[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M71HB26Z65B0PNGWVG7KB1DR":3,"skill-same:01M71HB26Z65B0PNGWVG7KB1DR":62},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":39,"commitSha":40,"skillDirectory":41,"forksCount":42,"repositoryHtmlUrl":43,"repositoryHomepageUrl":44,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M71HB26Z65B0PNGWVG7KB1DR","dispatch-agents",null,"Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).","danielvm-git\u002Fbigpowers","danielvm-git","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F1020864?v=4","01M71H1N1CTQ529S0KN7KETVG6","Daniel V M","01M71H1N218Y3S8WHCJ58NPRSW",290,"MIT","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002F.codebuddy\u002Fskills\u002Fdispatch-agents\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"dispatch agents","dispatch","delegate","when","tasks","review","run","sonnet","subagents","parallel","review gate","speed","use","task","gate","2026-11-10 10:12:30",false,"---\nname: dispatch-agents\nmodel: sonnet\ndescription: \"Dispatch multiple subagents in parallel on independent tasks. No waiting between them — all run concurrently. Use when tasks are truly decoupled and speed matters. Distinct from delegate-task (concurrent here, no inter-task review gate).\"\n---\n\n\u003C!-- story: e09s04 -->\n\u003C!-- story: e45s38 -->\n\u003C!-- story: e45s11 -->\n\n\n\u003C!-- story: e45s30 -->\n\n# Dispatch Agents\n> **HARD GATE** — **HARD GATE** — Agent work must be parallelizable and have explicit synchronization points. Do NOT dispatch work that has hidden dependencies between agents.\n\n\nRun multiple subagents in parallel on independent tasks. Use when tasks are genuinely decoupled — no agent needs the output of another to start.\n\n**Distinct from `delegate-task`:** This skill maximizes throughput via concurrency. There is no sequential review gate between tasks. Use `delegate-task` instead when a single task needs careful two-stage oversight before proceeding.\n\n## When to use\n\n- Tasks that can run simultaneously without shared state\n- Large plans that can be broken into parallel workstreams\n- Exploration: gather information from multiple parts of the codebase at once\n\n## When NOT to use\n\n- Task B depends on Task A's output\n- You need to review Task A before Task B can start safely\n- The tasks share a file and concurrent edits would conflict\n\n## Process\n\n### 1. Confirm independence\n\nBefore dispatching, verify each task pair is truly independent:\n- No shared files being written\n- No shared state (DB migrations, config files)\n- No ordering dependency between outcomes\n\nIf any two tasks conflict, sequence them with `delegate-task` or `execute-plan` instead.\n\n## Subagent depth tiers (e45s30)\n\nMap `effort:` frontmatter and story `risk:` to prompt depth — do not send `minimal_decisive` agents a `full_maturity` brief.\n\n| Tier | When | Brief shape | Token budget |\n|------|------|-------------|----------------|\n| `full_maturity` | `effort: heavy`, `risk: P0`, security-sensitive diffs | Full `task_brief` + CONVENTIONS excerpts + threat model if present | Full envelope |\n| `standard` | `effort: standard`, `risk: P1`–`P2` | Standard `task_brief` fields below | Default |\n| `minimal_decisive` | `effort: light`, `risk: P3`, read-only exploration | `goal` + `verify` + `in_scope` only | ≤15 lines |\n\nRecord `depth: \u003Ctier>` in the Agent tool description when dispatching.\n\n### 2. Write typed task briefs (Orca message protocol)\n\nBefore writing briefs, read `specs\u002Fstate.yaml` if it exists — each agent gets only the decisions relevant to its task, nothing else.\n\nEvery inter-agent message uses a **typed envelope** — no freeform prose between waves:\n\n| `type` | When | Required fields |\n|--------|------|-----------------|\n| `task_brief` | Dispatch | `task_id`, `goal`, `in_scope`, `out_of_bounds`, `verify`, `prior_decisions` |\n| `checkpoint` | Mid-wave progress | `task_id`, `status` (`running`\\|`blocked`), `comment` (one line) |\n| `result` | Agent return | `task_id`, `exit` (`pass`\\|`fail`), `summary`, `verify_output` |\n| `circuit_open` | 3 consecutive failures | `task_id`, `failures` (3), `escalate_to` (`user`) |\n\nExample `task_brief` (each agent starts cold — brief size directly controls token cost and hallucination risk):\n\n```yaml\ntype: task_brief\ntask_id: agent-1\ngoal: [one sentence — what success looks like]\nin_scope: [explicit file or module list]\nout_of_bounds: [what NOT to touch]\nverify: [runnable command]\nprior_decisions: [relevant entries from specs\u002Fstate.yaml — omit if none]\n```\n\nEmit **`checkpoint`** comments when an agent is slow or blocked — one line, no stack traces. Parent reads checkpoints before spawning follow-ups.\n\nDo not include the full conversation, full file contents, or decisions unrelated to this agent's task.\n\n### 3. Circuit breaker + iterative retrieval (max 3 cycles)\n\nTrack **consecutive failures per `task_id`**. On the **3rd consecutive `result.exit: fail`** for the same task, emit `type: circuit_open` and **stop dispatching** that task — escalate to user with the three failure summaries. Reset counter on any `pass`.\n\nAfter each wave completes:\n1. **Dispatch** — run parallel agents with typed `task_brief` envelopes.\n2. **Evaluate** — read `result` messages; list gaps vs goal; honor open circuits.\n3. **Refine** — tighten briefs or spawn follow-up agents (max **3 cycles** total).\n\nStop when gaps empty, circuit opens, or cycle 3 reached — escalate to user. If agents go silent without returning, invoke `diagnose-stall` before spawning another wave.\n\n### 4. Dispatch in parallel\n\nSpawn all agents in a single message using multiple Agent tool calls. Each agent gets its own complete brief.\n\n```\nAgent 1: brief for task A\nAgent 2: brief for task B\nAgent 3: brief for task C\n```\n\n### 5. Collect and review results\n\nWhen all agents return: review each result, run verify commands, check diffs for scope violations.\n\n### 6. Integrate\n\nMerge accepted results. Resolve conflicts manually; note in summary.\n\nReport: which tasks succeeded, which need revision, overall verify status.\n\n## Verify\n→ verify: `test -f skills\u002Fdispatch-agents\u002FSKILL.md && test -f scripts\u002Flib\u002Fcompleteness-critic.sh`\n","\u003C!-- story: e09s04 -->\n\u003C!-- story: e45s38 -->\n\u003C!-- story: e45s11 -->\n\n\n\u003C!-- story: e45s30 -->\n\n# Dispatch Agents\n> **HARD GATE** — **HARD GATE** — Agent work must be parallelizable and have explicit synchronization points. Do NOT dispatch work that has hidden dependencies between agents.\n\n\nRun multiple subagents in parallel on independent tasks. Use when tasks are genuinely decoupled — no agent needs the output of another to start.\n\n**Distinct from `delegate-task`:** This skill maximizes throughput via concurrency. There is no sequential review gate between tasks. Use `delegate-task` instead when a single task needs careful two-stage oversight before proceeding.\n\n## When to use\n\n- Tasks that can run simultaneously without shared state\n- Large plans that can be broken into parallel workstreams\n- Exploration: gather information from multiple parts of the codebase at once\n\n## When NOT to use\n\n- Task B depends on Task A's output\n- You need to review Task A before Task B can start safely\n- The tasks share a file and concurrent edits would conflict\n\n## Process\n\n### 1. Confirm independence\n\nBefore dispatching, verify each task pair is truly independent:\n- No shared files being written\n- No shared state (DB migrations, config files)\n- No ordering dependency between outcomes\n\nIf any two tasks conflict, sequence them with `delegate-task` or `execute-plan` instead.\n\n## Subagent depth tiers (e45s30)\n\nMap `effort:` frontmatter and story `risk:` to prompt depth — do not send `minimal_decisive` agents a `full_maturity` brief.\n\n| Tier | When | Brief shape | Token budget |\n|------|------|-------------|----------------|\n| `full_maturity` | `effort: heavy`, `risk: P0`, security-sensitive diffs | Full `task_brief` + CONVENTIONS excerpts + threat model if present | Full envelope |\n| `standard` | `effort: standard`, `risk: P1`–`P2` | Standard `task_brief` fields below | Default |\n| `minimal_decisive` | `effort: light`, `risk: P3`, read-only exploration | `goal` + `verify` + `in_scope` only | ≤15 lines |\n\nRecord `depth: \u003Ctier>` in the Agent tool description when dispatching.\n\n### 2. Write typed task briefs (Orca message protocol)\n\nBefore writing briefs, read `specs\u002Fstate.yaml` if it exists — each agent gets only the decisions relevant to its task, nothing else.\n\nEvery inter-agent message uses a **typed envelope** — no freeform prose between waves:\n\n| `type` | When | Required fields |\n|--------|------|-----------------|\n| `task_brief` | Dispatch | `task_id`, `goal`, `in_scope`, `out_of_bounds`, `verify`, `prior_decisions` |\n| `checkpoint` | Mid-wave progress | `task_id`, `status` (`running`\\|`blocked`), `comment` (one line) |\n| `result` | Agent return | `task_id`, `exit` (`pass`\\|`fail`), `summary`, `verify_output` |\n| `circuit_open` | 3 consecutive failures | `task_id`, `failures` (3), `escalate_to` (`user`) |\n\nExample `task_brief` (each agent starts cold — brief size directly controls token cost and hallucination risk):\n\n```yaml\ntype: task_brief\ntask_id: agent-1\ngoal: [one sentence — what success looks like]\nin_scope: [explicit file or module list]\nout_of_bounds: [what NOT to touch]\nverify: [runnable command]\nprior_decisions: [relevant entries from specs\u002Fstate.yaml — omit if none]\n```\n\nEmit **`checkpoint`** comments when an agent is slow or blocked — one line, no stack traces. Parent reads checkpoints before spawning follow-ups.\n\nDo not include the full conversation, full file contents, or decisions unrelated to this agent's task.\n\n### 3. Circuit breaker + iterative retrieval (max 3 cycles)\n\nTrack **consecutive failures per `task_id`**. On the **3rd consecutive `result.exit: fail`** for the same task, emit `type: circuit_open` and **stop dispatching** that task — escalate to user with the three failure summaries. Reset counter on any `pass`.\n\nAfter each wave completes:\n1. **Dispatch** — run parallel agents with typed `task_brief` envelopes.\n2. **Evaluate** — read `result` messages; list gaps vs goal; honor open circuits.\n3. **Refine** — tighten briefs or spawn follow-up agents (max **3 cycles** total).\n\nStop when gaps empty, circuit opens, or cycle 3 reached — escalate to user. If agents go silent without returning, invoke `diagnose-stall` before spawning another wave.\n\n### 4. Dispatch in parallel\n\nSpawn all agents in a single message using multiple Agent tool calls. Each agent gets its own complete brief.\n\n```\nAgent 1: brief for task A\nAgent 2: brief for task B\nAgent 3: brief for task C\n```\n\n### 5. Collect and review results\n\nWhen all agents return: review each result, run verify commands, check diffs for scope violations.\n\n### 6. Integrate\n\nMerge accepted results. Resolve conflicts manually; note in summary.\n\nReport: which tasks succeeded, which need revision, overall verify status.\n\n## Verify\n→ verify: `test -f skills\u002Fdispatch-agents\u002FSKILL.md && test -f scripts\u002Flib\u002Fcompleteness-critic.sh`\n",{"name":5,"model":26,"description":7},"main","72f5e4c8b43f60cf86b37078ad8cd7e22daf67aa",".codebuddy\u002Fskills\u002Fdispatch-agents",24,"https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers","https:\u002F\u002Fdanielvm-git.github.io\u002Fbigpowers\u002F","https:\u002F\u002Fgithub.com\u002Fdanielvm-git","danielvm.net","2026-11-10 01:18:54",{"source":8,"skillName":5,"commands":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add danielvm-git\u002Fbigpowers --skill dispatch-agents",{"tool":54,"command":55},"bunx","bunx skills add danielvm-git\u002Fbigpowers --skill dispatch-agents",{"tool":57,"command":58},"pnpm","pnpm dlx skills add danielvm-git\u002Fbigpowers --skill dispatch-agents","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002F.codebuddy\u002Fskills\u002Fdispatch-agents\u002FSKILL.md",true,[],[63,83,90,117,140,161],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":74,"publishedAt":34},"01M71KBG9F8X644MJB16H4V8M7","skill-verify-fail-open-fixture","Negative-path fixture for run-skill-verify.sh — must never PASS.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fspecs\u002Fverifications\u002Ffixtures\u002Fskill-verify-fail-open\u002FSKILL.md",[69],{"categoryNo":70,"categoryName":71,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[75,76,77,78,79,80,25,81,82],"fixture","open","verify","skill verify fail open fixture","skill verify","path","for","never",{"skillNo":84,"name":85,"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":86,"categories":87,"keywords":88,"publishedAt":34},"01M71KBE3BKEMKNE0C5DGVDWZH","negative-path","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fspecs\u002Fverifications\u002Ffixtures\u002Fnegative-path\u002FSKILL.md",[],[89,80],"negative path",{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":99,"publishedAt":34},"01M71KBBGF7Y4EB4AMHBZ8CJFC","write-document","Write, organize, and sync high-integrity technical documents using the BMAD methodology. Ensures every document is Bold, Minimal, Actionable, and Durable. Use when creating architectural docs, technical guides, or organizing the specs\u002F directory.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fwrite-document\u002FSKILL.md",[96],{"categoryNo":97,"categoryName":98,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000002","文档处理",[100,101,102,103,104,105,106,107,108,109,31,22,110,111,26,112,113,114,115,116],"write","write document","document","documents","actionable","technical","methodology","high","bmad","standard","minimal","bold","integrity","organize","sync","directory","guides",{"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":34},"01M71KB8TM089JJD5AY5KAFSDM","wire-observability","Add structured JSON logging, observability commands, and idempotent setup scripts to a project. Use when a project needs production-readiness instrumentation, when user wants structured logging, or as a production-readiness gate at any phase of development.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fwire-observability\u002FSKILL.md",[],[124,125,126,109,127,31,128,129,130,131,26,132,133,134,135,136,137,22,138,139],"observability","wire observability","readiness","commands","development","as","logging","add","instrumentation","at","structured logging","production-readiness","idempotent","phase","project","scripts",{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":146,"publishedAt":34},"01M71KB6CNRANP449DQA3NJZ96","wire-ci","CI pipeline setup with bundled, forge-neutral templates and local validation. Detects the forge from the git remote, generates workflows for supported forges, and skips honestly for the rest. The CI equivalent of wire-observability.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fwire-ci\u002FSKILL.md",[],[147,148,149,150,151,152,153,154,155,156,157,109,158,81,124,26,159,160],"wire ci","ci","remote","local","pipeline","forge","validation","setup","templates","REST","with","ci pipeline setup","git","workflows",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":178,"publishedAt":34},"01M71KB2ZV98P03X88QR8MT9F1","visual-dashboard","Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers\u002Fdashboard\u002F. Reads specs\u002Fstate.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel.","https:\u002F\u002Fgithub.com\u002Fdanielvm-git\u002Fbigpowers\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-dashboard\u002FSKILL.md",[167,170,175],{"categoryNo":168,"categoryName":169,"taxonomyType":72,"taxonomyTypeDesc":73},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":171,"categoryName":172,"taxonomyType":173,"taxonomyTypeDesc":174},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",{"categoryNo":176,"categoryName":177,"taxonomyType":173,"taxonomyTypeDesc":174},"01JBSEEDCAT000000000000033","数据分析师",[179,180,181,182,183,184,185,186,187,26,188,189,190,191,192,193,194,138,195,196],"dashboard","visual","visual dashboard","status","artifacts","http","plans","planning","panel","start","release","opencode","plan","browser","api","architecture","project status","http api"]