[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BP7DWSGE8AS43ZFVH9BDC2":3,"skill-same:01M7BP7DWSGE8AS43ZFVH9BDC2":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BP7DWSGE8AS43ZFVH9BDC2","V3 Deep Integration",null,"Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.","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-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fcli\u002F.claude\u002Fskills\u002Fv3-integration-deep\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: \"V3 Deep Integration\"\ndescription: \"Deep agentic-flow@alpha integration implementing ADR-001. Eliminates 10,000+ duplicate lines by building claude-flow as specialized extension rather than parallel implementation.\"\n---\n\n# V3 Deep Integration\n\n## What This Skill Does\n\nTransforms claude-flow from parallel implementation to specialized extension of agentic-flow@alpha, eliminating massive code duplication while achieving performance improvements and feature parity.\n\n## Quick Start\n\n```bash\n# Initialize deep integration\nTask(\"Integration architecture\", \"Design agentic-flow@alpha adapter layer\", \"v3-integration-architect\")\n\n# Feature integration (parallel)\nTask(\"SONA integration\", \"Integrate 5 SONA learning modes\", \"v3-integration-architect\")\nTask(\"Flash Attention\", \"Implement 2.49x-7.47x speedup\", \"v3-integration-architect\")\nTask(\"AgentDB coordination\", \"Setup 150x-12,500x search\", \"v3-integration-architect\")\n```\n\n## Code Deduplication Strategy\n\n### Current Overlap → Integration\n```\n┌─────────────────────────────────────────┐\n│  claude-flow          agentic-flow      │\n├─────────────────────────────────────────┤\n│ SwarmCoordinator  →   Swarm System      │ 80% overlap (eliminate)\n│ AgentManager      →   Agent Lifecycle   │ 70% overlap (eliminate)\n│ TaskScheduler     →   Task Execution    │ 60% overlap (eliminate)\n│ SessionManager    →   Session Mgmt      │ 50% overlap (eliminate)\n└─────────────────────────────────────────┘\n\nTARGET: \u003C5,000 lines (vs 15,000+ currently)\n```\n\n## agentic-flow@alpha Feature Integration\n\n### SONA Learning Modes\n```typescript\nclass SONAIntegration {\n  async initializeMode(mode: SONAMode): Promise\u003Cvoid> {\n    switch(mode) {\n      case 'real-time':   \u002F\u002F ~0.05ms adaptation\n      case 'balanced':    \u002F\u002F general purpose\n      case 'research':    \u002F\u002F deep exploration\n      case 'edge':        \u002F\u002F resource-constrained\n      case 'batch':       \u002F\u002F high-throughput\n    }\n    await this.agenticFlow.sona.setMode(mode);\n  }\n}\n```\n\n### Flash Attention Integration\n```typescript\nclass FlashAttentionIntegration {\n  async optimizeAttention(): Promise\u003CAttentionResult> {\n    return this.agenticFlow.attention.flashAttention({\n      speedupTarget: '2.49x-7.47x',\n      memoryReduction: '50-75%',\n      mechanisms: ['multi-head', 'linear', 'local', 'global']\n    });\n  }\n}\n```\n\n### AgentDB Coordination\n```typescript\nclass AgentDBIntegration {\n  async setupCrossAgentMemory(): Promise\u003Cvoid> {\n    await this.agentdb.enableCrossAgentSharing({\n      indexType: 'HNSW',\n      speedupTarget: '150x-12500x',\n      dimensions: 1536\n    });\n  }\n}\n```\n\n### MCP Tools Integration\n```typescript\nclass MCPToolsIntegration {\n  async integrateBuiltinTools(): Promise\u003Cvoid> {\n    \u002F\u002F Leverage 213 pre-built tools\n    const tools = await this.agenticFlow.mcp.getAvailableTools();\n    await this.registerClaudeFlowSpecificTools(tools);\n\n    \u002F\u002F Use 19 hook types\n    const hookTypes = await this.agenticFlow.hooks.getTypes();\n    await this.configureClaudeFlowHooks(hookTypes);\n  }\n}\n```\n\n## Migration Implementation\n\n### Phase 1: Adapter Layer\n```typescript\nimport { Agent as AgenticFlowAgent } from 'agentic-flow@alpha';\n\nexport class ClaudeFlowAgent extends AgenticFlowAgent {\n  async handleClaudeFlowTask(task: ClaudeTask): Promise\u003CTaskResult> {\n    return this.executeWithSONA(task);\n  }\n\n  \u002F\u002F Backward compatibility\n  async legacyCompatibilityLayer(oldAPI: any): Promise\u003Cany> {\n    return this.adaptToNewAPI(oldAPI);\n  }\n}\n```\n\n### Phase 2: System Migration\n```typescript\nclass SystemMigration {\n  async migrateSwarmCoordination(): Promise\u003Cvoid> {\n    \u002F\u002F Replace SwarmCoordinator (800+ lines) with agentic-flow Swarm\n    const swarmConfig = await this.extractSwarmConfig();\n    await this.agenticFlow.swarm.initialize(swarmConfig);\n  }\n\n  async migrateAgentManagement(): Promise\u003Cvoid> {\n    \u002F\u002F Replace AgentManager (1,736+ lines) with agentic-flow lifecycle\n    const agents = await this.extractActiveAgents();\n    for (const agent of agents) {\n      await this.agenticFlow.agent.create(agent);\n    }\n  }\n\n  async migrateTaskExecution(): Promise\u003Cvoid> {\n    \u002F\u002F Replace TaskScheduler with agentic-flow task graph\n    const tasks = await this.extractTasks();\n    await this.agenticFlow.task.executeGraph(this.buildTaskGraph(tasks));\n  }\n}\n```\n\n### Phase 3: Cleanup\n```typescript\nclass CodeCleanup {\n  async removeDeprecatedCode(): Promise\u003Cvoid> {\n    \u002F\u002F Remove massive duplicate implementations\n    await this.removeFile('src\u002Fcore\u002FSwarmCoordinator.ts');    \u002F\u002F 800+ lines\n    await this.removeFile('src\u002Fagents\u002FAgentManager.ts');      \u002F\u002F 1,736+ lines\n    await this.removeFile('src\u002Ftask\u002FTaskScheduler.ts');       \u002F\u002F 500+ lines\n\n    \u002F\u002F Total reduction: 10,000+ → \u003C5,000 lines\n  }\n}\n```\n\n## RL Algorithm Integration\n\n```typescript\nclass RLIntegration {\n  algorithms = [\n    'PPO', 'DQN', 'A2C', 'MCTS', 'Q-Learning',\n    'SARSA', 'Actor-Critic', 'Decision-Transformer'\n  ];\n\n  async optimizeAgentBehavior(): Promise\u003Cvoid> {\n    for (const algorithm of this.algorithms) {\n      await this.agenticFlow.rl.train(algorithm, {\n        episodes: 1000,\n        rewardFunction: this.claudeFlowRewardFunction\n      });\n    }\n  }\n}\n```\n\n## Performance Integration\n\n### Flash Attention Targets\n```typescript\nconst attentionBenchmark = {\n  baseline: 'current attention mechanism',\n  target: '2.49x-7.47x improvement',\n  memoryReduction: '50-75%',\n  implementation: 'agentic-flow@alpha Flash Attention'\n};\n```\n\n### AgentDB Search Performance\n```typescript\nconst searchBenchmark = {\n  baseline: 'linear search in current systems',\n  target: '150x-12,500x via HNSW indexing',\n  implementation: 'agentic-flow@alpha AgentDB'\n};\n```\n\n## Backward Compatibility\n\n### Gradual Migration\n```typescript\nclass BackwardCompatibility {\n  \u002F\u002F Phase 1: Dual operation\n  async enableDualOperation(): Promise\u003Cvoid> {\n    this.oldSystem.continue();\n    this.newSystem.initialize();\n    this.syncState(this.oldSystem, this.newSystem);\n  }\n\n  \u002F\u002F Phase 2: Feature-by-feature migration\n  async migrateGradually(): Promise\u003Cvoid> {\n    const features = this.getAllFeatures();\n    for (const feature of features) {\n      await this.migrateFeature(feature);\n      await this.validateFeatureParity(feature);\n    }\n  }\n\n  \u002F\u002F Phase 3: Complete transition\n  async completeTransition(): Promise\u003Cvoid> {\n    await this.validateFullParity();\n    await this.deprecateOldSystem();\n  }\n}\n```\n\n## Success Metrics\n\n- **Code Reduction**: \u003C5,000 lines orchestration (vs 15,000+)\n- **Performance**: 2.49x-7.47x Flash Attention speedup\n- **Search**: 150x-12,500x AgentDB improvement\n- **Memory**: 50-75% usage reduction\n- **Feature Parity**: 100% v2 functionality maintained\n- **SONA**: \u003C0.05ms adaptation time\n- **Integration**: All 213 MCP tools + 19 hook types available\n\n## Related V3 Skills\n\n- `v3-memory-unification` - Memory system integration\n- `v3-performance-optimization` - Performance target validation\n- `v3-swarm-coordination` - Swarm system migration\n- `v3-security-overhaul` - Secure integration patterns","# V3 Deep Integration\n\n## What This Skill Does\n\nTransforms claude-flow from parallel implementation to specialized extension of agentic-flow@alpha, eliminating massive code duplication while achieving performance improvements and feature parity.\n\n## Quick Start\n\n```bash\n# Initialize deep integration\nTask(\"Integration architecture\", \"Design agentic-flow@alpha adapter layer\", \"v3-integration-architect\")\n\n# Feature integration (parallel)\nTask(\"SONA integration\", \"Integrate 5 SONA learning modes\", \"v3-integration-architect\")\nTask(\"Flash Attention\", \"Implement 2.49x-7.47x speedup\", \"v3-integration-architect\")\nTask(\"AgentDB coordination\", \"Setup 150x-12,500x search\", \"v3-integration-architect\")\n```\n\n## Code Deduplication Strategy\n\n### Current Overlap → Integration\n```\n┌─────────────────────────────────────────┐\n│  claude-flow          agentic-flow      │\n├─────────────────────────────────────────┤\n│ SwarmCoordinator  →   Swarm System      │ 80% overlap (eliminate)\n│ AgentManager      →   Agent Lifecycle   │ 70% overlap (eliminate)\n│ TaskScheduler     →   Task Execution    │ 60% overlap (eliminate)\n│ SessionManager    →   Session Mgmt      │ 50% overlap (eliminate)\n└─────────────────────────────────────────┘\n\nTARGET: \u003C5,000 lines (vs 15,000+ currently)\n```\n\n## agentic-flow@alpha Feature Integration\n\n### SONA Learning Modes\n```typescript\nclass SONAIntegration {\n  async initializeMode(mode: SONAMode): Promise\u003Cvoid> {\n    switch(mode) {\n      case 'real-time':   \u002F\u002F ~0.05ms adaptation\n      case 'balanced':    \u002F\u002F general purpose\n      case 'research':    \u002F\u002F deep exploration\n      case 'edge':        \u002F\u002F resource-constrained\n      case 'batch':       \u002F\u002F high-throughput\n    }\n    await this.agenticFlow.sona.setMode(mode);\n  }\n}\n```\n\n### Flash Attention Integration\n```typescript\nclass FlashAttentionIntegration {\n  async optimizeAttention(): Promise\u003CAttentionResult> {\n    return this.agenticFlow.attention.flashAttention({\n      speedupTarget: '2.49x-7.47x',\n      memoryReduction: '50-75%',\n      mechanisms: ['multi-head', 'linear', 'local', 'global']\n    });\n  }\n}\n```\n\n### AgentDB Coordination\n```typescript\nclass AgentDBIntegration {\n  async setupCrossAgentMemory(): Promise\u003Cvoid> {\n    await this.agentdb.enableCrossAgentSharing({\n      indexType: 'HNSW',\n      speedupTarget: '150x-12500x',\n      dimensions: 1536\n    });\n  }\n}\n```\n\n### MCP Tools Integration\n```typescript\nclass MCPToolsIntegration {\n  async integrateBuiltinTools(): Promise\u003Cvoid> {\n    \u002F\u002F Leverage 213 pre-built tools\n    const tools = await this.agenticFlow.mcp.getAvailableTools();\n    await this.registerClaudeFlowSpecificTools(tools);\n\n    \u002F\u002F Use 19 hook types\n    const hookTypes = await this.agenticFlow.hooks.getTypes();\n    await this.configureClaudeFlowHooks(hookTypes);\n  }\n}\n```\n\n## Migration Implementation\n\n### Phase 1: Adapter Layer\n```typescript\nimport { Agent as AgenticFlowAgent } from 'agentic-flow@alpha';\n\nexport class ClaudeFlowAgent extends AgenticFlowAgent {\n  async handleClaudeFlowTask(task: ClaudeTask): Promise\u003CTaskResult> {\n    return this.executeWithSONA(task);\n  }\n\n  \u002F\u002F Backward compatibility\n  async legacyCompatibilityLayer(oldAPI: any): Promise\u003Cany> {\n    return this.adaptToNewAPI(oldAPI);\n  }\n}\n```\n\n### Phase 2: System Migration\n```typescript\nclass SystemMigration {\n  async migrateSwarmCoordination(): Promise\u003Cvoid> {\n    \u002F\u002F Replace SwarmCoordinator (800+ lines) with agentic-flow Swarm\n    const swarmConfig = await this.extractSwarmConfig();\n    await this.agenticFlow.swarm.initialize(swarmConfig);\n  }\n\n  async migrateAgentManagement(): Promise\u003Cvoid> {\n    \u002F\u002F Replace AgentManager (1,736+ lines) with agentic-flow lifecycle\n    const agents = await this.extractActiveAgents();\n    for (const agent of agents) {\n      await this.agenticFlow.agent.create(agent);\n    }\n  }\n\n  async migrateTaskExecution(): Promise\u003Cvoid> {\n    \u002F\u002F Replace TaskScheduler with agentic-flow task graph\n    const tasks = await this.extractTasks();\n    await this.agenticFlow.task.executeGraph(this.buildTaskGraph(tasks));\n  }\n}\n```\n\n### Phase 3: Cleanup\n```typescript\nclass CodeCleanup {\n  async removeDeprecatedCode(): Promise\u003Cvoid> {\n    \u002F\u002F Remove massive duplicate implementations\n    await this.removeFile('src\u002Fcore\u002FSwarmCoordinator.ts');    \u002F\u002F 800+ lines\n    await this.removeFile('src\u002Fagents\u002FAgentManager.ts');      \u002F\u002F 1,736+ lines\n    await this.removeFile('src\u002Ftask\u002FTaskScheduler.ts');       \u002F\u002F 500+ lines\n\n    \u002F\u002F Total reduction: 10,000+ → \u003C5,000 lines\n  }\n}\n```\n\n## RL Algorithm Integration\n\n```typescript\nclass RLIntegration {\n  algorithms = [\n    'PPO', 'DQN', 'A2C', 'MCTS', 'Q-Learning',\n    'SARSA', 'Actor-Critic', 'Decision-Transformer'\n  ];\n\n  async optimizeAgentBehavior(): Promise\u003Cvoid> {\n    for (const algorithm of this.algorithms) {\n      await this.agenticFlow.rl.train(algorithm, {\n        episodes: 1000,\n        rewardFunction: this.claudeFlowRewardFunction\n      });\n    }\n  }\n}\n```\n\n## Performance Integration\n\n### Flash Attention Targets\n```typescript\nconst attentionBenchmark = {\n  baseline: 'current attention mechanism',\n  target: '2.49x-7.47x improvement',\n  memoryReduction: '50-75%',\n  implementation: 'agentic-flow@alpha Flash Attention'\n};\n```\n\n### AgentDB Search Performance\n```typescript\nconst searchBenchmark = {\n  baseline: 'linear search in current systems',\n  target: '150x-12,500x via HNSW indexing',\n  implementation: 'agentic-flow@alpha AgentDB'\n};\n```\n\n## Backward Compatibility\n\n### Gradual Migration\n```typescript\nclass BackwardCompatibility {\n  \u002F\u002F Phase 1: Dual operation\n  async enableDualOperation(): Promise\u003Cvoid> {\n    this.oldSystem.continue();\n    this.newSystem.initialize();\n    this.syncState(this.oldSystem, this.newSystem);\n  }\n\n  \u002F\u002F Phase 2: Feature-by-feature migration\n  async migrateGradually(): Promise\u003Cvoid> {\n    const features = this.getAllFeatures();\n    for (const feature of features) {\n      await this.migrateFeature(feature);\n      await this.validateFeatureParity(feature);\n    }\n  }\n\n  \u002F\u002F Phase 3: Complete transition\n  async completeTransition(): Promise\u003Cvoid> {\n    await this.validateFullParity();\n    await this.deprecateOldSystem();\n  }\n}\n```\n\n## Success Metrics\n\n- **Code Reduction**: \u003C5,000 lines orchestration (vs 15,000+)\n- **Performance**: 2.49x-7.47x Flash Attention speedup\n- **Search**: 150x-12,500x AgentDB improvement\n- **Memory**: 50-75% usage reduction\n- **Feature Parity**: 100% v2 functionality maintained\n- **SONA**: \u003C0.05ms adaptation time\n- **Integration**: All 213 MCP tools + 19 hook types available\n\n## Related V3 Skills\n\n- `v3-memory-unification` - Memory system integration\n- `v3-performance-optimization` - Performance target validation\n- `v3-swarm-coordination` - Swarm system migration\n- `v3-security-overhaul` - Secure integration patterns",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fcli\u002F.claude\u002Fskills\u002Fv3-integration-deep",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":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"V3 Deep Integration\"",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"V3 Deep Integration\"",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill \"V3 Deep Integration\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002Fv3\u002F@claude-flow\u002Fcli\u002F.claude\u002Fskills\u002Fv3-integration-deep\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"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":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"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":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"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":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"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":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"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":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"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",[],[]]