[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6BXM2XPWREV0HSH87ZKVT5F":3,"skill-same:01M6BXM2XPWREV0HSH87ZKVT5F":59},{"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":31,"linkOnly":32,"markdownContent":33,"markdownBody":34,"frontMatter":35,"refName":36,"commitSha":37,"skillDirectory":38,"forksCount":39,"repositoryHtmlUrl":40,"repositoryHomepageUrl":6,"ownerHtmlUrl":41,"ownerBlogUrl":42,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6BXM2XPWREV0HSH87ZKVT5F","Swarm Orchestration",null,"Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.","diegopacheco\u002Fai-playground","diegopacheco","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F121278?v=4","01M6BXCP8P7GGSJ8M1W2MFDTGT","Diego Pacheco","01M6BXCPD3WM51H465XW9YM4BV",21,"Unlicense","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fswarm-orchestration\u002FSKILL.md",[],[19,20,5,21,22,23,24,25,26,27,28,29,30],"orchestration","swarm","agentic","workflows","distributed","orchestrate","topology","flow","execution","coordination","multi-agent","parallel","2026-11-10 10:12:30",false,"---\nname: \"Swarm Orchestration\"\ndescription: \"Orchestrate multi-agent swarms with agentic-flow for parallel task execution, dynamic topology, and intelligent coordination. Use when scaling beyond single agents, implementing complex workflows, or building distributed AI systems.\"\n---\n\n# Swarm Orchestration\n\n## What This Skill Does\n\nOrchestrates multi-agent swarms using agentic-flow's advanced coordination system. Supports mesh, hierarchical, and adaptive topologies with automatic task distribution, load balancing, and fault tolerance.\n\n## Prerequisites\n\n- agentic-flow v1.5.11+\n- Node.js 18+\n- Understanding of distributed systems (helpful)\n\n## Quick Start\n\n```bash\n# Initialize swarm\nnpx agentic-flow hooks swarm-init --topology mesh --max-agents 5\n\n# Spawn agents\nnpx agentic-flow hooks agent-spawn --type coder\nnpx agentic-flow hooks agent-spawn --type tester\nnpx agentic-flow hooks agent-spawn --type reviewer\n\n# Orchestrate task\nnpx agentic-flow hooks task-orchestrate \\\n  --task \"Build REST API with tests\" \\\n  --mode parallel\n```\n\n## Topology Patterns\n\n### 1. Mesh (Peer-to-Peer)\n```typescript\n\u002F\u002F Equal peers, distributed decision-making\nawait swarm.init({\n  topology: 'mesh',\n  agents: ['coder', 'tester', 'reviewer'],\n  communication: 'broadcast'\n});\n```\n\n### 2. Hierarchical (Queen-Worker)\n```typescript\n\u002F\u002F Centralized coordination, specialized workers\nawait swarm.init({\n  topology: 'hierarchical',\n  queen: 'architect',\n  workers: ['backend-dev', 'frontend-dev', 'db-designer']\n});\n```\n\n### 3. Adaptive (Dynamic)\n```typescript\n\u002F\u002F Automatically switches topology based on task\nawait swarm.init({\n  topology: 'adaptive',\n  optimization: 'task-complexity'\n});\n```\n\n## Task Orchestration\n\n### Parallel Execution\n```typescript\n\u002F\u002F Execute tasks concurrently\nconst results = await swarm.execute({\n  tasks: [\n    { agent: 'coder', task: 'Implement API endpoints' },\n    { agent: 'frontend', task: 'Build UI components' },\n    { agent: 'tester', task: 'Write test suite' }\n  ],\n  mode: 'parallel',\n  timeout: 300000 \u002F\u002F 5 minutes\n});\n```\n\n### Pipeline Execution\n```typescript\n\u002F\u002F Sequential pipeline with dependencies\nawait swarm.pipeline([\n  { stage: 'design', agent: 'architect' },\n  { stage: 'implement', agent: 'coder', after: 'design' },\n  { stage: 'test', agent: 'tester', after: 'implement' },\n  { stage: 'review', agent: 'reviewer', after: 'test' }\n]);\n```\n\n### Adaptive Execution\n```typescript\n\u002F\u002F Let swarm decide execution strategy\nawait swarm.autoOrchestrate({\n  goal: 'Build production-ready API',\n  constraints: {\n    maxTime: 3600,\n    maxAgents: 8,\n    quality: 'high'\n  }\n});\n```\n\n## Memory Coordination\n\n```typescript\n\u002F\u002F Share state across swarm\nawait swarm.memory.store('api-schema', {\n  endpoints: [...],\n  models: [...]\n});\n\n\u002F\u002F Agents read shared memory\nconst schema = await swarm.memory.retrieve('api-schema');\n```\n\n## Advanced Features\n\n### Load Balancing\n```typescript\n\u002F\u002F Automatic work distribution\nawait swarm.enableLoadBalancing({\n  strategy: 'dynamic',\n  metrics: ['cpu', 'memory', 'task-queue']\n});\n```\n\n### Fault Tolerance\n```typescript\n\u002F\u002F Handle agent failures\nawait swarm.setResiliency({\n  retry: { maxAttempts: 3, backoff: 'exponential' },\n  fallback: 'reassign-task'\n});\n```\n\n### Performance Monitoring\n```typescript\n\u002F\u002F Track swarm metrics\nconst metrics = await swarm.getMetrics();\n\u002F\u002F { throughput, latency, success_rate, agent_utilization }\n```\n\n## Integration with Hooks\n\n```bash\n# Pre-task coordination\nnpx agentic-flow hooks pre-task --description \"Build API\"\n\n# Post-task synchronization\nnpx agentic-flow hooks post-task --task-id \"task-123\"\n\n# Session restore\nnpx agentic-flow hooks session-restore --session-id \"swarm-001\"\n```\n\n## Best Practices\n\n1. **Start small**: Begin with 2-3 agents, scale up\n2. **Use memory**: Share context through swarm memory\n3. **Monitor metrics**: Track performance and bottlenecks\n4. **Enable hooks**: Automatic coordination and sync\n5. **Set timeouts**: Prevent hung tasks\n\n## Troubleshooting\n\n### Issue: Agents not coordinating\n**Solution**: Verify memory access and enable hooks\n\n### Issue: Poor performance\n**Solution**: Check topology (use adaptive) and enable load balancing\n\n## Learn More\n\n- Swarm Guide: docs\u002Fswarm\u002Forchestration.md\n- Topology Patterns: docs\u002Fswarm\u002Ftopologies.md\n- Hooks Integration: docs\u002Fhooks\u002Fcoordination.md\n","# Swarm Orchestration\n\n## What This Skill Does\n\nOrchestrates multi-agent swarms using agentic-flow's advanced coordination system. Supports mesh, hierarchical, and adaptive topologies with automatic task distribution, load balancing, and fault tolerance.\n\n## Prerequisites\n\n- agentic-flow v1.5.11+\n- Node.js 18+\n- Understanding of distributed systems (helpful)\n\n## Quick Start\n\n```bash\n# Initialize swarm\nnpx agentic-flow hooks swarm-init --topology mesh --max-agents 5\n\n# Spawn agents\nnpx agentic-flow hooks agent-spawn --type coder\nnpx agentic-flow hooks agent-spawn --type tester\nnpx agentic-flow hooks agent-spawn --type reviewer\n\n# Orchestrate task\nnpx agentic-flow hooks task-orchestrate \\\n  --task \"Build REST API with tests\" \\\n  --mode parallel\n```\n\n## Topology Patterns\n\n### 1. Mesh (Peer-to-Peer)\n```typescript\n\u002F\u002F Equal peers, distributed decision-making\nawait swarm.init({\n  topology: 'mesh',\n  agents: ['coder', 'tester', 'reviewer'],\n  communication: 'broadcast'\n});\n```\n\n### 2. Hierarchical (Queen-Worker)\n```typescript\n\u002F\u002F Centralized coordination, specialized workers\nawait swarm.init({\n  topology: 'hierarchical',\n  queen: 'architect',\n  workers: ['backend-dev', 'frontend-dev', 'db-designer']\n});\n```\n\n### 3. Adaptive (Dynamic)\n```typescript\n\u002F\u002F Automatically switches topology based on task\nawait swarm.init({\n  topology: 'adaptive',\n  optimization: 'task-complexity'\n});\n```\n\n## Task Orchestration\n\n### Parallel Execution\n```typescript\n\u002F\u002F Execute tasks concurrently\nconst results = await swarm.execute({\n  tasks: [\n    { agent: 'coder', task: 'Implement API endpoints' },\n    { agent: 'frontend', task: 'Build UI components' },\n    { agent: 'tester', task: 'Write test suite' }\n  ],\n  mode: 'parallel',\n  timeout: 300000 \u002F\u002F 5 minutes\n});\n```\n\n### Pipeline Execution\n```typescript\n\u002F\u002F Sequential pipeline with dependencies\nawait swarm.pipeline([\n  { stage: 'design', agent: 'architect' },\n  { stage: 'implement', agent: 'coder', after: 'design' },\n  { stage: 'test', agent: 'tester', after: 'implement' },\n  { stage: 'review', agent: 'reviewer', after: 'test' }\n]);\n```\n\n### Adaptive Execution\n```typescript\n\u002F\u002F Let swarm decide execution strategy\nawait swarm.autoOrchestrate({\n  goal: 'Build production-ready API',\n  constraints: {\n    maxTime: 3600,\n    maxAgents: 8,\n    quality: 'high'\n  }\n});\n```\n\n## Memory Coordination\n\n```typescript\n\u002F\u002F Share state across swarm\nawait swarm.memory.store('api-schema', {\n  endpoints: [...],\n  models: [...]\n});\n\n\u002F\u002F Agents read shared memory\nconst schema = await swarm.memory.retrieve('api-schema');\n```\n\n## Advanced Features\n\n### Load Balancing\n```typescript\n\u002F\u002F Automatic work distribution\nawait swarm.enableLoadBalancing({\n  strategy: 'dynamic',\n  metrics: ['cpu', 'memory', 'task-queue']\n});\n```\n\n### Fault Tolerance\n```typescript\n\u002F\u002F Handle agent failures\nawait swarm.setResiliency({\n  retry: { maxAttempts: 3, backoff: 'exponential' },\n  fallback: 'reassign-task'\n});\n```\n\n### Performance Monitoring\n```typescript\n\u002F\u002F Track swarm metrics\nconst metrics = await swarm.getMetrics();\n\u002F\u002F { throughput, latency, success_rate, agent_utilization }\n```\n\n## Integration with Hooks\n\n```bash\n# Pre-task coordination\nnpx agentic-flow hooks pre-task --description \"Build API\"\n\n# Post-task synchronization\nnpx agentic-flow hooks post-task --task-id \"task-123\"\n\n# Session restore\nnpx agentic-flow hooks session-restore --session-id \"swarm-001\"\n```\n\n## Best Practices\n\n1. **Start small**: Begin with 2-3 agents, scale up\n2. **Use memory**: Share context through swarm memory\n3. **Monitor metrics**: Track performance and bottlenecks\n4. **Enable hooks**: Automatic coordination and sync\n5. **Set timeouts**: Prevent hung tasks\n\n## Troubleshooting\n\n### Issue: Agents not coordinating\n**Solution**: Verify memory access and enable hooks\n\n### Issue: Poor performance\n**Solution**: Check topology (use adaptive) and enable load balancing\n\n## Learn More\n\n- Swarm Guide: docs\u002Fswarm\u002Forchestration.md\n- Topology Patterns: docs\u002Fswarm\u002Ftopologies.md\n- Hooks Integration: docs\u002Fhooks\u002Fcoordination.md\n",{"name":5,"description":7},"main","90d379e95fcc23dd9759654c345424e1752b0f3a","pocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fswarm-orchestration",9,"https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground","https:\u002F\u002Fgithub.com\u002Fdiegopacheco","http:\u002F\u002Fdiego-pacheco.blogspot.com","Brazilian Hands-on Software Architect | 20+ years in Tech | Author | Father. Opinions are my own!","2026-11-07 09:01:46",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add diegopacheco\u002Fai-playground --skill \"Swarm Orchestration\"",{"tool":51,"command":52},"bunx","bunx skills add diegopacheco\u002Fai-playground --skill \"Swarm Orchestration\"",{"tool":54,"command":55},"pnpm","pnpm dlx skills add diegopacheco\u002Fai-playground --skill \"Swarm Orchestration\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fclaude-flow-fun\u002F.claude\u002Fskills\u002Fswarm-orchestration\u002FSKILL.md",true,[],[60,78,88,101,117,136],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":71,"publishedAt":31},"01M6WJ537DN520XY8MSW9ZV0RP","word-count","Counts the words, lines and characters of a text or a file.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Ftext-skills\u002Fword-count\u002FSKILL.md",[66],{"categoryNo":67,"categoryName":68,"taxonomyType":69,"taxonomyTypeDesc":70},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[72,73,74,75,76,77],"count","word count","Word","characters","text","file",{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":31},"01M6WJ4Y2GT5SECWAKKYHGES4F","slugify","Turns a title or a sentence into a URL slug, lowercase words joined by hyphens with accents removed.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Ftext-skills\u002Fslugify\u002FSKILL.md",[],[80,85,86,87],"title","with","URL",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":31},"01M6WJ4V9CWHT9NVCD441VK5MH","json-format","Validates a JSON file and pretty prints it with two space indentation, or reports where the JSON is invalid.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Fdev-skills\u002Fjson-format\u002FSKILL.md",[],[95,96,97,77,98,99,100,86],"json","format","json format","reports","invalid","it",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":107,"publishedAt":31},"01M6WJ4QMRKW8EFP71F4KS2DHE","commit-message","Writes a conventional commit message for the staged git changes.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002Fupstream-skills\u002Fdev-skills\u002Fcommit-message\u002FSKILL.md",[],[108,109,110,111,112,113,114,115,116],"commit","commit message","message","git","conventional commit","for","changes","staged","conventional commit message",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":31},"01M6WJ4MAM2CJH0GWYXFBB9GQC","skills-gateway","Gateway and router to a catalog of skills that are not registered directly. Use it before any task a specialized skill could handle, such as text, JSON or git chores. It finds the right skill and loads its instructions.","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fskills-gateway-router\u002F.claude\u002Fskills\u002Fskills-gateway\u002FSKILL.md",[],[124,125,100,126,127,111,128,95,76,129,130,131,132,133,134,135],"skills gateway","gateway","task","loads","Bash","node","specialized","instructions","catalog","use","router","as",{"skillNo":137,"name":138,"nameZh":6,"description":139,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":140,"categories":141,"keywords":142,"publishedAt":31},"01M6M2PYJJQKMWGX7XT7ZJK0H3","decision-log","Record, list, show and supersede architecture decisions that persist across sessions in the shared agent infra state store. Use when the user says \"record this decision\", \"log an ADR\", \"what did we decide about\", \"list decisions\", or \"supersede decision\".","https:\u002F\u002Fgithub.com\u002Fdiegopacheco\u002Fai-playground\u002Fblob\u002Fmain\u002Fpocs\u002Fagent-skills-infra-poc\u002Fskills\u002Fdecision-log\u002FSKILL.md",[],[143,144,145,146,147,148,149,150,151,152,133,153,154,155,156,157,158,159,160,161],"decision log","log","decision","persist","architecture","state","adr","decide","decisions","list","show","infra","record","across","shared","store","about","supersede","sessions"]