[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6X78SWD4057GVPY009R7FT1":3,"skill-same:01M6X78SWD4057GVPY009R7FT1":53},{"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":24,"linkOnly":25,"markdownContent":26,"markdownBody":27,"frontMatter":28,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":6,"ownerHtmlUrl":35,"ownerBlogUrl":36,"ownerDescription":37,"updatedAt":38,"install":39,"resources":52},"01M6X78SWD4057GVPY009R7FT1","deepinit",null,"Deep codebase initialization with hierarchical AGENTS.md documentation","Cheggin\u002Frequest-for-startups","Cheggin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F79483996?v=4","01M6X6MGT5512GJHE8DY5B1ZQJ","Reagan Hsu","01M6X6MGY03X7ZJNVRFM3R1040",1,"GPL-3.0","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fdeepinit\u002FSKILL.md",[],[5,19,20,21,22,23],"documentation","deep","with","initialization","codebase","2026-11-10 10:12:30",false,"---\nname: deepinit\ndescription: Deep codebase initialization with hierarchical AGENTS.md documentation\nlevel: 4\n---\n\n# Deep Init Skill\n\nCreates comprehensive, hierarchical AGENTS.md documentation across the entire codebase.\n\n## Core Concept\n\nAGENTS.md files serve as **AI-readable documentation** that helps agents understand:\n- What each directory contains\n- How components relate to each other\n- Special instructions for working in that area\n- Dependencies and relationships\n\n## Hierarchical Tagging System\n\nEvery AGENTS.md (except root) includes a parent reference tag:\n\n```markdown\n\u003C!-- Parent: ..\u002FAGENTS.md -->\n```\n\nThis creates a navigable hierarchy:\n```\n\u002FAGENTS.md                          ← Root (no parent tag)\n├── src\u002FAGENTS.md                   ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n│   ├── src\u002Fcomponents\u002FAGENTS.md    ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n│   └── src\u002Futils\u002FAGENTS.md         ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n└── docs\u002FAGENTS.md                  ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n```\n\n## AGENTS.md Template\n\n```markdown\n\u003C!-- Parent: {relative_path_to_parent}\u002FAGENTS.md -->\n\u003C!-- Generated: {timestamp} | Updated: {timestamp} -->\n\n# {Directory Name}\n\n## Purpose\n{One-paragraph description of what this directory contains and its role}\n\n## Key Files\n{List each significant file with a one-line description}\n\n| File | Description |\n|------|-------------|\n| `file.ts` | Brief description of purpose |\n\n## Subdirectories\n{List each subdirectory with brief purpose}\n\n| Directory | Purpose |\n|-----------|---------|\n| `subdir\u002F` | What it contains (see `subdir\u002FAGENTS.md`) |\n\n## For AI Agents\n\n### Working In This Directory\n{Special instructions for AI agents modifying files here}\n\n### Testing Requirements\n{How to test changes in this directory}\n\n### Common Patterns\n{Code patterns or conventions used here}\n\n## Dependencies\n\n### Internal\n{References to other parts of the codebase this depends on}\n\n### External\n{Key external packages\u002Flibraries used}\n\n\u003C!-- MANUAL: Any manually added notes below this line are preserved on regeneration -->\n```\n\n## Execution Workflow\n\n### Step 1: Map Directory Structure\n\n```\nTask(subagent_type=\"explore\", model=\"haiku\",\n  prompt=\"List all directories recursively. Exclude: node_modules, .git, dist, build, __pycache__, .venv, coverage, .next, .nuxt\")\n```\n\n### Step 2: Create Work Plan\n\nGenerate todo items for each directory, organized by depth level:\n\n```\nLevel 0: \u002F (root)\nLevel 1: \u002Fsrc, \u002Fdocs, \u002Ftests\nLevel 2: \u002Fsrc\u002Fcomponents, \u002Fsrc\u002Futils, \u002Fdocs\u002Fapi\n...\n```\n\n### Step 3: Generate Level by Level\n\n**IMPORTANT**: Generate parent levels before child levels to ensure parent references are valid.\n\nFor each directory:\n1. Read all files in the directory\n2. Analyze purpose and relationships\n3. Generate AGENTS.md content\n4. Write file with proper parent reference\n\n### Step 4: Compare and Update (if exists)\n\nWhen AGENTS.md already exists:\n\n1. **Read existing content**\n2. **Identify sections**:\n   - Auto-generated sections (can be updated)\n   - Manual sections (`\u003C!-- MANUAL -->` preserved)\n3. **Compare**:\n   - New files added?\n   - Files removed?\n   - Structure changed?\n4. **Merge**:\n   - Update auto-generated content\n   - Preserve manual annotations\n   - Update timestamp\n\n### Step 5: Validate Hierarchy\n\nAfter generation, run validation checks:\n\n| Check | How to Verify | Corrective Action |\n|-------|--------------|-------------------|\n| Parent references resolve | Read each AGENTS.md, check `\u003C!-- Parent: -->` path exists | Fix path or remove orphan |\n| No orphaned AGENTS.md | Compare AGENTS.md locations to directory structure | Delete orphaned files |\n| Completeness | List all directories, check for AGENTS.md | Generate missing files |\n| Timestamps current | Check `\u003C!-- Generated: -->` dates | Regenerate outdated files |\n\nValidation script pattern:\n```bash\n# Find all AGENTS.md files\nfind . -name \"AGENTS.md\" -type f\n\n# Check parent references\ngrep -r \"\u003C!-- Parent:\" --include=\"AGENTS.md\" .\n```\n\n## Smart Delegation\n\n| Task | Agent |\n|------|-------|\n| Directory mapping | `explore` |\n| File analysis | `architect` |\n| Content generation | `writer` |\n| AGENTS.md writes | `writer` |\n\n## Empty Directory Handling\n\nWhen encountering empty or near-empty directories:\n\n| Condition | Action |\n|-----------|--------|\n| No files, no subdirectories | **Skip** - do not create AGENTS.md |\n| No files, has subdirectories | Create minimal AGENTS.md with subdirectory listing only |\n| Has only generated files (*.min.js, *.map) | Skip or minimal AGENTS.md |\n| Has only config files | Create AGENTS.md describing configuration purpose |\n\nExample minimal AGENTS.md for directory-only containers:\n```markdown\n\u003C!-- Parent: ..\u002FAGENTS.md -->\n# {Directory Name}\n\n## Purpose\nContainer directory for organizing related modules.\n\n## Subdirectories\n| Directory | Purpose |\n|-----------|---------|\n| `subdir\u002F` | Description (see `subdir\u002FAGENTS.md`) |\n```\n\n## Parallelization Rules\n\n1. **Same-level directories**: Process in parallel\n2. **Different levels**: Sequential (parent first)\n3. **Large directories**: Spawn dedicated agent per directory\n4. **Small directories**: Batch multiple into one agent\n\n## Quality Standards\n\n### Must Include\n- [ ] Accurate file descriptions\n- [ ] Correct parent references\n- [ ] Subdirectory links\n- [ ] AI agent instructions\n\n### Must Avoid\n- [ ] Generic boilerplate\n- [ ] Incorrect file names\n- [ ] Broken parent references\n- [ ] Missing important files\n\n## Example Output\n\n### Root AGENTS.md\n```markdown\n\u003C!-- Generated: 2024-01-15 | Updated: 2024-01-15 -->\n\n# my-project\n\n## Purpose\nA web application for managing user tasks with real-time collaboration features.\n\n## Key Files\n| File | Description |\n|------|-------------|\n| `package.json` | Project dependencies and scripts |\n| `tsconfig.json` | TypeScript configuration |\n| `.env.example` | Environment variable template |\n\n## Subdirectories\n| Directory | Purpose |\n|-----------|---------|\n| `src\u002F` | Application source code (see `src\u002FAGENTS.md`) |\n| `docs\u002F` | Documentation (see `docs\u002FAGENTS.md`) |\n| `tests\u002F` | Test suites (see `tests\u002FAGENTS.md`) |\n\n## For AI Agents\n\n### Working In This Directory\n- Always install dependencies after modifying the project manifest\n- Use TypeScript strict mode\n- Follow ESLint rules\n\n### Testing Requirements\n- Run tests before committing\n- Ensure >80% coverage\n\n### Common Patterns\n- Use barrel exports (index.ts)\n- Prefer functional components\n\n## Dependencies\n\n### External\n- React 18.x - UI framework\n- TypeScript 5.x - Type safety\n- Vite - Build tool\n\n\u003C!-- MANUAL: Custom project notes can be added below -->\n```\n\n### Nested AGENTS.md\n```markdown\n\u003C!-- Parent: ..\u002FAGENTS.md -->\n\u003C!-- Generated: 2024-01-15 | Updated: 2024-01-15 -->\n\n# components\n\n## Purpose\nReusable React components organized by feature and complexity.\n\n## Key Files\n| File | Description |\n|------|-------------|\n| `index.ts` | Barrel export for all components |\n| `Button.tsx` | Primary button component |\n| `Modal.tsx` | Modal dialog component |\n\n## Subdirectories\n| Directory | Purpose |\n|-----------|---------|\n| `forms\u002F` | Form-related components (see `forms\u002FAGENTS.md`) |\n| `layout\u002F` | Layout components (see `layout\u002FAGENTS.md`) |\n\n## For AI Agents\n\n### Working In This Directory\n- Each component has its own file\n- Use CSS modules for styling\n- Export via index.ts\n\n### Testing Requirements\n- Unit tests in `__tests__\u002F` subdirectory\n- Use React Testing Library\n\n### Common Patterns\n- Props interfaces defined above component\n- Use forwardRef for DOM-exposing components\n\n## Dependencies\n\n### Internal\n- `src\u002Fhooks\u002F` - Custom hooks used by components\n- `src\u002Futils\u002F` - Utility functions\n\n### External\n- `clsx` - Conditional class names\n- `lucide-react` - Icons\n\n\u003C!-- MANUAL: -->\n```\n\n## Triggering Update Mode\n\nWhen running on an existing codebase with AGENTS.md files:\n\n1. Detect existing files first\n2. Read and parse existing content\n3. Analyze current directory state\n4. Generate diff between existing and current\n5. Apply updates while preserving manual sections\n\n## Performance Considerations\n\n- **Cache directory listings** - Don't re-scan same directories\n- **Batch small directories** - Process multiple at once\n- **Skip unchanged** - If directory hasn't changed, skip regeneration\n- **Parallel writes** - Multiple agents writing different files simultaneously\n","# Deep Init Skill\n\nCreates comprehensive, hierarchical AGENTS.md documentation across the entire codebase.\n\n## Core Concept\n\nAGENTS.md files serve as **AI-readable documentation** that helps agents understand:\n- What each directory contains\n- How components relate to each other\n- Special instructions for working in that area\n- Dependencies and relationships\n\n## Hierarchical Tagging System\n\nEvery AGENTS.md (except root) includes a parent reference tag:\n\n```markdown\n\u003C!-- Parent: ..\u002FAGENTS.md -->\n```\n\nThis creates a navigable hierarchy:\n```\n\u002FAGENTS.md                          ← Root (no parent tag)\n├── src\u002FAGENTS.md                   ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n│   ├── src\u002Fcomponents\u002FAGENTS.md    ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n│   └── src\u002Futils\u002FAGENTS.md         ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n└── docs\u002FAGENTS.md                  ← \u003C!-- Parent: ..\u002FAGENTS.md -->\n```\n\n## AGENTS.md Template\n\n```markdown\n\u003C!-- Parent: {relative_path_to_parent}\u002FAGENTS.md -->\n\u003C!-- Generated: {timestamp} | Updated: {timestamp} -->\n\n# {Directory Name}\n\n## Purpose\n{One-paragraph description of what this directory contains and its role}\n\n## Key Files\n{List each significant file with a one-line description}\n\n| File | Description |\n|------|-------------|\n| `file.ts` | Brief description of purpose |\n\n## Subdirectories\n{List each subdirectory with brief purpose}\n\n| Directory | Purpose |\n|-----------|---------|\n| `subdir\u002F` | What it contains (see `subdir\u002FAGENTS.md`) |\n\n## For AI Agents\n\n### Working In This Directory\n{Special instructions for AI agents modifying files here}\n\n### Testing Requirements\n{How to test changes in this directory}\n\n### Common Patterns\n{Code patterns or conventions used here}\n\n## Dependencies\n\n### Internal\n{References to other parts of the codebase this depends on}\n\n### External\n{Key external packages\u002Flibraries used}\n\n\u003C!-- MANUAL: Any manually added notes below this line are preserved on regeneration -->\n```\n\n## Execution Workflow\n\n### Step 1: Map Directory Structure\n\n```\nTask(subagent_type=\"explore\", model=\"haiku\",\n  prompt=\"List all directories recursively. Exclude: node_modules, .git, dist, build, __pycache__, .venv, coverage, .next, .nuxt\")\n```\n\n### Step 2: Create Work Plan\n\nGenerate todo items for each directory, organized by depth level:\n\n```\nLevel 0: \u002F (root)\nLevel 1: \u002Fsrc, \u002Fdocs, \u002Ftests\nLevel 2: \u002Fsrc\u002Fcomponents, \u002Fsrc\u002Futils, \u002Fdocs\u002Fapi\n...\n```\n\n### Step 3: Generate Level by Level\n\n**IMPORTANT**: Generate parent levels before child levels to ensure parent references are valid.\n\nFor each directory:\n1. Read all files in the directory\n2. Analyze purpose and relationships\n3. Generate AGENTS.md content\n4. Write file with proper parent reference\n\n### Step 4: Compare and Update (if exists)\n\nWhen AGENTS.md already exists:\n\n1. **Read existing content**\n2. **Identify sections**:\n   - Auto-generated sections (can be updated)\n   - Manual sections (`\u003C!-- MANUAL -->` preserved)\n3. **Compare**:\n   - New files added?\n   - Files removed?\n   - Structure changed?\n4. **Merge**:\n   - Update auto-generated content\n   - Preserve manual annotations\n   - Update timestamp\n\n### Step 5: Validate Hierarchy\n\nAfter generation, run validation checks:\n\n| Check | How to Verify | Corrective Action |\n|-------|--------------|-------------------|\n| Parent references resolve | Read each AGENTS.md, check `\u003C!-- Parent: -->` path exists | Fix path or remove orphan |\n| No orphaned AGENTS.md | Compare AGENTS.md locations to directory structure | Delete orphaned files |\n| Completeness | List all directories, check for AGENTS.md | Generate missing files |\n| Timestamps current | Check `\u003C!-- Generated: -->` dates | Regenerate outdated files |\n\nValidation script pattern:\n```bash\n# Find all AGENTS.md files\nfind . -name \"AGENTS.md\" -type f\n\n# Check parent references\ngrep -r \"\u003C!-- Parent:\" --include=\"AGENTS.md\" .\n```\n\n## Smart Delegation\n\n| Task | Agent |\n|------|-------|\n| Directory mapping | `explore` |\n| File analysis | `architect` |\n| Content generation | `writer` |\n| AGENTS.md writes | `writer` |\n\n## Empty Directory Handling\n\nWhen encountering empty or near-empty directories:\n\n| Condition | Action |\n|-----------|--------|\n| No files, no subdirectories | **Skip** - do not create AGENTS.md |\n| No files, has subdirectories | Create minimal AGENTS.md with subdirectory listing only |\n| Has only generated files (*.min.js, *.map) | Skip or minimal AGENTS.md |\n| Has only config files | Create AGENTS.md describing configuration purpose |\n\nExample minimal AGENTS.md for directory-only containers:\n```markdown\n\u003C!-- Parent: ..\u002FAGENTS.md -->\n# {Directory Name}\n\n## Purpose\nContainer directory for organizing related modules.\n\n## Subdirectories\n| Directory | Purpose |\n|-----------|---------|\n| `subdir\u002F` | Description (see `subdir\u002FAGENTS.md`) |\n```\n\n## Parallelization Rules\n\n1. **Same-level directories**: Process in parallel\n2. **Different levels**: Sequential (parent first)\n3. **Large directories**: Spawn dedicated agent per directory\n4. **Small directories**: Batch multiple into one agent\n\n## Quality Standards\n\n### Must Include\n- [ ] Accurate file descriptions\n- [ ] Correct parent references\n- [ ] Subdirectory links\n- [ ] AI agent instructions\n\n### Must Avoid\n- [ ] Generic boilerplate\n- [ ] Incorrect file names\n- [ ] Broken parent references\n- [ ] Missing important files\n\n## Example Output\n\n### Root AGENTS.md\n```markdown\n\u003C!-- Generated: 2024-01-15 | Updated: 2024-01-15 -->\n\n# my-project\n\n## Purpose\nA web application for managing user tasks with real-time collaboration features.\n\n## Key Files\n| File | Description |\n|------|-------------|\n| `package.json` | Project dependencies and scripts |\n| `tsconfig.json` | TypeScript configuration |\n| `.env.example` | Environment variable template |\n\n## Subdirectories\n| Directory | Purpose |\n|-----------|---------|\n| `src\u002F` | Application source code (see `src\u002FAGENTS.md`) |\n| `docs\u002F` | Documentation (see `docs\u002FAGENTS.md`) |\n| `tests\u002F` | Test suites (see `tests\u002FAGENTS.md`) |\n\n## For AI Agents\n\n### Working In This Directory\n- Always install dependencies after modifying the project manifest\n- Use TypeScript strict mode\n- Follow ESLint rules\n\n### Testing Requirements\n- Run tests before committing\n- Ensure >80% coverage\n\n### Common Patterns\n- Use barrel exports (index.ts)\n- Prefer functional components\n\n## Dependencies\n\n### External\n- React 18.x - UI framework\n- TypeScript 5.x - Type safety\n- Vite - Build tool\n\n\u003C!-- MANUAL: Custom project notes can be added below -->\n```\n\n### Nested AGENTS.md\n```markdown\n\u003C!-- Parent: ..\u002FAGENTS.md -->\n\u003C!-- Generated: 2024-01-15 | Updated: 2024-01-15 -->\n\n# components\n\n## Purpose\nReusable React components organized by feature and complexity.\n\n## Key Files\n| File | Description |\n|------|-------------|\n| `index.ts` | Barrel export for all components |\n| `Button.tsx` | Primary button component |\n| `Modal.tsx` | Modal dialog component |\n\n## Subdirectories\n| Directory | Purpose |\n|-----------|---------|\n| `forms\u002F` | Form-related components (see `forms\u002FAGENTS.md`) |\n| `layout\u002F` | Layout components (see `layout\u002FAGENTS.md`) |\n\n## For AI Agents\n\n### Working In This Directory\n- Each component has its own file\n- Use CSS modules for styling\n- Export via index.ts\n\n### Testing Requirements\n- Unit tests in `__tests__\u002F` subdirectory\n- Use React Testing Library\n\n### Common Patterns\n- Props interfaces defined above component\n- Use forwardRef for DOM-exposing components\n\n## Dependencies\n\n### Internal\n- `src\u002Fhooks\u002F` - Custom hooks used by components\n- `src\u002Futils\u002F` - Utility functions\n\n### External\n- `clsx` - Conditional class names\n- `lucide-react` - Icons\n\n\u003C!-- MANUAL: -->\n```\n\n## Triggering Update Mode\n\nWhen running on an existing codebase with AGENTS.md files:\n\n1. Detect existing files first\n2. Read and parse existing content\n3. Analyze current directory state\n4. Generate diff between existing and current\n5. Apply updates while preserving manual sections\n\n## Performance Considerations\n\n- **Cache directory listings** - Don't re-scan same directories\n- **Batch small directories** - Process multiple at once\n- **Skip unchanged** - If directory hasn't changed, skip regeneration\n- **Parallel writes** - Multiple agents writing different files simultaneously\n",{"name":5,"level":29,"description":7},4,"main","92dddf7f6e7b55d1424795ce11586b05dba9d8c8","skills\u002Fdeepinit",3,"https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups","https:\u002F\u002Fgithub.com\u002FCheggin","reaganhsu.com","MTS @datacurve-ai, prev. founding eng @browser-use ","2026-04-24 08:33:47",{"source":8,"skillName":5,"commands":40,"prompt":50,"zipAvailable":51},[41,44,47],{"tool":42,"command":43},"npx","npx skills add Cheggin\u002Frequest-for-startups --skill deepinit",{"tool":45,"command":46},"bunx","bunx skills add Cheggin\u002Frequest-for-startups --skill deepinit",{"tool":48,"command":49},"pnpm","pnpm dlx skills add Cheggin\u002Frequest-for-startups --skill deepinit","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fdeepinit\u002FSKILL.md",true,[],[54,78,98,141,156,179],{"skillNo":55,"name":56,"nameZh":6,"description":57,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":24},"01M6X7PHK069RZH25A3RXN5049","writer-memory","Agentic memory system for writers - track characters, relationships, scenes, and themes","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fwriter-memory\u002FSKILL.md",[],[61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"memory","writer","writer memory","system","characters","track","for","themes","memory system","scenes","relationships","query","export","status","validate","init","agentic",{"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":24},"01M6X7PC3G9228Z323X5YAKTVW","wiki","LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fwiki\u002FSKILL.md",[],[80,85,86,87,88,89,90,91,92,93,94,95,96,72,97],"wiki lint","knowledge","model","llm wiki","markdown","wiki query","knowledge base","lint","sessions","karpathy","add","across","base",{"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":120,"publishedAt":24},"01M6X7P5XFW5C16H3JE4NFQ7MF","website-creation","Build production-quality SaaS websites with opinionated design presets. Use when creating any startup website. The user MUST pick a design style before building. Enforces shadcn\u002Fui, Figma design principles, specific CSS values per style, and anti-AI-writing. Load alongside anti-ai-writing skill. LIGHT MODE ONLY.","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fwebsite-creation\u002FSKILL.md",[104,109,112,117],{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":110,"categoryName":111,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000032","设计师","PROFESSION","适用职业",{"categoryNo":118,"categoryName":119,"taxonomyType":115,"taxonomyTypeDesc":116},"01JBSEEDCAT000000000000036","内容创作者",[121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140],"website creation","website","creation","when","design style","mode","brand-guidelines","full","ui","writing","design principles","only","pick","polish","audit","shadcn","figma","css","Anti-AI","design",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":24},"01M6X7P3PCEAKA2SBETXHHTNBA","visual-verdict","Structured visual QA verdict for screenshot-to-reference comparisons","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[],[148,149,150,67,151,152,153,154,155],"visual verdict","verdict","visual","visual qa","structured","reference","screenshot","qa",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":170,"publishedAt":24},"01M6X7NXEWWC4NFT0ZK1RRSGES","visual-qa-pipeline","Screenshot every page with Playwright, feed to visual QA agent for design evaluation, report results to Slack. Use after every build phase to verify UI matches the chosen design preset. Integrates with the Playwright skill and the website-creation preset system.","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-qa-pipeline\u002FSKILL.md",[162,165,168,169],{"categoryNo":163,"categoryName":164,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000005","邮件与沟通",{"categoryNo":166,"categoryName":167,"taxonomyType":107,"taxonomyTypeDesc":108},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":105,"categoryName":106,"taxonomyType":107,"taxonomyTypeDesc":108},{"categoryNo":113,"categoryName":114,"taxonomyType":115,"taxonomyTypeDesc":116},[150,171,151,155,172,173,100,123,128,174,134,175,129,122,154,67,176,140,177,178],"pipeline","visual qa pipeline","slack","page","Evaluation","review","verify ui","phase",{"skillNo":180,"name":181,"nameZh":6,"description":182,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":183,"categories":184,"keywords":185,"publishedAt":24},"01M6X7NSNW00RQ8J531F52YHV9","verify","Verify that a change really works before you claim completion","https:\u002F\u002Fgithub.com\u002FCheggin\u002Frequest-for-startups\u002Fblob\u002Fmain\u002Fskills\u002Fverify\u002FSKILL.md",[],[181,186,187,188,189,190,171,191,192],"deploy-pipeline","true","you","claim","quality","deploy","change"]