[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CGFYX8YJ7SF367ACRKNG9F":3,"skill-same:01M7CGFYX8YJ7SF367ACRKNG9F":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},"01M7CGFYX8YJ7SF367ACRKNG9F","agentflow",null,"Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.","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\u002Fagentflow\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agentflow\ndescription: \"Orchestrate autonomous AI development pipelines through your Kanban board (Asana, GitHub Projects, Linear). Manages multi-worker Claude Code dispatch, deterministic quality gates, adversarial review, per-task cost tracking, and crash-proof pipeline execution.\"\nrisk: safe\nsource: community\ndate_added: \"2026-04-02\"\n---\n\n# AgentFlow\n\n## Overview\n\nAgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine — tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.\n\nThe result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.\n\n## When to Use This Skill\n\n- Use when you need to orchestrate multiple Claude Code workers across a full development lifecycle (build, review, test, integrate)\n- Use when you want deterministic quality gates (tsc\u002Feslint\u002Ftests) before AI review on AI-generated code\n- Use when you want full pipeline visibility from your Kanban board or phone\n- Use when running a solo or team project that needs autonomous task dispatch with cost tracking\n- Use when you need crash-proof orchestration that survives session restarts\n\n## Core Concepts\n\n### 7-Stage Kanban Pipeline\n\nTasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer — no separate database, no message queue, no custom infrastructure.\n\n### Stateless Orchestrator\n\nA crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.\n\n### Deterministic Before Probabilistic\n\nHard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.\n\n### Adversarial Review\n\nA different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.\n\n### Transitive Priority Dispatch\n\nTasks that unblock the most downstream work get built first, automatically computing the critical path.\n\n## Skills \u002F Commands\n\n### `\u002Fspec-to-board`\nDecomposes a SPEC.md into atomic tasks on your Kanban board with dependencies mapped.\n\n### `\u002Fsdlc-orchestrate`\nDispatches tasks to workers based on transitive priority and conflict detection. Runs as a crontab sweep.\n\n### `\u002Fsdlc-worker --slot \u003CN>`\nRuns a worker in a terminal slot that picks up tasks, builds code, and creates PRs. Run 3-4 workers in parallel.\n\n### `\u002Fsdlc-health`\nReal-time pipeline status dashboard showing current stage, assigned agent, retry count, and accumulated cost for every task.\n\n### `\u002Fsdlc-stop`\nGraceful shutdown: active workers finish their current task, unstarted tasks return to Backlog.\n\n## Step-by-Step Guide\n\n### 1. Write Your Spec\n\nCreate a `SPEC.md` for your project describing what you want to build.\n\n### 2. Decompose Into Tasks\n\n```\nclaude -p \"\u002Fspec-to-board\"\n```\n\nThis reads your SPEC.md, decomposes it into atomic tasks, maps dependencies, and creates them on your Kanban board.\n\n### 3. Start Workers\n\nOpen 3-4 terminal windows, each as a worker slot:\n\n```bash\n# Terminal 2 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T2\"\n\n# Terminal 3 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T3\"\n\n# Terminal 4 — Reviewer\nclaude -p \"\u002Fsdlc-worker --slot T4\"\n\n# Terminal 5 — Tester\nclaude -p \"\u002Fsdlc-worker --slot T5\"\n```\n\n### 4. Start the Orchestrator\n\n```bash\n# Add to crontab (runs every 15 minutes)\ncrontab -e\n# Add: *\u002F15 * * * * ~\u002F.claude\u002Fsdlc\u002Fagentflow-cron.sh >> \u002Ftmp\u002Fagentflow-orchestrate.log 2>&1\n```\n\n### 5. Monitor and Intervene\n\nOpen your Kanban board on your phone. Watch tasks flow through the pipeline. Drag any card to \"Needs Human\" to intervene. Run `\u002Fsdlc-health` for a terminal dashboard.\n\n### 6. Stop the Pipeline\n\n```\nclaude -p \"\u002Fsdlc-stop\"\n```\n\n## Quality Gates\n\nEach stage enforces specific gates before promotion:\n\n- **Build to Review**: `tsc` + `eslint` + `npm test` must all pass (deterministic)\n- **Review to Test**: Adversarial reviewer must list 3 issues before passing\n- **Test to Integrate**: 80% coverage threshold on new files\n- **Integrate to Done**: Full test suite on main after merge; auto-reverts on failure\n\n## Cost Tracking\n\nPer-task cost tracking with stage ceilings (Sonnet defaults):\n\n- Research: ~$0.10\n- Build: ~$0.40\n- Review: ~$0.10\n- Test: ~$0.05\n- Integrate: ~$0.03\n\nAutomatic guardrails: warning at $3\u002F$8, hard stop at $10\u002F$20 (Sonnet\u002FOpus) with human escalation.\n\n## Safety and Recovery\n\n- **Auto-revert**: Integration failures trigger `git revert` (new commit, never force-push)\n- **Blocked tasks**: After 2 failed attempts, tasks escalate to human review\n- **Dead agent detection**: Heartbeat every 5 min, reassign after 10 min timeout\n- **Graceful shutdown**: `\u002Fsdlc-stop` drains workers, returns unstarted tasks to backlog\n- **Scope creep detection**: PR diff files compared against predicted files list\n- **Spec drift detection**: SHA-256 hash comparison catches requirement changes mid-sprint\n\n## Installation\n\n```bash\n# Clone the repo\ngit clone https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow.git\n\n# Copy skills and prompts to your Claude Code config\ncp -r agentflow\u002Fskills\u002F* ~\u002F.claude\u002Fskills\u002F\ncp -r agentflow\u002Fprompts\u002F* ~\u002F.claude\u002Fsdlc\u002Fprompts\u002F\ncp agentflow\u002Fconventions.md ~\u002F.claude\u002Fsdlc\u002Fconventions.md\n```\n\nOr install as a Claude Code plugin:\n\n```bash\n\u002Fplugin marketplace add UrRhb\u002Fagentflow\n\u002Fplugin install agentflow\n```\n\n## Best Practices\n\n- Do: Write a clear SPEC.md before running `\u002Fspec-to-board`\n- Do: Start with 3-4 workers for a typical project\n- Do: Monitor from your Kanban board and drag cards to \"Needs Human\" when needed\n- Do: Review LEARNINGS.md periodically — it captures common failure patterns\n- Don't: Skip the deterministic quality gates — they catch most issues cheaply\n- Don't: Force-push to main — AgentFlow uses `git revert` for safety\n- Don't: Run more workers than your project's parallelism supports\n\n## Troubleshooting\n\n### Problem: Worker appears stuck or dead\n**Symptoms:** Task card hasn't moved in 15+ minutes, no new comments\n**Solution:** The orchestrator detects dead agents via heartbeat and reassigns after 10 minutes. If the issue persists, run `\u002Fsdlc-health` to check status and manually drag the card back to Backlog.\n\n### Problem: Cost guardrail triggered\n**Symptoms:** Task moved to \"Needs Human\" with COST:CRITICAL tag\n**Solution:** Review the task's comment thread for accumulated context. Decide whether to increase the budget, simplify the task, or split it into smaller pieces.\n\n### Problem: Integration test failure after merge\n**Symptoms:** Task auto-reverted from main\n**Solution:** The auto-revert preserves main stability. Check the task's retry context in comments, which carries what was tried and what failed. The next worker assigned will use this context.\n\n## Related Skills\n\n- `@brainstorming` - Use before AgentFlow to design your SPEC.md\n- `@writing-plans` - Complements spec writing for task decomposition\n- `@test-driven-development` - Works well with AgentFlow's quality gates\n- `@subagent-driven-development` - Alternative approach to multi-agent coordination\n\n## Additional Resources\n\n- [AgentFlow Repository](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow)\n- [Architecture Documentation](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Farchitecture.md)\n- [Gap Registry (45 failure modes)](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgap-registry.md)\n- [Getting Started Guide](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgetting-started.md)\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","# AgentFlow\n\n## Overview\n\nAgentFlow turns your existing Kanban board into a fully autonomous AI development pipeline. Instead of building custom orchestration infrastructure, it treats your project management tool (Asana, GitHub Projects, Linear) as a distributed state machine — tasks move through stages, AI agents read and write state via comments, and humans intervene through the same UI they already use.\n\nThe result is complete pipeline observability from your phone, free crash recovery (state lives in your PM tool, not in memory), and human override at any point by dragging a card.\n\n## When to Use This Skill\n\n- Use when you need to orchestrate multiple Claude Code workers across a full development lifecycle (build, review, test, integrate)\n- Use when you want deterministic quality gates (tsc\u002Feslint\u002Ftests) before AI review on AI-generated code\n- Use when you want full pipeline visibility from your Kanban board or phone\n- Use when running a solo or team project that needs autonomous task dispatch with cost tracking\n- Use when you need crash-proof orchestration that survives session restarts\n\n## Core Concepts\n\n### 7-Stage Kanban Pipeline\n\nTasks flow through: Backlog, Research, Build, Review, Test, Integrate, Done. Each stage has specific gates. The Kanban board IS the orchestration layer — no separate database, no message queue, no custom infrastructure.\n\n### Stateless Orchestrator\n\nA crontab-driven one-shot sweep runs every 15 minutes. No daemon, no session dependency. If it crashes, the next sweep picks up where it left off because all state lives in your PM tool.\n\n### Deterministic Before Probabilistic\n\nHard gates (tsc + eslint + tests) run before any AI review, catching roughly 60% of issues at near-zero cost. AI review comes after, as a second layer.\n\n### Adversarial Review\n\nA different AI agent reviews code and must list 3 things wrong before deciding to pass. This prevents rubber-stamp approvals.\n\n### Transitive Priority Dispatch\n\nTasks that unblock the most downstream work get built first, automatically computing the critical path.\n\n## Skills \u002F Commands\n\n### `\u002Fspec-to-board`\nDecomposes a SPEC.md into atomic tasks on your Kanban board with dependencies mapped.\n\n### `\u002Fsdlc-orchestrate`\nDispatches tasks to workers based on transitive priority and conflict detection. Runs as a crontab sweep.\n\n### `\u002Fsdlc-worker --slot \u003CN>`\nRuns a worker in a terminal slot that picks up tasks, builds code, and creates PRs. Run 3-4 workers in parallel.\n\n### `\u002Fsdlc-health`\nReal-time pipeline status dashboard showing current stage, assigned agent, retry count, and accumulated cost for every task.\n\n### `\u002Fsdlc-stop`\nGraceful shutdown: active workers finish their current task, unstarted tasks return to Backlog.\n\n## Step-by-Step Guide\n\n### 1. Write Your Spec\n\nCreate a `SPEC.md` for your project describing what you want to build.\n\n### 2. Decompose Into Tasks\n\n```\nclaude -p \"\u002Fspec-to-board\"\n```\n\nThis reads your SPEC.md, decomposes it into atomic tasks, maps dependencies, and creates them on your Kanban board.\n\n### 3. Start Workers\n\nOpen 3-4 terminal windows, each as a worker slot:\n\n```bash\n# Terminal 2 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T2\"\n\n# Terminal 3 — Builder\nclaude -p \"\u002Fsdlc-worker --slot T3\"\n\n# Terminal 4 — Reviewer\nclaude -p \"\u002Fsdlc-worker --slot T4\"\n\n# Terminal 5 — Tester\nclaude -p \"\u002Fsdlc-worker --slot T5\"\n```\n\n### 4. Start the Orchestrator\n\n```bash\n# Add to crontab (runs every 15 minutes)\ncrontab -e\n# Add: *\u002F15 * * * * ~\u002F.claude\u002Fsdlc\u002Fagentflow-cron.sh >> \u002Ftmp\u002Fagentflow-orchestrate.log 2>&1\n```\n\n### 5. Monitor and Intervene\n\nOpen your Kanban board on your phone. Watch tasks flow through the pipeline. Drag any card to \"Needs Human\" to intervene. Run `\u002Fsdlc-health` for a terminal dashboard.\n\n### 6. Stop the Pipeline\n\n```\nclaude -p \"\u002Fsdlc-stop\"\n```\n\n## Quality Gates\n\nEach stage enforces specific gates before promotion:\n\n- **Build to Review**: `tsc` + `eslint` + `npm test` must all pass (deterministic)\n- **Review to Test**: Adversarial reviewer must list 3 issues before passing\n- **Test to Integrate**: 80% coverage threshold on new files\n- **Integrate to Done**: Full test suite on main after merge; auto-reverts on failure\n\n## Cost Tracking\n\nPer-task cost tracking with stage ceilings (Sonnet defaults):\n\n- Research: ~$0.10\n- Build: ~$0.40\n- Review: ~$0.10\n- Test: ~$0.05\n- Integrate: ~$0.03\n\nAutomatic guardrails: warning at $3\u002F$8, hard stop at $10\u002F$20 (Sonnet\u002FOpus) with human escalation.\n\n## Safety and Recovery\n\n- **Auto-revert**: Integration failures trigger `git revert` (new commit, never force-push)\n- **Blocked tasks**: After 2 failed attempts, tasks escalate to human review\n- **Dead agent detection**: Heartbeat every 5 min, reassign after 10 min timeout\n- **Graceful shutdown**: `\u002Fsdlc-stop` drains workers, returns unstarted tasks to backlog\n- **Scope creep detection**: PR diff files compared against predicted files list\n- **Spec drift detection**: SHA-256 hash comparison catches requirement changes mid-sprint\n\n## Installation\n\n```bash\n# Clone the repo\ngit clone https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow.git\n\n# Copy skills and prompts to your Claude Code config\ncp -r agentflow\u002Fskills\u002F* ~\u002F.claude\u002Fskills\u002F\ncp -r agentflow\u002Fprompts\u002F* ~\u002F.claude\u002Fsdlc\u002Fprompts\u002F\ncp agentflow\u002Fconventions.md ~\u002F.claude\u002Fsdlc\u002Fconventions.md\n```\n\nOr install as a Claude Code plugin:\n\n```bash\n\u002Fplugin marketplace add UrRhb\u002Fagentflow\n\u002Fplugin install agentflow\n```\n\n## Best Practices\n\n- Do: Write a clear SPEC.md before running `\u002Fspec-to-board`\n- Do: Start with 3-4 workers for a typical project\n- Do: Monitor from your Kanban board and drag cards to \"Needs Human\" when needed\n- Do: Review LEARNINGS.md periodically — it captures common failure patterns\n- Don't: Skip the deterministic quality gates — they catch most issues cheaply\n- Don't: Force-push to main — AgentFlow uses `git revert` for safety\n- Don't: Run more workers than your project's parallelism supports\n\n## Troubleshooting\n\n### Problem: Worker appears stuck or dead\n**Symptoms:** Task card hasn't moved in 15+ minutes, no new comments\n**Solution:** The orchestrator detects dead agents via heartbeat and reassigns after 10 minutes. If the issue persists, run `\u002Fsdlc-health` to check status and manually drag the card back to Backlog.\n\n### Problem: Cost guardrail triggered\n**Symptoms:** Task moved to \"Needs Human\" with COST:CRITICAL tag\n**Solution:** Review the task's comment thread for accumulated context. Decide whether to increase the budget, simplify the task, or split it into smaller pieces.\n\n### Problem: Integration test failure after merge\n**Symptoms:** Task auto-reverted from main\n**Solution:** The auto-revert preserves main stability. Check the task's retry context in comments, which carries what was tried and what failed. The next worker assigned will use this context.\n\n## Related Skills\n\n- `@brainstorming` - Use before AgentFlow to design your SPEC.md\n- `@writing-plans` - Complements spec writing for task decomposition\n- `@test-driven-development` - Works well with AgentFlow's quality gates\n- `@subagent-driven-development` - Alternative approach to multi-agent coordination\n\n## Additional Resources\n\n- [AgentFlow Repository](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow)\n- [Architecture Documentation](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Farchitecture.md)\n- [Gap Registry (45 failure modes)](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgap-registry.md)\n- [Getting Started Guide](https:\u002F\u002Fgithub.com\u002FUrRhb\u002Fagentflow\u002Fblob\u002Fmain\u002Fdocs\u002Fgetting-started.md)\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},"safe","community","2026-04-02","main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Skills-技能包\u002FYYC3-Skills-技能包-antigravity-awesome-skills\u002Fskills\u002Fagentflow",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 agentflow",{"tool":42,"command":43},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agentflow",{"tool":45,"command":46},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agentflow","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\u002Fagentflow\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",[],[]]