[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CJ4FWMN9DQ0SHT33CDNDT4":3,"skill-same:01M7CJ4FWMN9DQ0SHT33CDNDT4":50},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":32,"ownerHtmlUrl":33,"ownerBlogUrl":6,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M7CJ4FWMN9DQ0SHT33CDNDT4","conductor-implement",null,"Execute tasks from a track's implementation plan following TDD workflow","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\u002Fskills\u002Fconductor-implement\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: conductor-implement\ndescription: \"Execute tasks from a track's implementation plan following TDD workflow\"\nrisk: critical\nsource: community\ndate_added: \"2026-02-27\"\n---\n\n# Implement Track\n\nExecute tasks from a track's implementation plan, following the workflow rules defined in `conductor\u002Fworkflow.md`.\n\n## Use this skill when\n\n- Working on implement track tasks or workflows\n- Needing guidance, best practices, or checklists for implement track\n\n## Do not use this skill when\n\n- The task is unrelated to implement track\n- You need a different domain or tool outside this scope\n\n## Instructions\n\n- Clarify goals, constraints, and required inputs.\n- Apply relevant best practices and validate outcomes.\n- Provide actionable steps and verification.\n- If detailed examples are required, open `resources\u002Fimplementation-playbook.md`.\n\n## Pre-flight Checks\n\n1. Verify Conductor is initialized:\n   - Check `conductor\u002Fproduct.md` exists\n   - Check `conductor\u002Fworkflow.md` exists\n   - Check `conductor\u002Ftracks.md` exists\n   - If missing: Display error and suggest running `\u002Fconductor:setup` first\n\n2. Load workflow configuration:\n   - Read `conductor\u002Fworkflow.md`\n   - Parse TDD strictness level\n   - Parse commit strategy\n   - Parse verification checkpoint rules\n\n## Track Selection\n\n### If argument provided:\n\n- Validate track exists: `conductor\u002Ftracks\u002F{argument}\u002Fplan.md`\n- If not found: Search for partial matches, suggest corrections\n\n### If no argument:\n\n1. Read `conductor\u002Ftracks.md`\n2. Parse for incomplete tracks (status `[ ]` or `[~]`)\n3. Display selection menu:\n\n   ```\n   Select a track to implement:\n\n   In Progress:\n   1. [~] auth_20250115 - User Authentication (Phase 2, Task 3)\n\n   Pending:\n   2. [ ] nav-fix_20250114 - Navigation Bug Fix\n   3. [ ] dashboard_20250113 - Dashboard Feature\n\n   Enter number or track ID:\n   ```\n\n## Context Loading\n\nLoad all relevant context for implementation:\n\n1. Track documents:\n   - `conductor\u002Ftracks\u002F{trackId}\u002Fspec.md` - Requirements\n   - `conductor\u002Ftracks\u002F{trackId}\u002Fplan.md` - Task list\n   - `conductor\u002Ftracks\u002F{trackId}\u002Fmetadata.json` - Progress state\n\n2. Project context:\n   - `conductor\u002Fproduct.md` - Product understanding\n   - `conductor\u002Ftech-stack.md` - Technical constraints\n   - `conductor\u002Fworkflow.md` - Process rules\n\n3. Code style (if exists):\n   - `conductor\u002Fcode_styleguides\u002F{language}.md`\n\n## Track Status Update\n\nUpdate track to in-progress:\n\n1. In `conductor\u002Ftracks.md`:\n   - Change `[ ]` to `[~]` for this track\n\n2. In `conductor\u002Ftracks\u002F{trackId}\u002Fmetadata.json`:\n   - Set `status: \"in_progress\"`\n   - Update `updated` timestamp\n\n## Task Execution Loop\n\nFor each incomplete task in plan.md (marked with `[ ]`):\n\n### 1. Task Identification\n\nParse plan.md to find next incomplete task:\n\n- Look for lines matching `- [ ] Task X.Y: {description}`\n- Track current phase from structure\n\n### 2. Task Start\n\nMark task as in-progress:\n\n- Update plan.md: Change `[ ]` to `[~]` for current task\n- Announce: \"Starting Task X.Y: {description}\"\n\n### 3. TDD Workflow (if TDD enabled in workflow.md)\n\n**Red Phase - Write Failing Test:**\n\n```\nFollowing TDD workflow for Task X.Y...\n\nStep 1: Writing failing test\n```\n\n- Create test file if needed\n- Write test(s) for the task functionality\n- Run tests to confirm they fail\n- If tests pass unexpectedly: HALT, investigate\n\n**Green Phase - Implement:**\n\n```\nStep 2: Implementing minimal code to pass test\n```\n\n- Write minimum code to make test pass\n- Run tests to confirm they pass\n- If tests fail: Debug and fix\n\n**Refactor Phase:**\n\n```\nStep 3: Refactoring while keeping tests green\n```\n\n- Clean up code\n- Run tests to ensure still passing\n\n### 4. Non-TDD Workflow (if TDD not strict)\n\n- Implement the task directly\n- Run any existing tests\n- Manual verification as needed\n\n### 5. Task Completion\n\n**Commit changes** (following commit strategy from workflow.md):\n\n```bash\ngit add -A\ngit commit -m \"{commit_prefix}: {task description} ({trackId})\"\n```\n\n**Update plan.md:**\n\n- Change `[~]` to `[x]` for completed task\n- Commit plan update:\n\n```bash\ngit add conductor\u002Ftracks\u002F{trackId}\u002Fplan.md\ngit commit -m \"chore: mark task X.Y complete ({trackId})\"\n```\n\n**Update metadata.json:**\n\n- Increment `tasks.completed`\n- Update `updated` timestamp\n\n### 6. Phase Completion Check\n\nAfter each task, check if phase is complete:\n\n- Parse plan.md for phase structure\n- If all tasks in current phase are `[x]`:\n\n**Run phase verification:**\n\n```\nPhase {N} complete. Running verification...\n```\n\n- Execute verification tasks listed for the phase\n- Run full test suite: `npm test` \u002F `pytest` \u002F etc.\n\n**Report and wait for approval:**\n\n```\nPhase {N} Verification Results:\n- All phase tasks: Complete\n- Tests: {passing\u002Ffailing}\n- Verification: {pass\u002Ffail}\n\nApprove to continue to Phase {N+1}?\n1. Yes, continue\n2. No, there are issues to fix\n3. Pause implementation\n```\n\n**CRITICAL: Wait for explicit user approval before proceeding to next phase.**\n\n## Error Handling During Implementation\n\n### On Tool Failure\n\n```\nERROR: {tool} failed with: {error message}\n\nOptions:\n1. Retry the operation\n2. Skip this task and continue\n3. Pause implementation\n4. Revert current task changes\n```\n\n- HALT and present options\n- Do NOT automatically continue\n\n### On Test Failure\n\n```\nTESTS FAILING after Task X.Y\n\nFailed tests:\n- {test name}: {failure reason}\n\nOptions:\n1. Attempt to fix\n2. Rollback task changes\n3. Pause for manual intervention\n```\n\n### On Git Failure\n\n```\nGIT ERROR: {error message}\n\nThis may indicate:\n- Uncommitted changes from outside Conductor\n- Merge conflicts\n- Permission issues\n\nOptions:\n1. Show git status\n2. Attempt to resolve\n3. Pause for manual intervention\n```\n\n## Track Completion\n\nWhen all phases and tasks are complete:\n\n### 1. Final Verification\n\n```\nAll tasks complete. Running final verification...\n```\n\n- Run full test suite\n- Check all acceptance criteria from spec.md\n- Generate verification report\n\n### 2. Update Track Status\n\nIn `conductor\u002Ftracks.md`:\n\n- Change `[~]` to `[x]` for this track\n- Update the \"Updated\" column\n\nIn `conductor\u002Ftracks\u002F{trackId}\u002Fmetadata.json`:\n\n- Set `status: \"complete\"`\n- Set `phases.completed` to total\n- Set `tasks.completed` to total\n- Update `updated` timestamp\n\nIn `conductor\u002Ftracks\u002F{trackId}\u002Fplan.md`:\n\n- Update header status to `[x] Complete`\n\n### 3. Documentation Sync Offer\n\n```\nTrack complete! Would you like to sync documentation?\n\nThis will update:\n- conductor\u002Fproduct.md (if new features added)\n- conductor\u002Ftech-stack.md (if new dependencies added)\n- README.md (if applicable)\n\n1. Yes, sync documentation\n2. No, skip\n```\n\n### 4. Cleanup Offer\n\n```\nTrack {trackId} is complete.\n\nCleanup options:\n1. Archive - Move to conductor\u002Ftracks\u002F_archive\u002F\n2. Delete - Remove track directory\n3. Keep - Leave as-is\n```\n\n### 5. Completion Summary\n\n```\nTrack Complete: {track title}\n\nSummary:\n- Track ID: {trackId}\n- Phases completed: {N}\u002F{N}\n- Tasks completed: {M}\u002F{M}\n- Commits created: {count}\n- Tests: All passing\n\nNext steps:\n- Run \u002Fconductor:status to see project progress\n- Run \u002Fconductor:new-track for next feature\n```\n\n## Progress Tracking\n\nMaintain progress in `metadata.json` throughout:\n\n```json\n{\n  \"id\": \"auth_20250115\",\n  \"title\": \"User Authentication\",\n  \"type\": \"feature\",\n  \"status\": \"in_progress\",\n  \"created\": \"2025-01-15T10:00:00Z\",\n  \"updated\": \"2025-01-15T14:30:00Z\",\n  \"current_phase\": 2,\n  \"current_task\": \"2.3\",\n  \"phases\": {\n    \"total\": 3,\n    \"completed\": 1\n  },\n  \"tasks\": {\n    \"total\": 12,\n    \"completed\": 7\n  },\n  \"commits\": [\n    \"abc1234: feat: add login form (auth_20250115)\",\n    \"def5678: feat: add password validation (auth_20250115)\"\n  ]\n}\n```\n\n## Resumption\n\nIf implementation is paused and resumed:\n\n1. Load `metadata.json` for current state\n2. Find current task from `current_task` field\n3. Check if task is `[~]` in plan.md\n4. Ask user:\n\n   ```\n   Resuming track: {title}\n\n   Last task in progress: Task {X.Y}: {description}\n\n   Options:\n   1. Continue from where we left off\n   2. Restart current task\n   3. Show progress summary first\n   ```\n\n## Critical Rules\n\n1. **NEVER skip verification checkpoints** - Always wait for user approval between phases\n2. **STOP on any failure** - Do not attempt to continue past errors\n3. **Follow workflow.md strictly** - TDD, commit strategy, and verification rules are mandatory\n4. **Keep plan.md updated** - Task status must reflect actual progress\n5. **Commit frequently** - Each task completion should be committed\n6. **Track all commits** - Record commit hashes in metadata.json for potential revert\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","# Implement Track\n\nExecute tasks from a track's implementation plan, following the workflow rules defined in `conductor\u002Fworkflow.md`.\n\n## Use this skill when\n\n- Working on implement track tasks or workflows\n- Needing guidance, best practices, or checklists for implement track\n\n## Do not use this skill when\n\n- The task is unrelated to implement track\n- You need a different domain or tool outside this scope\n\n## Instructions\n\n- Clarify goals, constraints, and required inputs.\n- Apply relevant best practices and validate outcomes.\n- Provide actionable steps and verification.\n- If detailed examples are required, open `resources\u002Fimplementation-playbook.md`.\n\n## Pre-flight Checks\n\n1. Verify Conductor is initialized:\n   - Check `conductor\u002Fproduct.md` exists\n   - Check `conductor\u002Fworkflow.md` exists\n   - Check `conductor\u002Ftracks.md` exists\n   - If missing: Display error and suggest running `\u002Fconductor:setup` first\n\n2. Load workflow configuration:\n   - Read `conductor\u002Fworkflow.md`\n   - Parse TDD strictness level\n   - Parse commit strategy\n   - Parse verification checkpoint rules\n\n## Track Selection\n\n### If argument provided:\n\n- Validate track exists: `conductor\u002Ftracks\u002F{argument}\u002Fplan.md`\n- If not found: Search for partial matches, suggest corrections\n\n### If no argument:\n\n1. Read `conductor\u002Ftracks.md`\n2. Parse for incomplete tracks (status `[ ]` or `[~]`)\n3. Display selection menu:\n\n   ```\n   Select a track to implement:\n\n   In Progress:\n   1. [~] auth_20250115 - User Authentication (Phase 2, Task 3)\n\n   Pending:\n   2. [ ] nav-fix_20250114 - Navigation Bug Fix\n   3. [ ] dashboard_20250113 - Dashboard Feature\n\n   Enter number or track ID:\n   ```\n\n## Context Loading\n\nLoad all relevant context for implementation:\n\n1. Track documents:\n   - `conductor\u002Ftracks\u002F{trackId}\u002Fspec.md` - Requirements\n   - `conductor\u002Ftracks\u002F{trackId}\u002Fplan.md` - Task list\n   - `conductor\u002Ftracks\u002F{trackId}\u002Fmetadata.json` - Progress state\n\n2. Project context:\n   - `conductor\u002Fproduct.md` - Product understanding\n   - `conductor\u002Ftech-stack.md` - Technical constraints\n   - `conductor\u002Fworkflow.md` - Process rules\n\n3. Code style (if exists):\n   - `conductor\u002Fcode_styleguides\u002F{language}.md`\n\n## Track Status Update\n\nUpdate track to in-progress:\n\n1. In `conductor\u002Ftracks.md`:\n   - Change `[ ]` to `[~]` for this track\n\n2. In `conductor\u002Ftracks\u002F{trackId}\u002Fmetadata.json`:\n   - Set `status: \"in_progress\"`\n   - Update `updated` timestamp\n\n## Task Execution Loop\n\nFor each incomplete task in plan.md (marked with `[ ]`):\n\n### 1. Task Identification\n\nParse plan.md to find next incomplete task:\n\n- Look for lines matching `- [ ] Task X.Y: {description}`\n- Track current phase from structure\n\n### 2. Task Start\n\nMark task as in-progress:\n\n- Update plan.md: Change `[ ]` to `[~]` for current task\n- Announce: \"Starting Task X.Y: {description}\"\n\n### 3. TDD Workflow (if TDD enabled in workflow.md)\n\n**Red Phase - Write Failing Test:**\n\n```\nFollowing TDD workflow for Task X.Y...\n\nStep 1: Writing failing test\n```\n\n- Create test file if needed\n- Write test(s) for the task functionality\n- Run tests to confirm they fail\n- If tests pass unexpectedly: HALT, investigate\n\n**Green Phase - Implement:**\n\n```\nStep 2: Implementing minimal code to pass test\n```\n\n- Write minimum code to make test pass\n- Run tests to confirm they pass\n- If tests fail: Debug and fix\n\n**Refactor Phase:**\n\n```\nStep 3: Refactoring while keeping tests green\n```\n\n- Clean up code\n- Run tests to ensure still passing\n\n### 4. Non-TDD Workflow (if TDD not strict)\n\n- Implement the task directly\n- Run any existing tests\n- Manual verification as needed\n\n### 5. Task Completion\n\n**Commit changes** (following commit strategy from workflow.md):\n\n```bash\ngit add -A\ngit commit -m \"{commit_prefix}: {task description} ({trackId})\"\n```\n\n**Update plan.md:**\n\n- Change `[~]` to `[x]` for completed task\n- Commit plan update:\n\n```bash\ngit add conductor\u002Ftracks\u002F{trackId}\u002Fplan.md\ngit commit -m \"chore: mark task X.Y complete ({trackId})\"\n```\n\n**Update metadata.json:**\n\n- Increment `tasks.completed`\n- Update `updated` timestamp\n\n### 6. Phase Completion Check\n\nAfter each task, check if phase is complete:\n\n- Parse plan.md for phase structure\n- If all tasks in current phase are `[x]`:\n\n**Run phase verification:**\n\n```\nPhase {N} complete. Running verification...\n```\n\n- Execute verification tasks listed for the phase\n- Run full test suite: `npm test` \u002F `pytest` \u002F etc.\n\n**Report and wait for approval:**\n\n```\nPhase {N} Verification Results:\n- All phase tasks: Complete\n- Tests: {passing\u002Ffailing}\n- Verification: {pass\u002Ffail}\n\nApprove to continue to Phase {N+1}?\n1. Yes, continue\n2. No, there are issues to fix\n3. Pause implementation\n```\n\n**CRITICAL: Wait for explicit user approval before proceeding to next phase.**\n\n## Error Handling During Implementation\n\n### On Tool Failure\n\n```\nERROR: {tool} failed with: {error message}\n\nOptions:\n1. Retry the operation\n2. Skip this task and continue\n3. Pause implementation\n4. Revert current task changes\n```\n\n- HALT and present options\n- Do NOT automatically continue\n\n### On Test Failure\n\n```\nTESTS FAILING after Task X.Y\n\nFailed tests:\n- {test name}: {failure reason}\n\nOptions:\n1. Attempt to fix\n2. Rollback task changes\n3. Pause for manual intervention\n```\n\n### On Git Failure\n\n```\nGIT ERROR: {error message}\n\nThis may indicate:\n- Uncommitted changes from outside Conductor\n- Merge conflicts\n- Permission issues\n\nOptions:\n1. Show git status\n2. Attempt to resolve\n3. Pause for manual intervention\n```\n\n## Track Completion\n\nWhen all phases and tasks are complete:\n\n### 1. Final Verification\n\n```\nAll tasks complete. Running final verification...\n```\n\n- Run full test suite\n- Check all acceptance criteria from spec.md\n- Generate verification report\n\n### 2. Update Track Status\n\nIn `conductor\u002Ftracks.md`:\n\n- Change `[~]` to `[x]` for this track\n- Update the \"Updated\" column\n\nIn `conductor\u002Ftracks\u002F{trackId}\u002Fmetadata.json`:\n\n- Set `status: \"complete\"`\n- Set `phases.completed` to total\n- Set `tasks.completed` to total\n- Update `updated` timestamp\n\nIn `conductor\u002Ftracks\u002F{trackId}\u002Fplan.md`:\n\n- Update header status to `[x] Complete`\n\n### 3. Documentation Sync Offer\n\n```\nTrack complete! Would you like to sync documentation?\n\nThis will update:\n- conductor\u002Fproduct.md (if new features added)\n- conductor\u002Ftech-stack.md (if new dependencies added)\n- README.md (if applicable)\n\n1. Yes, sync documentation\n2. No, skip\n```\n\n### 4. Cleanup Offer\n\n```\nTrack {trackId} is complete.\n\nCleanup options:\n1. Archive - Move to conductor\u002Ftracks\u002F_archive\u002F\n2. Delete - Remove track directory\n3. Keep - Leave as-is\n```\n\n### 5. Completion Summary\n\n```\nTrack Complete: {track title}\n\nSummary:\n- Track ID: {trackId}\n- Phases completed: {N}\u002F{N}\n- Tasks completed: {M}\u002F{M}\n- Commits created: {count}\n- Tests: All passing\n\nNext steps:\n- Run \u002Fconductor:status to see project progress\n- Run \u002Fconductor:new-track for next feature\n```\n\n## Progress Tracking\n\nMaintain progress in `metadata.json` throughout:\n\n```json\n{\n  \"id\": \"auth_20250115\",\n  \"title\": \"User Authentication\",\n  \"type\": \"feature\",\n  \"status\": \"in_progress\",\n  \"created\": \"2025-01-15T10:00:00Z\",\n  \"updated\": \"2025-01-15T14:30:00Z\",\n  \"current_phase\": 2,\n  \"current_task\": \"2.3\",\n  \"phases\": {\n    \"total\": 3,\n    \"completed\": 1\n  },\n  \"tasks\": {\n    \"total\": 12,\n    \"completed\": 7\n  },\n  \"commits\": [\n    \"abc1234: feat: add login form (auth_20250115)\",\n    \"def5678: feat: add password validation (auth_20250115)\"\n  ]\n}\n```\n\n## Resumption\n\nIf implementation is paused and resumed:\n\n1. Load `metadata.json` for current state\n2. Find current task from `current_task` field\n3. Check if task is `[~]` in plan.md\n4. Ask user:\n\n   ```\n   Resuming track: {title}\n\n   Last task in progress: Task {X.Y}: {description}\n\n   Options:\n   1. Continue from where we left off\n   2. Restart current task\n   3. Show progress summary first\n   ```\n\n## Critical Rules\n\n1. **NEVER skip verification checkpoints** - Always wait for user approval between phases\n2. **STOP on any failure** - Do not attempt to continue past errors\n3. **Follow workflow.md strictly** - TDD, commit strategy, and verification rules are mandatory\n4. **Keep plan.md updated** - Task status must reflect actual progress\n5. **Commit frequently** - Each task completion should be committed\n6. **Track all commits** - Record commit hashes in metadata.json for potential revert\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,"date_added":26,"description":7},"critical","community","2026-02-27","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fconductor-implement",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":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill conductor-implement",{"tool":42,"command":43},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill conductor-implement",{"tool":45,"command":46},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill conductor-implement","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\u002Fskills\u002Fconductor-implement\u002FSKILL.md",true,[],[51,58,65,72,79,86],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":57,"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":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":64,"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":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"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":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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",[],[]]