[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C8QNEM1FCVNQRFYW99VC8M":3,"skill-same:01M7C8QNEM1FCVNQRFYW99VC8M":51},{"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":28,"commitSha":29,"skillDirectory":30,"forksCount":31,"repositoryHtmlUrl":32,"repositoryHomepageUrl":33,"ownerHtmlUrl":34,"ownerBlogUrl":6,"ownerDescription":35,"updatedAt":36,"install":37,"resources":50},"01M7C8QNEM1FCVNQRFYW99VC8M","codebase-audit-pre-push",null,"Deep audit before GitHub push: removes junk files, dead code, security holes, and optimization issues. Checks every file line-by-line for production readiness.","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-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcodebase-audit-pre-push\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: codebase-audit-pre-push\ndescription: \"Deep audit before GitHub push: removes junk files, dead code, security holes, and optimization issues. Checks every file line-by-line for production readiness.\"\ncategory: development\nrisk: safe\nsource: community\ndate_added: \"2026-03-05\"\n---\n\n# Pre-Push Codebase Audit\n\nAs a senior engineer, you're doing the final review before pushing this code to GitHub. Check everything carefully and fix problems as you find them.  \n\n## When to Use This Skill  \n\n- User requests \"audit the codebase\" or \"review before push\"  \n- Before making the first push to GitHub  \n- Before making a repository public  \n- Pre-production deployment review  \n- User asks to \"clean up the code\" or \"optimize everything\"  \n\n## Your Job  \n\nReview the entire codebase file by file. Read the code carefully. Fix issues right away. Don't just note problems—make the necessary changes.  \n\n## Audit Process  \n\n### 1. Clean Up Junk Files  \n\nStart by looking for files that shouldn't be on GitHub:  \n\n**Delete these immediately:**  \n- OS files: `.DS_Store`, `Thumbs.db`, `desktop.ini`  \n- Logs: `*.log`, `npm-debug.log*`, `yarn-error.log*`  \n- Temp files: `*.tmp`, `*.temp`, `*.cache`, `*.swp`  \n- Build output: `dist\u002F`, `build\u002F`, `.next\u002F`, `out\u002F`, `.cache\u002F`  \n- Dependencies: `node_modules\u002F`, `vendor\u002F`, `__pycache__\u002F`, `*.pyc`  \n- IDE files: `.idea\u002F`, `.vscode\u002F` (ask user first), `*.iml`, `.project`  \n- Backup files: `*.bak`, `*_old.*`, `*_backup.*`, `*_copy.*`  \n- Test artifacts: `coverage\u002F`, `.nyc_output\u002F`, `test-results\u002F`  \n- Personal junk: `TODO.txt`, `NOTES.txt`, `scratch.*`, `test123.*`  \n\n**Critical - Check for secrets:**  \n- `.env` files (should never be committed)  \n- Files containing: `password`, `api_key`, `token`, `secret`, `private_key`  \n- `*.pem`, `*.key`, `*.cert`, `credentials.json`, `serviceAccountKey.json`  \n\nIf you find secrets in the code, mark it as a CRITICAL BLOCKER.  \n\n### 2. Fix .gitignore  \n\nCheck if the `.gitignore` file exists and is thorough. If it’s missing or not complete, update it to include all junk file patterns above. Ensure that `.env.example` exists with keys but no values.  \n\n### 3. Audit Every Source File  \n\nLook through each code file and check:  \n\n**Dead Code (remove immediately):**  \n- Commented-out code blocks  \n- Unused imports\u002Frequires  \n- Unused variables (declared but never used)  \n- Unused functions (defined but never called)  \n- Unreachable code (after `return`, inside `if (false)`)  \n- Duplicate logic (same code in multiple places—combine)  \n\n**Code Quality (fix issues as you go):**  \n- Vague names: `data`, `info`, `temp`, `thing` → rename to be descriptive  \n- Magic numbers: `if (status === 3)` → extract to named constant  \n- Debug statements: remove `console.log`, `print()`, `debugger`  \n- TODO\u002FFIXME comments: either resolve them or delete them  \n- TypeScript `any`: add proper types or explain why `any` is used  \n- Use `===` instead of `==` in JavaScript  \n- Functions longer than 50 lines: consider splitting  \n- Nested code greater than 3 levels: refactor with early returns  \n\n**Logic Issues (critical):**  \n- Missing null\u002Fundefined checks  \n- Array operations on potentially empty arrays  \n- Async functions that are not awaited  \n- Promises without `.catch()` or try\u002Fcatch  \n- Possibilities for infinite loops  \n- Missing `default` in switch statements  \n\n### 4. Security Check (Zero Tolerance)  \n\n**Secrets:** Search for hardcoded passwords, API keys, and tokens. They must be in environment variables.  \n\n**Injection vulnerabilities:**  \n- SQL: No string concatenation in queries—use parameterized queries only  \n- Command injection: No `exec()` with user-provided input  \n- Path traversal: No file paths from user input without validation  \n- XSS: No `innerHTML` or `dangerouslySetInnerHTML` with user data  \n\n**Auth\u002FAuthorization:**  \n- Passwords hashed with bcrypt\u002Fargon2 (never MD5 or plain text)  \n- Protected routes check for authentication  \n- Authorization checks on the server side, not just in the UI  \n- No IDOR: verify users own the resources they are accessing  \n\n**Data exposure:**  \n- API responses do not leak unnecessary information  \n- Error messages do not expose stack traces or database details  \n- Pagination is present on list endpoints  \n\n**Dependencies:**  \n- Run `npm audit` or an equivalent tool  \n- Flag critically outdated or vulnerable packages  \n\n### 5. Scalability Check  \n\n**Database:**  \n- N+1 queries: loops with database calls inside → use JOINs or batch queries  \n- Missing indexes on WHERE\u002FORDER BY columns  \n- Unbounded queries: add LIMIT or pagination  \n- Avoid `SELECT *`: specify columns  \n\n**API Design:**  \n- Heavy operations (like email, reports, file processing) → move to a background queue  \n- Rate limiting on public endpoints  \n- Caching for data that is read frequently  \n- Timeouts on external calls  \n\n**Code:**  \n- No global mutable state  \n- Clean up event listeners (to avoid memory leaks)  \n- Stream large files instead of loading them into memory  \n\n### 6. Architecture Check  \n\n**Organization:**  \n- Clear folder structure  \n- Files are in logical locations  \n- No \"misc\" or \"stuff\" folders  \n\n**Separation of concerns:**  \n- UI layer: only responsible for rendering  \n- Business logic: pure functions  \n- Data layer: isolated database queries  \n- No 500+ line \"god files\"  \n\n**Reusability:**  \n- Duplicate code → extract to shared utilities  \n- Constants defined once and imported  \n- Types\u002Finterfaces reused, not redefined  \n\n### 7. Performance  \n\n**Backend:**  \n- Expensive operations do not block requests  \n- Batch database calls when possible  \n- Set cache headers correctly  \n\n**Frontend (if applicable):**  \n- Implement code splitting  \n- Optimize images  \n- Avoid massive dependencies for small utilities  \n- Use lazy loading for heavy components  \n\n### 8. Documentation  \n\n**README.md must include:**  \n- Description of what the project does  \n- Instructions for installation and execution  \n- Required environment variables  \n- Guidance on running tests  \n\n**Code comments:**  \n- Explain WHY, not WHAT  \n- Provide explanations for complex logic  \n- Avoid comments that merely repeat the code  \n\n### 9. Testing  \n\n- Critical paths should have tests (auth, payments, core features)  \n- No `test.only` or `fdescribe` should remain in the code  \n- Avoid `test.skip` without an explanation  \n- Tests should verify behavior, not implementation details  \n\n### 10. Final Verification  \n\nAfter making all changes, run the app. Ensure nothing is broken. Check that:  \n- The app starts without errors  \n- Main features work  \n- Tests pass (if they exist)  \n- No regressions have been introduced  \n\n## Output Format  \n\nAfter auditing, provide a report:  \n\n```\nCODEBASE AUDIT COMPLETE  \n\nFILES REMOVED:  \n- node_modules\u002F (build artifact)  \n- .env (contained secrets)  \n- old_backup.js (unused duplicate)  \n\nCODE CHANGES:  \n[src\u002Fapi\u002Fusers.js]  \n  ✂ Removed unused import: lodash  \n  ✂ Removed dead function: formatOldWay()  \n  🔧 Renamed 'data' → 'userData' for clarity  \n  🛡 Added try\u002Fcatch around API call (line 47)  \n\n[src\u002Fdb\u002Fqueries.js]  \n  ⚡ Fixed N+1 query: now uses JOIN instead of loop  \n\nSECURITY ISSUES:  \n🚨 CRITICAL: Hardcoded API key in config.js (line 12) → moved to .env  \n⚠️ HIGH: SQL injection risk in search.js (line 34) → fixed with parameterized query  \n\nSCALABILITY:  \n⚡ Added pagination to \u002Fapi\u002Fusers endpoint  \n⚡ Added index on users.email column  \n\nFINAL STATUS:  \n✅ CLEAN - Ready to push to GitHub  \n\nScores:  \nSecurity: 9\u002F10 (one minor header missing)  \nCode Quality: 10\u002F10  \nScalability: 9\u002F10  \nOverall: 9\u002F10  \n```  \n\n## Key Principles  \n\n- Read the code thoroughly, don't skim  \n- Fix issues immediately, don’t just document them  \n- If uncertain about removing something, ask the user  \n- Test after making changes  \n- Be thorough but practical—focus on real problems  \n- Security issues are blockers—nothing should ship with critical vulnerabilities  \n\n## Related Skills  \n\n- `@security-auditor` - Deeper security review  \n- `@systematic-debugging` - Investigate specific issues  \n- `@git-pushing` - Push code after audit\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n","# Pre-Push Codebase Audit\n\nAs a senior engineer, you're doing the final review before pushing this code to GitHub. Check everything carefully and fix problems as you find them.  \n\n## When to Use This Skill  \n\n- User requests \"audit the codebase\" or \"review before push\"  \n- Before making the first push to GitHub  \n- Before making a repository public  \n- Pre-production deployment review  \n- User asks to \"clean up the code\" or \"optimize everything\"  \n\n## Your Job  \n\nReview the entire codebase file by file. Read the code carefully. Fix issues right away. Don't just note problems—make the necessary changes.  \n\n## Audit Process  \n\n### 1. Clean Up Junk Files  \n\nStart by looking for files that shouldn't be on GitHub:  \n\n**Delete these immediately:**  \n- OS files: `.DS_Store`, `Thumbs.db`, `desktop.ini`  \n- Logs: `*.log`, `npm-debug.log*`, `yarn-error.log*`  \n- Temp files: `*.tmp`, `*.temp`, `*.cache`, `*.swp`  \n- Build output: `dist\u002F`, `build\u002F`, `.next\u002F`, `out\u002F`, `.cache\u002F`  \n- Dependencies: `node_modules\u002F`, `vendor\u002F`, `__pycache__\u002F`, `*.pyc`  \n- IDE files: `.idea\u002F`, `.vscode\u002F` (ask user first), `*.iml`, `.project`  \n- Backup files: `*.bak`, `*_old.*`, `*_backup.*`, `*_copy.*`  \n- Test artifacts: `coverage\u002F`, `.nyc_output\u002F`, `test-results\u002F`  \n- Personal junk: `TODO.txt`, `NOTES.txt`, `scratch.*`, `test123.*`  \n\n**Critical - Check for secrets:**  \n- `.env` files (should never be committed)  \n- Files containing: `password`, `api_key`, `token`, `secret`, `private_key`  \n- `*.pem`, `*.key`, `*.cert`, `credentials.json`, `serviceAccountKey.json`  \n\nIf you find secrets in the code, mark it as a CRITICAL BLOCKER.  \n\n### 2. Fix .gitignore  \n\nCheck if the `.gitignore` file exists and is thorough. If it’s missing or not complete, update it to include all junk file patterns above. Ensure that `.env.example` exists with keys but no values.  \n\n### 3. Audit Every Source File  \n\nLook through each code file and check:  \n\n**Dead Code (remove immediately):**  \n- Commented-out code blocks  \n- Unused imports\u002Frequires  \n- Unused variables (declared but never used)  \n- Unused functions (defined but never called)  \n- Unreachable code (after `return`, inside `if (false)`)  \n- Duplicate logic (same code in multiple places—combine)  \n\n**Code Quality (fix issues as you go):**  \n- Vague names: `data`, `info`, `temp`, `thing` → rename to be descriptive  \n- Magic numbers: `if (status === 3)` → extract to named constant  \n- Debug statements: remove `console.log`, `print()`, `debugger`  \n- TODO\u002FFIXME comments: either resolve them or delete them  \n- TypeScript `any`: add proper types or explain why `any` is used  \n- Use `===` instead of `==` in JavaScript  \n- Functions longer than 50 lines: consider splitting  \n- Nested code greater than 3 levels: refactor with early returns  \n\n**Logic Issues (critical):**  \n- Missing null\u002Fundefined checks  \n- Array operations on potentially empty arrays  \n- Async functions that are not awaited  \n- Promises without `.catch()` or try\u002Fcatch  \n- Possibilities for infinite loops  \n- Missing `default` in switch statements  \n\n### 4. Security Check (Zero Tolerance)  \n\n**Secrets:** Search for hardcoded passwords, API keys, and tokens. They must be in environment variables.  \n\n**Injection vulnerabilities:**  \n- SQL: No string concatenation in queries—use parameterized queries only  \n- Command injection: No `exec()` with user-provided input  \n- Path traversal: No file paths from user input without validation  \n- XSS: No `innerHTML` or `dangerouslySetInnerHTML` with user data  \n\n**Auth\u002FAuthorization:**  \n- Passwords hashed with bcrypt\u002Fargon2 (never MD5 or plain text)  \n- Protected routes check for authentication  \n- Authorization checks on the server side, not just in the UI  \n- No IDOR: verify users own the resources they are accessing  \n\n**Data exposure:**  \n- API responses do not leak unnecessary information  \n- Error messages do not expose stack traces or database details  \n- Pagination is present on list endpoints  \n\n**Dependencies:**  \n- Run `npm audit` or an equivalent tool  \n- Flag critically outdated or vulnerable packages  \n\n### 5. Scalability Check  \n\n**Database:**  \n- N+1 queries: loops with database calls inside → use JOINs or batch queries  \n- Missing indexes on WHERE\u002FORDER BY columns  \n- Unbounded queries: add LIMIT or pagination  \n- Avoid `SELECT *`: specify columns  \n\n**API Design:**  \n- Heavy operations (like email, reports, file processing) → move to a background queue  \n- Rate limiting on public endpoints  \n- Caching for data that is read frequently  \n- Timeouts on external calls  \n\n**Code:**  \n- No global mutable state  \n- Clean up event listeners (to avoid memory leaks)  \n- Stream large files instead of loading them into memory  \n\n### 6. Architecture Check  \n\n**Organization:**  \n- Clear folder structure  \n- Files are in logical locations  \n- No \"misc\" or \"stuff\" folders  \n\n**Separation of concerns:**  \n- UI layer: only responsible for rendering  \n- Business logic: pure functions  \n- Data layer: isolated database queries  \n- No 500+ line \"god files\"  \n\n**Reusability:**  \n- Duplicate code → extract to shared utilities  \n- Constants defined once and imported  \n- Types\u002Finterfaces reused, not redefined  \n\n### 7. Performance  \n\n**Backend:**  \n- Expensive operations do not block requests  \n- Batch database calls when possible  \n- Set cache headers correctly  \n\n**Frontend (if applicable):**  \n- Implement code splitting  \n- Optimize images  \n- Avoid massive dependencies for small utilities  \n- Use lazy loading for heavy components  \n\n### 8. Documentation  \n\n**README.md must include:**  \n- Description of what the project does  \n- Instructions for installation and execution  \n- Required environment variables  \n- Guidance on running tests  \n\n**Code comments:**  \n- Explain WHY, not WHAT  \n- Provide explanations for complex logic  \n- Avoid comments that merely repeat the code  \n\n### 9. Testing  \n\n- Critical paths should have tests (auth, payments, core features)  \n- No `test.only` or `fdescribe` should remain in the code  \n- Avoid `test.skip` without an explanation  \n- Tests should verify behavior, not implementation details  \n\n### 10. Final Verification  \n\nAfter making all changes, run the app. Ensure nothing is broken. Check that:  \n- The app starts without errors  \n- Main features work  \n- Tests pass (if they exist)  \n- No regressions have been introduced  \n\n## Output Format  \n\nAfter auditing, provide a report:  \n\n```\nCODEBASE AUDIT COMPLETE  \n\nFILES REMOVED:  \n- node_modules\u002F (build artifact)  \n- .env (contained secrets)  \n- old_backup.js (unused duplicate)  \n\nCODE CHANGES:  \n[src\u002Fapi\u002Fusers.js]  \n  ✂ Removed unused import: lodash  \n  ✂ Removed dead function: formatOldWay()  \n  🔧 Renamed 'data' → 'userData' for clarity  \n  🛡 Added try\u002Fcatch around API call (line 47)  \n\n[src\u002Fdb\u002Fqueries.js]  \n  ⚡ Fixed N+1 query: now uses JOIN instead of loop  \n\nSECURITY ISSUES:  \n🚨 CRITICAL: Hardcoded API key in config.js (line 12) → moved to .env  \n⚠️ HIGH: SQL injection risk in search.js (line 34) → fixed with parameterized query  \n\nSCALABILITY:  \n⚡ Added pagination to \u002Fapi\u002Fusers endpoint  \n⚡ Added index on users.email column  \n\nFINAL STATUS:  \n✅ CLEAN - Ready to push to GitHub  \n\nScores:  \nSecurity: 9\u002F10 (one minor header missing)  \nCode Quality: 10\u002F10  \nScalability: 9\u002F10  \nOverall: 9\u002F10  \n```  \n\n## Key Principles  \n\n- Read the code thoroughly, don't skim  \n- Fix issues immediately, don’t just document them  \n- If uncertain about removing something, ask the user  \n- Test after making changes  \n- Be thorough but practical—focus on real problems  \n- Security issues are blockers—nothing should ship with critical vulnerabilities  \n\n## Related Skills  \n\n- `@security-auditor` - Deeper security review  \n- `@systematic-debugging` - Investigate specific issues  \n- `@git-pushing` - Push code after audit\n\n## Limitations\n- Use this skill only when the task clearly matches the scope described above.\n- Do not treat the output as a substitute for environment-specific validation, testing, or expert review.\n- Stop and ask for clarification if required inputs, permissions, safety boundaries, or success criteria are missing.\n",{"name":5,"risk":24,"source":25,"category":26,"date_added":27,"description":7},"safe","community","development","2026-03-05","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcodebase-audit-pre-push",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":38,"prompt":48,"zipAvailable":49},[39,42,45],{"tool":40,"command":41},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill codebase-audit-pre-push",{"tool":43,"command":44},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill codebase-audit-pre-push",{"tool":46,"command":47},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill codebase-audit-pre-push","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fplugins\u002Fantigravity-awesome-skills\u002Fskills\u002Fcodebase-audit-pre-push\u002FSKILL.md",true,[],[52,59,66,73,80,87],{"skillNo":53,"name":54,"nameZh":6,"description":55,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":56,"categories":57,"keywords":58,"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":60,"name":61,"nameZh":6,"description":62,"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":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":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":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":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":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":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":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":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":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",[],[]]