[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6J7HDFHBGAPR18FVX43NEZ3":3,"skill-same:01M6J7HDFHBGAPR18FVX43NEZ3":78},{"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":26,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":48,"commitSha":49,"skillDirectory":50,"forksCount":51,"repositoryHtmlUrl":52,"repositoryHomepageUrl":53,"ownerHtmlUrl":54,"ownerBlogUrl":55,"ownerDescription":56,"updatedAt":57,"install":58,"resources":71},"01M6J7HDFHBGAPR18FVX43NEZ3","oma-coordination",null,"Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI. Use for manual step-by-step coordination and workflow guidance.","gracefullight\u002Fkaltura-downloader","gracefullight","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F11773683?v=4","01M6J7GSY7FXW67X6ZKN19ZPZZ","Eunkwang Shin","01M6J7GT2CQACSHSFZAS5FCN4C",1,"MIT","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-coordination\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000009","前端开发","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"coordination","oma coordination","frontend","cli","workflow","qa","projects","guide","use","backend","mobile","guidance","pm","via","manual","for","2026-11-10 10:12:30",false,"---\nname: oma-coordination\ndescription: Guide for coordinating PM, Frontend, Backend, Mobile, and QA agents on complex projects via CLI. Use for manual step-by-step coordination and workflow guidance.\n---\n\n# Multi-Agent Workflow Guide\n\n## Scheduling\n\n### Goal\nGuide manual multi-agent coordination for complex work that spans PM, frontend, backend, mobile, and QA responsibilities.\n\n### Intent signature\n- User wants step-by-step coordination, manual agent spawning, or multi-domain work planning without full automation.\n- Task spans multiple specialist agents and requires contract alignment.\n\n### When to use\n\n- Complex feature spanning multiple domains (full-stack, mobile)\n- Coordination needed between frontend, backend, mobile, and QA\n- User wants step-by-step guidance for multi-agent coordination\n\n### When NOT to use\n\n- Simple single-domain task -> use the specific agent directly\n- User wants automated execution -> use orchestrator\n- Quick bug fixes or minor changes\n\n### Expected inputs\n- Complex feature or project goal\n- Required domains and priority tiers\n- Workspace\u002Fsession constraints and API\u002Fdata contract needs\n\n### Expected outputs\n- Manual coordination sequence\n- PM task decomposition, agent spawn order, monitoring guidance, and QA review step\n- API\u002Fdata contract alignment checkpoints\n\n### Dependencies\n- PM, frontend, backend, mobile, QA, and orchestrator skills\n- `resources\u002Fexamples.md`\n- CLI `oma agent:spawn` and progress\u002Fresult memory conventions\n\n### Control-flow features\n- Branches by task complexity, priority tiers, dependency ordering, and whether automation is desired\n- Spawns independent same-priority tasks in parallel when appropriate\n- Monitors progress files and contract alignment\n\n## Structural Flow\n\n### Entry\n1. Confirm the task is complex enough for multi-agent coordination.\n2. Start with PM task decomposition.\n3. Identify priority tiers and shared contracts.\n\n### Scenes\n1. **PREPARE**: Define session, domains, and task decomposition needs.\n2. **ACT**: Spawn agents by priority with separate workspaces.\n3. **VERIFY**: Monitor progress and API\u002Fdata contract alignment.\n4. **FINALIZE**: Run QA review and coordinate remediation.\n\n### Transitions\n- If task is simple, route to one specialist.\n- If user wants automated execution, use orchestrator.\n- If QA finds CRITICAL issues, re-spawn responsible agents.\n\n### Failure and recovery\n- If contracts diverge, pause downstream frontend\u002Fmobile work until backend\u002FAPI contract is reconciled.\n- If agent workspaces conflict, split ownership boundaries.\n- If progress stalls, inspect progress files and reissue focused instructions.\n\n### Exit\n- Success: specialist outputs are coordinated and QA-reviewed.\n- Partial success: blocked agents, contract conflicts, or QA failures are explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Read request and domains | `READ` | User prompt and project context |\n| Select agent plan | `SELECT` | PM decomposition and priority tiers |\n| Spawn agents | `CALL_TOOL` | `oma agent:spawn` |\n| Monitor progress | `READ` | `progress-{agent}[-{sessionId}].md` |\n| Validate contracts | `VALIDATE` | API\u002Fdata model alignment |\n| Notify coordination status | `NOTIFY` | Final coordination summary |\n\n### Tools and instruments\n- `oma agent:spawn`, PM\u002Ffrontend\u002Fbackend\u002Fmobile\u002FQA agents\n- Memory\u002Fprogress\u002Fresult files\n- Serena MCP for exploration and modification when used by specialists\n\n### Canonical command path\n```bash\noma agent:spawn pm \"\u003Cplanning task>\" \u003Csession-id> -w .\u002Fpm\noma agent:spawn backend \"\u003Cbackend task>\" \u003Csession-id> -w .\u002Fbackend &\noma agent:spawn frontend \"\u003Cfrontend task>\" \u003Csession-id> -w .\u002Ffrontend &\nwait\n```\n\nWhen native runtime dispatch is available (per-agent target vendor equals the current runtime vendor), prefer the runtime's native subagent path and use `oma agent:spawn` as the cross-vendor fallback — same resolution rule as oma-orchestrator.\n\nUseful `agent:spawn` options: `-m\u002F--model \u003Cvendor>` (CLI vendor override), `--isolation worktree` (git worktree per spawn, prevents file conflicts), `--read-only` (non-destructive tools only, e.g. for review\u002FQA passes).\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `LOCAL_FS` | Progress\u002Fresult files and workspaces |\n| `PROCESS` | Agent spawn commands |\n| `MEMORY` | Session state and task board |\n| `CODEBASE` | Shared contracts and implementation areas |\n\n### Preconditions\n- Task requires multiple domains.\n- PM decomposition can identify independent priority tiers.\n\n### Effects and side effects\n- Spawns or guides multiple agents.\n- Coordinates workspace ownership and QA feedback.\n\n### Guardrails\n\n1. Always start with PM Agent for task decomposition\n2. Spawn independent tasks in parallel (same priority tier)\n3. Define API contracts before frontend\u002Fmobile tasks\n4. QA review is always the final step\n5. Assign separate workspaces to avoid file conflicts (or use `--isolation worktree` for a git worktree per spawn)\n6. Always use Serena MCP tools as the primary method for code exploration and modification\n7. Never skip steps in the workflow; follow each step sequentially without omission\n\n### Workflow\n\n#### Step 1: Plan with PM Agent\n\nPM Agent analyzes requirements, selects tech stack, creates task breakdown with priorities.\n\n#### Step 2: Spawn Agents by Priority\n\nResolve the dispatch path per agent, then spawn:\n\n1. Resolve the per-agent target vendor from oma-config.yaml (`agents:` override, else `model_preset`)\n2. If the target vendor equals the current runtime vendor and a native subagent path exists, use native dispatch\n3. Otherwise use `oma agent:spawn` for that agent\n4. Spawn all same-priority tasks in parallel using background processes\n\n```bash\n# Example: spawn backend and frontend in parallel\noma agent:spawn backend \"task description\" session-id -w .\u002Fbackend &\noma agent:spawn frontend \"task description\" session-id -w .\u002Ffrontend &\nwait\n```\n\n#### Step 3: Monitor & Coordinate\n\n- Use memory read tool to poll `progress-{agent}[-{sessionId}].md` files (spawned agents write the session-suffixed form)\n- Verify API contracts align between agents\n- Ensure shared data models are consistent\n\n#### Step 4: QA Review\n\nSpawn QA Agent last to review all deliverables. Address CRITICAL issues by re-spawning agents.\n\n### Automated Alternative\n\nFor fully automated execution without manual spawning, use the **orchestrator** skill instead.\n\n## References\n\n- Workflow examples: `resources\u002Fexamples.md`\n","# Multi-Agent Workflow Guide\n\n## Scheduling\n\n### Goal\nGuide manual multi-agent coordination for complex work that spans PM, frontend, backend, mobile, and QA responsibilities.\n\n### Intent signature\n- User wants step-by-step coordination, manual agent spawning, or multi-domain work planning without full automation.\n- Task spans multiple specialist agents and requires contract alignment.\n\n### When to use\n\n- Complex feature spanning multiple domains (full-stack, mobile)\n- Coordination needed between frontend, backend, mobile, and QA\n- User wants step-by-step guidance for multi-agent coordination\n\n### When NOT to use\n\n- Simple single-domain task -> use the specific agent directly\n- User wants automated execution -> use orchestrator\n- Quick bug fixes or minor changes\n\n### Expected inputs\n- Complex feature or project goal\n- Required domains and priority tiers\n- Workspace\u002Fsession constraints and API\u002Fdata contract needs\n\n### Expected outputs\n- Manual coordination sequence\n- PM task decomposition, agent spawn order, monitoring guidance, and QA review step\n- API\u002Fdata contract alignment checkpoints\n\n### Dependencies\n- PM, frontend, backend, mobile, QA, and orchestrator skills\n- `resources\u002Fexamples.md`\n- CLI `oma agent:spawn` and progress\u002Fresult memory conventions\n\n### Control-flow features\n- Branches by task complexity, priority tiers, dependency ordering, and whether automation is desired\n- Spawns independent same-priority tasks in parallel when appropriate\n- Monitors progress files and contract alignment\n\n## Structural Flow\n\n### Entry\n1. Confirm the task is complex enough for multi-agent coordination.\n2. Start with PM task decomposition.\n3. Identify priority tiers and shared contracts.\n\n### Scenes\n1. **PREPARE**: Define session, domains, and task decomposition needs.\n2. **ACT**: Spawn agents by priority with separate workspaces.\n3. **VERIFY**: Monitor progress and API\u002Fdata contract alignment.\n4. **FINALIZE**: Run QA review and coordinate remediation.\n\n### Transitions\n- If task is simple, route to one specialist.\n- If user wants automated execution, use orchestrator.\n- If QA finds CRITICAL issues, re-spawn responsible agents.\n\n### Failure and recovery\n- If contracts diverge, pause downstream frontend\u002Fmobile work until backend\u002FAPI contract is reconciled.\n- If agent workspaces conflict, split ownership boundaries.\n- If progress stalls, inspect progress files and reissue focused instructions.\n\n### Exit\n- Success: specialist outputs are coordinated and QA-reviewed.\n- Partial success: blocked agents, contract conflicts, or QA failures are explicit.\n\n## Logical Operations\n\n### Actions\n| Action | SSL primitive | Evidence |\n|--------|---------------|----------|\n| Read request and domains | `READ` | User prompt and project context |\n| Select agent plan | `SELECT` | PM decomposition and priority tiers |\n| Spawn agents | `CALL_TOOL` | `oma agent:spawn` |\n| Monitor progress | `READ` | `progress-{agent}[-{sessionId}].md` |\n| Validate contracts | `VALIDATE` | API\u002Fdata model alignment |\n| Notify coordination status | `NOTIFY` | Final coordination summary |\n\n### Tools and instruments\n- `oma agent:spawn`, PM\u002Ffrontend\u002Fbackend\u002Fmobile\u002FQA agents\n- Memory\u002Fprogress\u002Fresult files\n- Serena MCP for exploration and modification when used by specialists\n\n### Canonical command path\n```bash\noma agent:spawn pm \"\u003Cplanning task>\" \u003Csession-id> -w .\u002Fpm\noma agent:spawn backend \"\u003Cbackend task>\" \u003Csession-id> -w .\u002Fbackend &\noma agent:spawn frontend \"\u003Cfrontend task>\" \u003Csession-id> -w .\u002Ffrontend &\nwait\n```\n\nWhen native runtime dispatch is available (per-agent target vendor equals the current runtime vendor), prefer the runtime's native subagent path and use `oma agent:spawn` as the cross-vendor fallback — same resolution rule as oma-orchestrator.\n\nUseful `agent:spawn` options: `-m\u002F--model \u003Cvendor>` (CLI vendor override), `--isolation worktree` (git worktree per spawn, prevents file conflicts), `--read-only` (non-destructive tools only, e.g. for review\u002FQA passes).\n\n### Resource scope\n| Scope | Resource target |\n|-------|-----------------|\n| `LOCAL_FS` | Progress\u002Fresult files and workspaces |\n| `PROCESS` | Agent spawn commands |\n| `MEMORY` | Session state and task board |\n| `CODEBASE` | Shared contracts and implementation areas |\n\n### Preconditions\n- Task requires multiple domains.\n- PM decomposition can identify independent priority tiers.\n\n### Effects and side effects\n- Spawns or guides multiple agents.\n- Coordinates workspace ownership and QA feedback.\n\n### Guardrails\n\n1. Always start with PM Agent for task decomposition\n2. Spawn independent tasks in parallel (same priority tier)\n3. Define API contracts before frontend\u002Fmobile tasks\n4. QA review is always the final step\n5. Assign separate workspaces to avoid file conflicts (or use `--isolation worktree` for a git worktree per spawn)\n6. Always use Serena MCP tools as the primary method for code exploration and modification\n7. Never skip steps in the workflow; follow each step sequentially without omission\n\n### Workflow\n\n#### Step 1: Plan with PM Agent\n\nPM Agent analyzes requirements, selects tech stack, creates task breakdown with priorities.\n\n#### Step 2: Spawn Agents by Priority\n\nResolve the dispatch path per agent, then spawn:\n\n1. Resolve the per-agent target vendor from oma-config.yaml (`agents:` override, else `model_preset`)\n2. If the target vendor equals the current runtime vendor and a native subagent path exists, use native dispatch\n3. Otherwise use `oma agent:spawn` for that agent\n4. Spawn all same-priority tasks in parallel using background processes\n\n```bash\n# Example: spawn backend and frontend in parallel\noma agent:spawn backend \"task description\" session-id -w .\u002Fbackend &\noma agent:spawn frontend \"task description\" session-id -w .\u002Ffrontend &\nwait\n```\n\n#### Step 3: Monitor & Coordinate\n\n- Use memory read tool to poll `progress-{agent}[-{sessionId}].md` files (spawned agents write the session-suffixed form)\n- Verify API contracts align between agents\n- Ensure shared data models are consistent\n\n#### Step 4: QA Review\n\nSpawn QA Agent last to review all deliverables. Address CRITICAL issues by re-spawning agents.\n\n### Automated Alternative\n\nFor fully automated execution without manual spawning, use the **orchestrator** skill instead.\n\n## References\n\n- Workflow examples: `resources\u002Fexamples.md`\n",{"name":5,"description":7},"main","ba5c378471d265938d6f5036c6b22c8e4a385c94",".agents\u002Fskills\u002Foma-coordination",0,"https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader","https:\u002F\u002Fchromewebstore.google.com\u002Fdetail\u002Fkaltura-downloader\u002Fmmeomcgalmlhandhdgmfkjeaindgjhle","https:\u002F\u002Fgithub.com\u002Fgracefullight","https:\u002F\u002Fgracefullight.dev","I literally can’t sleep if I don’t code for even a single day.","2026-10-06 01:43:25",{"source":8,"skillName":5,"commands":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add gracefullight\u002Fkaltura-downloader --skill oma-coordination",{"tool":64,"command":65},"bunx","bunx skills add gracefullight\u002Fkaltura-downloader --skill oma-coordination",{"tool":67,"command":68},"pnpm","pnpm dlx skills add gracefullight\u002Fkaltura-downloader --skill oma-coordination","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-coordination\u002FSKILL.md",true,[72],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"resources\u002Fexamples.md","REFERENCE","参考文档",2123,"https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Foma-coordination\u002Fresources\u002Fexamples.md",[79,85,95,101,108,117],{"skillNo":80,"name":81,"nameZh":6,"description":6,"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":43},"01M6J7W2SFEJKP2QSQBA68Q49X","work","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fwork\u002FSKILL.md",[],[81],{"skillNo":86,"name":87,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":93,"publishedAt":43},"01M6J7W17HBR9RJHF63SAWTR3X","video","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fvideo\u002FSKILL.md",[90],{"categoryNo":91,"categoryName":92,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体",[94],"Video",{"skillNo":96,"name":97,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":98,"categories":99,"keywords":100,"publishedAt":43},"01M6J7VZMFE8WVH33K0DEPC2YR","ultrawork","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fultrawork\u002FSKILL.md",[],[97],{"skillNo":102,"name":103,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":43},"01M6J7VY165B9KNA578KWF8RQA","tools","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Ftools\u002FSKILL.md",[],[107],"Tools",{"skillNo":109,"name":110,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":43},"01M6J7VWBNB3JGJMYRRF7C764J","stack-set","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fstack-set\u002FSKILL.md",[],[114,115,116],"SET","stack","stack set",{"skillNo":118,"name":119,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":122,"publishedAt":43},"01M6J7VTSHG09PBTYRHQ7V8RX2","setup","https:\u002F\u002Fgithub.com\u002Fgracefullight\u002Fkaltura-downloader\u002Fblob\u002Fmain\u002F.qwen\u002Fskills\u002Fsetup\u002FSKILL.md",[],[119]]