{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agent-team-orchestration",
    "name": "Agent Team Orchestration",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/arminnaimi/agent-team-orchestration",
    "canonicalUrl": "https://clawhub.ai/arminnaimi/agent-team-orchestration",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agent-team-orchestration",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-team-orchestration",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/communication.md",
      "references/patterns.md",
      "references/task-lifecycle.md",
      "references/team-setup.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/agent-team-orchestration"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/agent-team-orchestration",
    "agentPageUrl": "https://openagent3.xyz/skills/agent-team-orchestration/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-team-orchestration/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-team-orchestration/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Agent Team Orchestration",
        "body": "Production playbook for running multi-agent teams with clear roles, structured task flow, and quality gates."
      },
      {
        "title": "Quick Start: Minimal 2-Agent Team",
        "body": "A builder and a reviewer. The simplest useful team."
      },
      {
        "title": "1. Define Roles",
        "body": "Orchestrator (you) — Route tasks, track state, report results\nBuilder agent     — Execute work, produce artifacts"
      },
      {
        "title": "2. Spawn a Task",
        "body": "1. Create task record (file, DB, or task board)\n2. Spawn builder with:\n   - Task ID and description\n   - Output path for artifacts\n   - Handoff instructions (what to produce, where to put it)\n3. On completion: review artifacts, mark done, report"
      },
      {
        "title": "3. Add a Reviewer",
        "body": "Builder produces artifact → Reviewer checks it → Orchestrator ships or returns\n\nThat's the core loop. Everything below scales this pattern."
      },
      {
        "title": "Roles",
        "body": "Every agent has one primary role. Overlap causes confusion.\n\nRolePurposeModel guidanceOrchestratorRoute work, track state, make priority callsHigh-reasoning model (handles judgment)BuilderProduce artifacts — code, docs, configsCan use cost-effective models for mechanical workReviewerVerify quality, push back on gapsHigh-reasoning model (catches what builders miss)OpsCron jobs, standups, health checks, dispatchingCheapest model that's reliable\n\n→ Read references/team-setup.md when defining a new team or adding agents."
      },
      {
        "title": "Task States",
        "body": "Every task moves through a defined lifecycle:\n\nInbox → Assigned → In Progress → Review → Done | Failed\n\nRules:\n\nOrchestrator owns state transitions — don't rely on agents to update their own status\nEvery transition gets a comment (who, what, why)\nFailed is a valid end state — capture why and move on\n\n→ Read references/task-lifecycle.md when designing task flows or debugging stuck tasks."
      },
      {
        "title": "Handoffs",
        "body": "When work passes between agents, the handoff message includes:\n\nWhat was done — summary of changes/output\nWhere artifacts are — exact file paths\nHow to verify — test commands or acceptance criteria\nKnown issues — anything incomplete or risky\nWhat's next — clear next action for the receiving agent\n\nBad handoff: \"Done, check the files.\"\nGood handoff: \"Built auth module at /shared/artifacts/auth/. Run npm test auth to verify. Known issue: rate limiting not implemented yet. Next: reviewer checks error handling edge cases.\""
      },
      {
        "title": "Reviews",
        "body": "Cross-role reviews prevent quality drift:\n\nBuilders review specs — \"Is this feasible? What's missing?\"\nReviewers check builds — \"Does this match the spec? Edge cases?\"\nOrchestrator reviews priorities — \"Is this the right work right now?\"\n\nSkip the review step and quality degrades within 3-5 tasks. Every time.\n\n→ Read references/communication.md when setting up agent communication channels.\n→ Read references/patterns.md for proven multi-step workflows."
      },
      {
        "title": "Reference Files",
        "body": "FileRead when...team-setup.mdDefining agents, roles, models, workspacestask-lifecycle.mdDesigning task states, transitions, commentscommunication.mdSetting up async/sync communication, artifact pathspatterns.mdImplementing specific workflows (spec→build→test, parallel research, escalation)"
      },
      {
        "title": "Spawning without clear artifact output paths",
        "body": "Agent produces great work, but you can't find it. Always specify the exact output path in the spawn prompt. Use a shared artifacts directory with predictable structure."
      },
      {
        "title": "No review step = quality drift",
        "body": "\"It's a small change, skip review.\" Do this three times and you have compounding errors. Every artifact gets at least one set of eyes that didn't produce it."
      },
      {
        "title": "Agents not commenting on task progress",
        "body": "Silent agents create coordination blind spots. Require comments at: start, blocker, handoff, completion. If an agent goes silent, assume it's stuck."
      },
      {
        "title": "Not verifying agent capabilities before assigning",
        "body": "Assigning browser-based testing to an agent without browser access. Assigning image work to a text-only model. Check capabilities before routing."
      },
      {
        "title": "Orchestrator doing execution work",
        "body": "The orchestrator routes and tracks — it doesn't build. The moment you start \"just quickly doing this one thing,\" you've lost oversight of the rest of the team."
      },
      {
        "title": "When NOT to Use This Skill",
        "body": "Single-agent setups — Just follow standard AGENTS.md conventions. Team orchestration adds overhead that solo agents don't need.\nOne-off task delegation — Use sessions_spawn directly. This skill is for sustained workflows with multiple handoffs.\nSimple question routing — If you're just forwarding a question to a specialist, that's a message, not a workflow.\n\nThis skill is for sustained team workflows — recurring collaboration patterns where agents depend on each other's output over multiple tasks."
      }
    ],
    "body": "Agent Team Orchestration\n\nProduction playbook for running multi-agent teams with clear roles, structured task flow, and quality gates.\n\nQuick Start: Minimal 2-Agent Team\n\nA builder and a reviewer. The simplest useful team.\n\n1. Define Roles\nOrchestrator (you) — Route tasks, track state, report results\nBuilder agent     — Execute work, produce artifacts\n\n2. Spawn a Task\n1. Create task record (file, DB, or task board)\n2. Spawn builder with:\n   - Task ID and description\n   - Output path for artifacts\n   - Handoff instructions (what to produce, where to put it)\n3. On completion: review artifacts, mark done, report\n\n3. Add a Reviewer\nBuilder produces artifact → Reviewer checks it → Orchestrator ships or returns\n\n\nThat's the core loop. Everything below scales this pattern.\n\nCore Concepts\nRoles\n\nEvery agent has one primary role. Overlap causes confusion.\n\nRole\tPurpose\tModel guidance\nOrchestrator\tRoute work, track state, make priority calls\tHigh-reasoning model (handles judgment)\nBuilder\tProduce artifacts — code, docs, configs\tCan use cost-effective models for mechanical work\nReviewer\tVerify quality, push back on gaps\tHigh-reasoning model (catches what builders miss)\nOps\tCron jobs, standups, health checks, dispatching\tCheapest model that's reliable\n\n→ Read references/team-setup.md when defining a new team or adding agents.\n\nTask States\n\nEvery task moves through a defined lifecycle:\n\nInbox → Assigned → In Progress → Review → Done | Failed\n\n\nRules:\n\nOrchestrator owns state transitions — don't rely on agents to update their own status\nEvery transition gets a comment (who, what, why)\nFailed is a valid end state — capture why and move on\n\n→ Read references/task-lifecycle.md when designing task flows or debugging stuck tasks.\n\nHandoffs\n\nWhen work passes between agents, the handoff message includes:\n\nWhat was done — summary of changes/output\nWhere artifacts are — exact file paths\nHow to verify — test commands or acceptance criteria\nKnown issues — anything incomplete or risky\nWhat's next — clear next action for the receiving agent\n\nBad handoff: \"Done, check the files.\" Good handoff: \"Built auth module at /shared/artifacts/auth/. Run npm test auth to verify. Known issue: rate limiting not implemented yet. Next: reviewer checks error handling edge cases.\"\n\nReviews\n\nCross-role reviews prevent quality drift:\n\nBuilders review specs — \"Is this feasible? What's missing?\"\nReviewers check builds — \"Does this match the spec? Edge cases?\"\nOrchestrator reviews priorities — \"Is this the right work right now?\"\n\nSkip the review step and quality degrades within 3-5 tasks. Every time.\n\n→ Read references/communication.md when setting up agent communication channels. → Read references/patterns.md for proven multi-step workflows.\n\nReference Files\nFile\tRead when...\nteam-setup.md\tDefining agents, roles, models, workspaces\ntask-lifecycle.md\tDesigning task states, transitions, comments\ncommunication.md\tSetting up async/sync communication, artifact paths\npatterns.md\tImplementing specific workflows (spec→build→test, parallel research, escalation)\nCommon Pitfalls\nSpawning without clear artifact output paths\n\nAgent produces great work, but you can't find it. Always specify the exact output path in the spawn prompt. Use a shared artifacts directory with predictable structure.\n\nNo review step = quality drift\n\n\"It's a small change, skip review.\" Do this three times and you have compounding errors. Every artifact gets at least one set of eyes that didn't produce it.\n\nAgents not commenting on task progress\n\nSilent agents create coordination blind spots. Require comments at: start, blocker, handoff, completion. If an agent goes silent, assume it's stuck.\n\nNot verifying agent capabilities before assigning\n\nAssigning browser-based testing to an agent without browser access. Assigning image work to a text-only model. Check capabilities before routing.\n\nOrchestrator doing execution work\n\nThe orchestrator routes and tracks — it doesn't build. The moment you start \"just quickly doing this one thing,\" you've lost oversight of the rest of the team.\n\nWhen NOT to Use This Skill\nSingle-agent setups — Just follow standard AGENTS.md conventions. Team orchestration adds overhead that solo agents don't need.\nOne-off task delegation — Use sessions_spawn directly. This skill is for sustained workflows with multiple handoffs.\nSimple question routing — If you're just forwarding a question to a specialist, that's a message, not a workflow.\n\nThis skill is for sustained team workflows — recurring collaboration patterns where agents depend on each other's output over multiple tasks."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/arminnaimi/agent-team-orchestration",
    "publisherUrl": "https://clawhub.ai/arminnaimi/agent-team-orchestration",
    "owner": "arminnaimi",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agent-team-orchestration",
    "downloadUrl": "https://openagent3.xyz/downloads/agent-team-orchestration",
    "agentUrl": "https://openagent3.xyz/skills/agent-team-orchestration/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-team-orchestration/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-team-orchestration/agent.md"
  }
}