{
  "schemaVersion": "1.0",
  "item": {
    "slug": "agent-team-kit",
    "name": "Agent Team Kit",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ryancampbell/agent-team-kit",
    "canonicalUrl": "https://clawhub.ai/ryancampbell/agent-team-kit",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/agent-team-kit",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=agent-team-kit",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "README.md",
      "SKILL.md",
      "agents-config-draft.md",
      "package.json",
      "templates/HEARTBEAT.md",
      "templates/process/BACKLOG.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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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-kit"
    },
    "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-kit",
    "agentPageUrl": "https://openagent3.xyz/skills/agent-team-kit/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-team-kit/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-team-kit/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Agent Team Kit — SKILL.md",
        "body": "A framework for self-sustaining AI agent teams."
      },
      {
        "title": "What This Is",
        "body": "A complete team process kit for OpenClaw agents that enables:\n\nSelf-service work queues — Agents pick up tasks without human bottlenecks\nClear role ownership — Everyone knows who does what\nContinuous discovery — Work flows in automatically\nProactive operation — The team runs itself via heartbeat"
      },
      {
        "title": "1. Copy the Process Files",
        "body": "# From your workspace root\ncp -r skills/agent-team-kit/templates/process ./process\n\nThis creates:\n\nprocess/INTAKE.md — The 5-phase work loop\nprocess/ROLES.md — Role definitions\nprocess/OPPORTUNITIES.md — Raw ideas/discoveries\nprocess/BACKLOG.md — Triaged work queue\nprocess/STATUS.md — Who's working on what"
      },
      {
        "title": "2. Add Heartbeat Config",
        "body": "Merge templates/HEARTBEAT.md into your existing HEARTBEAT.md:\n\ncat skills/agent-team-kit/templates/HEARTBEAT.md >> HEARTBEAT.md\n\nOr copy it directly if you don't have one yet."
      },
      {
        "title": "3. Customize Roles",
        "body": "Edit process/ROLES.md to match your team:\n\nRename roles to fit your domain\nAdd/remove specialized execution roles\nUpdate the human lead section with your name"
      },
      {
        "title": "The Intake Loop",
        "body": "DISCOVER → TRIAGE → READY → EXECUTE → FEEDBACK\n    ↑                                      ↓\n    └──────────────────────────────────────┘\n\nDiscover — Find opportunities (Scout role)\nTriage — Decide what's ready (Rhythm role)\nReady — Self-service queue (any agent)\nExecute — Do the work (assigned agent)\nFeedback — Learn and spawn new ideas (completing agent)"
      },
      {
        "title": "Core Roles",
        "body": "RoleMissionOwnsScout 🔍Find opportunitiesOPPORTUNITIES.md, discoveryRhythm 🥁Keep work flowingBACKLOG.md, triageHarmony 🤝Keep team healthyUnblocking, retros[Human]Strategic directionHard calls, spawning\n\nExecution roles (spawn as needed):\n\nLink 🔗 — Builder\nPixel 🎨 — Designer\nSage 🦉 — Architect\nEcho 📢 — Voice\nSpark ✨ — Creative"
      },
      {
        "title": "Self-Service",
        "body": "If it's in Ready, any agent can pick it up. No approval needed."
      },
      {
        "title": "Clear Ownership",
        "body": "Every phase has ONE owner. No ambiguity."
      },
      {
        "title": "Always Log",
        "body": "Ideas, discoveries, completions — if you don't log it, it didn't happen."
      },
      {
        "title": "Spawn, Don't Solo",
        "body": "Main agent coordinates. Sub-agents execute. Don't do everything yourself."
      },
      {
        "title": "File Structure",
        "body": "process/\n├── INTAKE.md         # How the loop works (reference)\n├── ROLES.md          # Who does what\n├── OPPORTUNITIES.md  # Raw discoveries (anyone adds)\n├── BACKLOG.md        # Triaged work (Rhythm maintains)\n└── STATUS.md         # Current activity (self-updated)\n\nHEARTBEAT.md          # Proactive check triggers"
      },
      {
        "title": "Heartbeat Integration",
        "body": "Add to your heartbeat checks:\n\n### Team Health (run hourly)\n- [ ] OPPORTUNITIES.md stale? → Spawn Scout\n- [ ] Ready queue empty? → Alert Rhythm  \n- [ ] Active work stuck >2h? → Nudge owner\n- [ ] Any unresolved blockers? → Harmony\n\nThe heartbeat keeps the loop spinning even when the human isn't watching."
      },
      {
        "title": "Adding a New Role",
        "body": "Define in ROLES.md:\n\nMission (one sentence)\nOwns (what they're responsible for)\nCadence (how often they work)\nOutputs (what they produce)\n\n\n\nUpdate the ownership matrix\n\n\nAdd spawn criteria in INTAKE.md if needed"
      },
      {
        "title": "Changing the Loop",
        "body": "The 5-phase loop is flexible. Adapt it:\n\nAdd validation gates between phases\nSplit EXECUTE into parallel tracks\nAdd approval checkpoints (if your domain requires it)"
      },
      {
        "title": "Anti-Patterns",
        "body": "❌ Human manually adds every task → Use triage role instead\n❌ Waiting for permission to pick up work → Ready = fair game\n❌ One agent does everything → Spawn specialists\n❌ Ideas stay in heads → Log to OPPORTUNITIES.md\n❌ Heartbeat just returns OK → Actually check the loop"
      },
      {
        "title": "Metrics (Optional)",
        "body": "Track team health:\n\nCycle time — OPPORTUNITIES → DONE\nQueue depth — Items in Ready (healthy: 5-15)\nStale items — Days since last triage\nSpawn rate — Sub-agents created per day\n\nThe system runs itself. Your job is to trust it."
      }
    ],
    "body": "Agent Team Kit — SKILL.md\n\nA framework for self-sustaining AI agent teams.\n\nWhat This Is\n\nA complete team process kit for OpenClaw agents that enables:\n\nSelf-service work queues — Agents pick up tasks without human bottlenecks\nClear role ownership — Everyone knows who does what\nContinuous discovery — Work flows in automatically\nProactive operation — The team runs itself via heartbeat\nQuick Start\n1. Copy the Process Files\n# From your workspace root\ncp -r skills/agent-team-kit/templates/process ./process\n\n\nThis creates:\n\nprocess/INTAKE.md — The 5-phase work loop\nprocess/ROLES.md — Role definitions\nprocess/OPPORTUNITIES.md — Raw ideas/discoveries\nprocess/BACKLOG.md — Triaged work queue\nprocess/STATUS.md — Who's working on what\n2. Add Heartbeat Config\n\nMerge templates/HEARTBEAT.md into your existing HEARTBEAT.md:\n\ncat skills/agent-team-kit/templates/HEARTBEAT.md >> HEARTBEAT.md\n\n\nOr copy it directly if you don't have one yet.\n\n3. Customize Roles\n\nEdit process/ROLES.md to match your team:\n\nRename roles to fit your domain\nAdd/remove specialized execution roles\nUpdate the human lead section with your name\nThe Intake Loop\nDISCOVER → TRIAGE → READY → EXECUTE → FEEDBACK\n    ↑                                      ↓\n    └──────────────────────────────────────┘\n\nDiscover — Find opportunities (Scout role)\nTriage — Decide what's ready (Rhythm role)\nReady — Self-service queue (any agent)\nExecute — Do the work (assigned agent)\nFeedback — Learn and spawn new ideas (completing agent)\nCore Roles\nRole\tMission\tOwns\nScout 🔍\tFind opportunities\tOPPORTUNITIES.md, discovery\nRhythm 🥁\tKeep work flowing\tBACKLOG.md, triage\nHarmony 🤝\tKeep team healthy\tUnblocking, retros\n[Human]\tStrategic direction\tHard calls, spawning\n\nExecution roles (spawn as needed):\n\nLink 🔗 — Builder\nPixel 🎨 — Designer\nSage 🦉 — Architect\nEcho 📢 — Voice\nSpark ✨ — Creative\nKey Principles\nSelf-Service\n\nIf it's in Ready, any agent can pick it up. No approval needed.\n\nClear Ownership\n\nEvery phase has ONE owner. No ambiguity.\n\nAlways Log\n\nIdeas, discoveries, completions — if you don't log it, it didn't happen.\n\nSpawn, Don't Solo\n\nMain agent coordinates. Sub-agents execute. Don't do everything yourself.\n\nFile Structure\nprocess/\n├── INTAKE.md         # How the loop works (reference)\n├── ROLES.md          # Who does what\n├── OPPORTUNITIES.md  # Raw discoveries (anyone adds)\n├── BACKLOG.md        # Triaged work (Rhythm maintains)\n└── STATUS.md         # Current activity (self-updated)\n\nHEARTBEAT.md          # Proactive check triggers\n\nHeartbeat Integration\n\nAdd to your heartbeat checks:\n\n### Team Health (run hourly)\n- [ ] OPPORTUNITIES.md stale? → Spawn Scout\n- [ ] Ready queue empty? → Alert Rhythm  \n- [ ] Active work stuck >2h? → Nudge owner\n- [ ] Any unresolved blockers? → Harmony\n\n\nThe heartbeat keeps the loop spinning even when the human isn't watching.\n\nCustomization\nAdding a New Role\n\nDefine in ROLES.md:\n\nMission (one sentence)\nOwns (what they're responsible for)\nCadence (how often they work)\nOutputs (what they produce)\n\nUpdate the ownership matrix\n\nAdd spawn criteria in INTAKE.md if needed\n\nChanging the Loop\n\nThe 5-phase loop is flexible. Adapt it:\n\nAdd validation gates between phases\nSplit EXECUTE into parallel tracks\nAdd approval checkpoints (if your domain requires it)\nAnti-Patterns\n\n❌ Human manually adds every task → Use triage role instead\n❌ Waiting for permission to pick up work → Ready = fair game\n❌ One agent does everything → Spawn specialists\n❌ Ideas stay in heads → Log to OPPORTUNITIES.md\n❌ Heartbeat just returns OK → Actually check the loop\n\nMetrics (Optional)\n\nTrack team health:\n\nCycle time — OPPORTUNITIES → DONE\nQueue depth — Items in Ready (healthy: 5-15)\nStale items — Days since last triage\nSpawn rate — Sub-agents created per day\n\nThe system runs itself. Your job is to trust it."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ryancampbell/agent-team-kit",
    "publisherUrl": "https://clawhub.ai/ryancampbell/agent-team-kit",
    "owner": "ryancampbell",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/agent-team-kit",
    "downloadUrl": "https://openagent3.xyz/downloads/agent-team-kit",
    "agentUrl": "https://openagent3.xyz/skills/agent-team-kit/agent",
    "manifestUrl": "https://openagent3.xyz/skills/agent-team-kit/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/agent-team-kit/agent.md"
  }
}