[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6F997VT0BA4PTH4CQWB7MET":3,"skill-same:01M6F997VT0BA4PTH4CQWB7MET":78},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":60,"ownerHtmlUrl":61,"ownerBlogUrl":6,"ownerDescription":62,"updatedAt":63,"install":64,"resources":77},"01M6F997VT0BA4PTH4CQWB7MET","cursor-advanced-composer",null,"Advanced Cursor Composer techniques: agent mode, parallel agents, complex refactoring, and multi-step\norchestration. Triggers on \"advanced composer\", \"composer patterns\", \"multi-file generation\",\n\"composer refactoring\", \"agent mode\", \"parallel agents\".","ComeOnOliver\u002Fskillshub","ComeOnOliver","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F43215937?v=4","01M6E5JNFECJAAVFE0W7SMWWD2","Haoran Shu","01M6E5JNNDQS7AJZDYFQ8TPZCK",66,"MIT","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fjeremylongshore\u002Fclaude-code-plugins-plus-skills\u002Fcursor-advanced-composer\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"cursor advanced composer","advanced","composer","cursor","write","cursor-advanced","io","triggers","patterns","edit","openclaw","read","parallel","refactoring","Bash","saas","parallel agents","file","code","orchestration","2026-11-10 10:12:30",false,"---\nname: \"cursor-advanced-composer\"\ndescription: |\n  Advanced Cursor Composer techniques: agent mode, parallel agents, complex refactoring, and multi-step\n  orchestration. Triggers on \"advanced composer\", \"composer patterns\", \"multi-file generation\",\n  \"composer refactoring\", \"agent mode\", \"parallel agents\".\nallowed-tools: \"Read, Write, Edit, Bash(cmd:*)\"\nversion: 1.0.0\nlicense: MIT\nauthor: \"Jeremy Longshore \u003Cjeremy@intentsolutions.io>\"\ncompatible-with: claude-code, codex, openclaw\ntags: [saas, cursor, cursor-advanced]\n\n---\n# Cursor Advanced Composer\n\nAdvanced patterns for Cursor Composer including agent orchestration, complex multi-file refactoring, architecture migrations, and quality-control workflows.\n\n## Agent Mode Deep Dive\n\nIn Agent mode, Composer autonomously chains tool calls: reading files, searching the codebase, running terminal commands, and writing code. It operates in a loop until the task is complete or it hits the 25-tool-call limit.\n\n### Agent Tool Capabilities\n\n| Tool | What it does | Approval needed? |\n|------|-------------|------------------|\n| Read file | Reads any file in workspace | No |\n| Search codebase | Semantic + text search | No |\n| Write file | Creates or overwrites files | Shows diff first |\n| Edit file | Modifies sections of files | Shows diff first |\n| Run terminal command | Executes shell commands | Yes (click Allow) |\n| List directory | Browses folder structure | No |\n\n### Controlling Agent Behavior\n\nGive the agent constraints in your prompt:\n\n```\nMigrate all React class components in src\u002Fcomponents\u002F to functional\ncomponents with hooks.\n\nConstraints:\n- Do NOT modify test files\n- Preserve all existing prop types\n- Replace lifecycle methods with useEffect equivalents\n- Keep the same file names and export structure\n- Run `npm test` after each file to verify\n```\n\n### Checkpoint Pattern\n\nFor large refactors, use explicit checkpoints:\n\n```\nPhase 1: Create the new database schema types in src\u002Ftypes\u002Fschema-v2.ts.\n         Show me the types before proceeding.\n\nPhase 2: Update the repository layer to use the new types.\n         Run tests after each repository file change.\n\nPhase 3: Update the API routes to use the new repository methods.\n\nPhase 4: Update the frontend components to match the new API response shapes.\n\nStop after each phase and show me a summary of changes.\n```\n\nThe agent pauses after 25 tool calls automatically. Click \"Continue\" to allow more.\n\n## Parallel Agent Workflows\n\nRun up to 8 Composer agents simultaneously, each in its own tab.\n\n### Use Case: Parallel Feature Development\n\n```\n# Agent 1 (Tab: \"Auth\")\nImplement JWT authentication:\n- src\u002Fmiddleware\u002Fauth.ts\n- src\u002Fservices\u002Ftoken.service.ts\n- src\u002Fapi\u002Fauth\u002Flogin\u002Froute.ts\n- src\u002Fapi\u002Fauth\u002Frefresh\u002Froute.ts\n\n# Agent 2 (Tab: \"Products\")\nImplement product catalog:\n- prisma\u002Fschema additions\n- src\u002Fapi\u002Fproducts\u002Froute.ts\n- src\u002Fservices\u002Fproduct.service.ts\n\n# Agent 3 (Tab: \"Tests\")\nWrite integration tests for the existing user API:\n- tests\u002Fintegration\u002Fusers.test.ts\n```\n\nEach agent has its own context and conversation history. They can modify the same codebase simultaneously, but be careful with overlapping files.\n\n### Conflict Resolution Between Agents\n\nIf two agents modify the same file, the second write overwrites the first. Mitigate this by:\n- Assigning non-overlapping file scopes to each agent\n- Running agents sequentially for shared files\n- Using git to cherry-pick the best changes\n\n## Complex Refactoring Patterns\n\n### Pattern: Extract and Replace\n\nExtract a pattern into a shared utility, then replace all occurrences:\n\n```\n@src\u002Fapi\u002F\n\nI see repeated error handling in every API route:\ntry { ... } catch (err) { if (err instanceof ZodError) ... }\n\nStep 1: Create src\u002Futils\u002Fapi-handler.ts with a withValidation()\nwrapper that handles the try\u002Fcatch + Zod pattern.\n\nStep 2: Update ALL route files in src\u002Fapi\u002F to use withValidation()\ninstead of manual try\u002Fcatch.\n\nShow me api-handler.ts first, then refactor the routes.\n```\n\n### Pattern: Interface-First Migration\n\nDefine the target interface, then migrate implementations:\n\n```\n@src\u002Fservices\u002F\n\nStep 1: Create src\u002Finterfaces\u002Frepository.ts with a generic\nRepository\u003CT> interface:\n  - findById(id: string): Promise\u003CT | null>\n  - findMany(filter: Filter\u003CT>): Promise\u003CT[]>\n  - create(data: CreateInput\u003CT>): Promise\u003CT>\n  - update(id: string, data: UpdateInput\u003CT>): Promise\u003CT>\n  - delete(id: string): Promise\u003Cvoid>\n\nStep 2: Refactor UserService to implement Repository\u003CUser>.\nStep 3: Refactor ProductService to implement Repository\u003CProduct>.\nStep 4: Update API routes to use the Repository interface type.\n```\n\n### Pattern: Test-Driven Refactoring\n\nWrite tests first, then refactor with confidence:\n\n```\n@src\u002Fservices\u002Fpayment.service.ts\n\nStep 1: Write comprehensive tests for the current PaymentService\nbehavior. Cover all public methods and edge cases.\nRun `npm test` to verify they pass.\n\nStep 2: Refactor PaymentService to use the Strategy pattern for\ndifferent payment providers (Stripe, PayPal, manual).\nRun `npm test` after each change to ensure nothing breaks.\n```\n\n## Multi-Codebase Orchestration\n\nFor monorepos or multi-root workspaces:\n\n```\n@packages\u002Fshared\u002Fsrc\u002Ftypes\u002F\n@packages\u002Fapi\u002Fsrc\u002Froutes\u002F\n@packages\u002Fweb\u002Fsrc\u002Fhooks\u002F\n\nAdd a \"notifications\" feature across all packages:\n1. shared: NotificationType enum, Notification interface\n2. api: GET \u002Fnotifications, POST \u002Fnotifications\u002Fmark-read endpoints\n3. web: useNotifications hook, NotificationBell component\n\nUse the shared types in both api and web packages.\nImport from @myorg\u002Fshared (the workspace alias).\n```\n\n## Quality Control Workflows\n\n### Pre-Apply Review Checklist\n\nBefore clicking \"Apply All\":\n\n1. **Read every diff** -- do not blindly apply multi-file changes\n2. **Check imports** -- Composer sometimes generates wrong import paths\n3. **Verify types** -- ensure type annotations are correct, not `any`\n4. **Look for hallucinations** -- methods or modules that do not exist\n5. **Run build** -- `Cmd+`` > run your build command after applying\n\n### Post-Apply Validation\n\n```\n# In Composer or terminal:\nnpm run build       # Catches import errors, type mismatches\nnpm run lint        # Catches style violations\nnpm run test        # Catches behavior regressions\n```\n\n### Rollback Strategy\n\nIf applied changes break the build:\n\n```bash\n# Undo all uncommitted changes\ngit checkout .\n\n# Or selectively undo specific files\ngit checkout -- src\u002Fapi\u002Fproducts\u002Froute.ts\n```\n\nAlways commit working code before starting a Composer session.\n\n## Advanced Prompting Techniques\n\n### System-Level Instructions via Rules\n\nCreate a Composer-specific rule:\n\n```yaml\n# .cursor\u002Frules\u002Fcomposer-standards.mdc\n---\ndescription: \"Standards for Composer-generated code\"\nglobs: \"\"\nalwaysApply: true\n---\nWhen generating code via Composer:\n- Always include JSDoc comments on exported functions\n- Always add error handling (never let functions throw unhandled)\n- Generate corresponding test files for new modules\n- Use named exports, never default exports\n- Import types with `import type` syntax\n```\n\n### Iterative Refinement\n\nAfter first pass:\n```\nThe generated product.service.ts looks good but:\n1. Add pagination support to findMany (page, limit params)\n2. Add a findByCategory method\n3. Use transactions for createWithItems\n```\n\nComposer retains conversation context, so follow-up instructions build on previous output.\n\n## Enterprise Considerations\n\n- **Compliance**: Review generated code for license compliance before committing\n- **Security**: Composer may generate code with SQL injection or XSS vulnerabilities -- always audit\n- **Cost**: Agent mode with reasoning models (o1, Opus) can consume thousands of tokens per session\n- **Audit trail**: Commit Composer output with descriptive messages for code review traceability\n\n## Resources\n\n- [Composer Overview](https:\u002F\u002Fdocs.cursor.com\u002Fcomposer\u002Foverview)\n- [Agent Mode Documentation](https:\u002F\u002Fdocs.cursor.com\u002Fagent)\n- [Cursor 2.0 Agent Architecture](https:\u002F\u002Fcursor.com\u002Fblog)\n\n","# Cursor Advanced Composer\n\nAdvanced patterns for Cursor Composer including agent orchestration, complex multi-file refactoring, architecture migrations, and quality-control workflows.\n\n## Agent Mode Deep Dive\n\nIn Agent mode, Composer autonomously chains tool calls: reading files, searching the codebase, running terminal commands, and writing code. It operates in a loop until the task is complete or it hits the 25-tool-call limit.\n\n### Agent Tool Capabilities\n\n| Tool | What it does | Approval needed? |\n|------|-------------|------------------|\n| Read file | Reads any file in workspace | No |\n| Search codebase | Semantic + text search | No |\n| Write file | Creates or overwrites files | Shows diff first |\n| Edit file | Modifies sections of files | Shows diff first |\n| Run terminal command | Executes shell commands | Yes (click Allow) |\n| List directory | Browses folder structure | No |\n\n### Controlling Agent Behavior\n\nGive the agent constraints in your prompt:\n\n```\nMigrate all React class components in src\u002Fcomponents\u002F to functional\ncomponents with hooks.\n\nConstraints:\n- Do NOT modify test files\n- Preserve all existing prop types\n- Replace lifecycle methods with useEffect equivalents\n- Keep the same file names and export structure\n- Run `npm test` after each file to verify\n```\n\n### Checkpoint Pattern\n\nFor large refactors, use explicit checkpoints:\n\n```\nPhase 1: Create the new database schema types in src\u002Ftypes\u002Fschema-v2.ts.\n         Show me the types before proceeding.\n\nPhase 2: Update the repository layer to use the new types.\n         Run tests after each repository file change.\n\nPhase 3: Update the API routes to use the new repository methods.\n\nPhase 4: Update the frontend components to match the new API response shapes.\n\nStop after each phase and show me a summary of changes.\n```\n\nThe agent pauses after 25 tool calls automatically. Click \"Continue\" to allow more.\n\n## Parallel Agent Workflows\n\nRun up to 8 Composer agents simultaneously, each in its own tab.\n\n### Use Case: Parallel Feature Development\n\n```\n# Agent 1 (Tab: \"Auth\")\nImplement JWT authentication:\n- src\u002Fmiddleware\u002Fauth.ts\n- src\u002Fservices\u002Ftoken.service.ts\n- src\u002Fapi\u002Fauth\u002Flogin\u002Froute.ts\n- src\u002Fapi\u002Fauth\u002Frefresh\u002Froute.ts\n\n# Agent 2 (Tab: \"Products\")\nImplement product catalog:\n- prisma\u002Fschema additions\n- src\u002Fapi\u002Fproducts\u002Froute.ts\n- src\u002Fservices\u002Fproduct.service.ts\n\n# Agent 3 (Tab: \"Tests\")\nWrite integration tests for the existing user API:\n- tests\u002Fintegration\u002Fusers.test.ts\n```\n\nEach agent has its own context and conversation history. They can modify the same codebase simultaneously, but be careful with overlapping files.\n\n### Conflict Resolution Between Agents\n\nIf two agents modify the same file, the second write overwrites the first. Mitigate this by:\n- Assigning non-overlapping file scopes to each agent\n- Running agents sequentially for shared files\n- Using git to cherry-pick the best changes\n\n## Complex Refactoring Patterns\n\n### Pattern: Extract and Replace\n\nExtract a pattern into a shared utility, then replace all occurrences:\n\n```\n@src\u002Fapi\u002F\n\nI see repeated error handling in every API route:\ntry { ... } catch (err) { if (err instanceof ZodError) ... }\n\nStep 1: Create src\u002Futils\u002Fapi-handler.ts with a withValidation()\nwrapper that handles the try\u002Fcatch + Zod pattern.\n\nStep 2: Update ALL route files in src\u002Fapi\u002F to use withValidation()\ninstead of manual try\u002Fcatch.\n\nShow me api-handler.ts first, then refactor the routes.\n```\n\n### Pattern: Interface-First Migration\n\nDefine the target interface, then migrate implementations:\n\n```\n@src\u002Fservices\u002F\n\nStep 1: Create src\u002Finterfaces\u002Frepository.ts with a generic\nRepository\u003CT> interface:\n  - findById(id: string): Promise\u003CT | null>\n  - findMany(filter: Filter\u003CT>): Promise\u003CT[]>\n  - create(data: CreateInput\u003CT>): Promise\u003CT>\n  - update(id: string, data: UpdateInput\u003CT>): Promise\u003CT>\n  - delete(id: string): Promise\u003Cvoid>\n\nStep 2: Refactor UserService to implement Repository\u003CUser>.\nStep 3: Refactor ProductService to implement Repository\u003CProduct>.\nStep 4: Update API routes to use the Repository interface type.\n```\n\n### Pattern: Test-Driven Refactoring\n\nWrite tests first, then refactor with confidence:\n\n```\n@src\u002Fservices\u002Fpayment.service.ts\n\nStep 1: Write comprehensive tests for the current PaymentService\nbehavior. Cover all public methods and edge cases.\nRun `npm test` to verify they pass.\n\nStep 2: Refactor PaymentService to use the Strategy pattern for\ndifferent payment providers (Stripe, PayPal, manual).\nRun `npm test` after each change to ensure nothing breaks.\n```\n\n## Multi-Codebase Orchestration\n\nFor monorepos or multi-root workspaces:\n\n```\n@packages\u002Fshared\u002Fsrc\u002Ftypes\u002F\n@packages\u002Fapi\u002Fsrc\u002Froutes\u002F\n@packages\u002Fweb\u002Fsrc\u002Fhooks\u002F\n\nAdd a \"notifications\" feature across all packages:\n1. shared: NotificationType enum, Notification interface\n2. api: GET \u002Fnotifications, POST \u002Fnotifications\u002Fmark-read endpoints\n3. web: useNotifications hook, NotificationBell component\n\nUse the shared types in both api and web packages.\nImport from @myorg\u002Fshared (the workspace alias).\n```\n\n## Quality Control Workflows\n\n### Pre-Apply Review Checklist\n\nBefore clicking \"Apply All\":\n\n1. **Read every diff** -- do not blindly apply multi-file changes\n2. **Check imports** -- Composer sometimes generates wrong import paths\n3. **Verify types** -- ensure type annotations are correct, not `any`\n4. **Look for hallucinations** -- methods or modules that do not exist\n5. **Run build** -- `Cmd+`` > run your build command after applying\n\n### Post-Apply Validation\n\n```\n# In Composer or terminal:\nnpm run build       # Catches import errors, type mismatches\nnpm run lint        # Catches style violations\nnpm run test        # Catches behavior regressions\n```\n\n### Rollback Strategy\n\nIf applied changes break the build:\n\n```bash\n# Undo all uncommitted changes\ngit checkout .\n\n# Or selectively undo specific files\ngit checkout -- src\u002Fapi\u002Fproducts\u002Froute.ts\n```\n\nAlways commit working code before starting a Composer session.\n\n## Advanced Prompting Techniques\n\n### System-Level Instructions via Rules\n\nCreate a Composer-specific rule:\n\n```yaml\n# .cursor\u002Frules\u002Fcomposer-standards.mdc\n---\ndescription: \"Standards for Composer-generated code\"\nglobs: \"\"\nalwaysApply: true\n---\nWhen generating code via Composer:\n- Always include JSDoc comments on exported functions\n- Always add error handling (never let functions throw unhandled)\n- Generate corresponding test files for new modules\n- Use named exports, never default exports\n- Import types with `import type` syntax\n```\n\n### Iterative Refinement\n\nAfter first pass:\n```\nThe generated product.service.ts looks good but:\n1. Add pagination support to findMany (page, limit params)\n2. Add a findByCategory method\n3. Use transactions for createWithItems\n```\n\nComposer retains conversation context, so follow-up instructions build on previous output.\n\n## Enterprise Considerations\n\n- **Compliance**: Review generated code for license compliance before committing\n- **Security**: Composer may generate code with SQL injection or XSS vulnerabilities -- always audit\n- **Cost**: Agent mode with reasoning models (o1, Opus) can consume thousands of tokens per session\n- **Audit trail**: Commit Composer output with descriptive messages for code review traceability\n\n## Resources\n\n- [Composer Overview](https:\u002F\u002Fdocs.cursor.com\u002Fcomposer\u002Foverview)\n- [Agent Mode Documentation](https:\u002F\u002Fdocs.cursor.com\u002Fagent)\n- [Cursor 2.0 Agent Architecture](https:\u002F\u002Fcursor.com\u002Fblog)\n\n",{"name":5,"tags":49,"author":50,"license":15,"version":51,"description":52,"allowed-tools":53,"compatible-with":54},[39,27,29],"Jeremy Longshore \u003Cjeremy@intentsolutions.io>","1.0.0","Advanced Cursor Composer techniques: agent mode, parallel agents, complex refactoring, and multi-step\norchestration. Triggers on \"advanced composer\", \"composer patterns\", \"multi-file generation\",\n\"composer refactoring\", \"agent mode\", \"parallel agents\".\n","Read, Write, Edit, Bash(cmd:*)","claude-code, codex, openclaw","main","def8531e65114c0fca8fb8551c1871ee0eed705c","skills\u002Fjeremylongshore\u002Fclaude-code-plugins-plus-skills\u002Fcursor-advanced-composer",24,"https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub","https:\u002F\u002Fskillshub.wtf","https:\u002F\u002Fgithub.com\u002FComeOnOliver","AI & Blockchain Engineer\r\n","2026-06-24 22:07:19",{"source":8,"skillName":5,"commands":65,"prompt":75,"zipAvailable":76},[66,69,72],{"tool":67,"command":68},"npx","npx skills add ComeOnOliver\u002Fskillshub --skill cursor-advanced-composer",{"tool":70,"command":71},"bunx","bunx skills add ComeOnOliver\u002Fskillshub --skill cursor-advanced-composer",{"tool":73,"command":74},"pnpm","pnpm dlx skills add ComeOnOliver\u002Fskillshub --skill cursor-advanced-composer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fjeremylongshore\u002Fclaude-code-plugins-plus-skills\u002Fcursor-advanced-composer\u002FSKILL.md",true,[],[79,89,99,108,114,121],{"skillNo":80,"name":81,"nameZh":6,"description":6,"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":85,"publishedAt":44},"01M6FKJN13GMG4KY57J3QD8GY5","model-hierarchy-skill","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzscole\u002Fmodel-hierarchy-skill\u002Fmodel-hierarchy-skill\u002FSKILL.md",[84],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[86,87,88],"model","model hierarchy","model hierarchy skill",{"skillNo":90,"name":91,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":95,"publishedAt":44},"01M6FKJJJ6GCAMR4PPPRD12M5X","zoom-mcp","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-mcp\u002FSKILL.md",[94],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[96,97,98],"MCP","zoom","zoom mcp",{"skillNo":100,"name":101,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":44},"01M6FKJE3KYT3KPEZMEEHYKA6K","zoom-apps-sdk","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fzoom-apps-sdk\u002FSKILL.md",[],[105,106,107,97],"sdk","zoom apps sdk","apps",{"skillNo":109,"name":110,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":44},"01M6FKJ9EDH9Q5VWDF8HAJRSP0","windows","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwindows\u002FSKILL.md",[],[110],{"skillNo":115,"name":116,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":117,"categories":118,"keywords":120,"publishedAt":44},"01M6FKJ666BEEFC3AE9GJ72Q93","whiteboard","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwhiteboard\u002FSKILL.md",[119],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[116],{"skillNo":122,"name":123,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":44},"01M6FKJ21WFCDGTJQ2Q91T9DVW","websockets","https:\u002F\u002Fgithub.com\u002FComeOnOliver\u002Fskillshub\u002Fblob\u002Fmain\u002Fskills\u002Fzoom\u002Fskills\u002Fwebsockets\u002FSKILL.md",[],[123]]