSS inference algorithms\n\n## Contributing\n\nSee implementation plan in project documentation.\n\nImplementation phases:\n1. Foundation & CLI (Week 1)\n2. Auto-Detection Engine (Week 2)\n3. Design Extraction (Week 3-4)\n4. Product Extraction (Week 5-6)\n5. Multi-AI Orchestration (Week 7)\n6. Quality Gates (Week 8)\n7. Testing & Documentation (Week 10)\n\n\n*This skill implements the design specified in PRD v2.0 (AI-Executable)*\n",{"name":5,"description":7,"disable-model-invocation":24},true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","03-逆向工程\u002Fskill-extract",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":24},[35,38,41],{"tool":36,"command":37},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-extract",{"tool":39,"command":40},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-extract",{"tool":42,"command":43},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill skill-extract","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fskill-extract\u002FSKILL.md",[46],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"agents\u002Fopenai.yaml","REFERENCE","参考文档",162,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F03-逆向工程\u002Fskill-extract\u002Fagents\u002Fopenai.yaml",[53,61,66,73,80,87],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":60},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],"2026-11-16 10:05:34",{"skillNo":62,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":63,"categories":64,"keywords":65,"publishedAt":60},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":60},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":77,"categories":78,"keywords":79,"publishedAt":60},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":86,"publishedAt":60},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":91,"categories":92,"keywords":93,"publishedAt":60},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]