{
  "schemaVersion": "1.0",
  "item": {
    "slug": "firm-orchestration",
    "name": "Firm Orchestration",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/romainsantoli-web/firm-orchestration",
    "canonicalUrl": "https://clawhub.ai/romainsantoli-web/firm-orchestration",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/firm-orchestration",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=firm-orchestration",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.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/firm-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/firm-orchestration",
    "agentPageUrl": "https://openagent3.xyz/skills/firm-orchestration/agent",
    "manifestUrl": "https://openagent3.xyz/skills/firm-orchestration/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/firm-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": "firm-orchestration",
        "body": "This skill implements the A2A (Agent-to-Agent) pyramid pattern for OpenClaw."
      },
      {
        "title": "Architecture",
        "body": "CEO Agent (orchestrator)\n ├── Department Strategy\n │   └── Service Planning → Employee Analyst\n ├── Department Engineering\n │   └── Service Backend  → Employee Implementer\n ├── Department Quality\n │   └── Service Testing  → Employee Auditor\n └── Department Operations\n     └── Service Release  → Employee Coordinator"
      },
      {
        "title": "Usage",
        "body": "Send this to your OpenClaw session to trigger a full firm orchestration run:\n\n@firm-orchestration run\n  objective: \"Build a payment API\"\n  departments: [\"engineering\", \"quality\"]\n  delivery_format: \"github_pr\""
      },
      {
        "title": "Tools activated",
        "body": "ToolPurposesessions_listDiscover active department/service sessionssessions_spawnSpawn missing sessions per pyramid levelsessions_sendDelegate objectives down the hierarchysessions_historyCollect results from child sessions"
      },
      {
        "title": "Handoff contract",
        "body": "Each delegation payload follows this schema:\n\n{\n  \"from\": \"ceo\",\n  \"to\": \"department:engineering\",\n  \"objective\": \"...\",\n  \"constraints\": [\"...\", \"...\"],\n  \"definition_of_done\": \"...\",\n  \"context_ref\": \"memory:delivery/latest\",\n  \"reply_session\": \"main\"\n}"
      },
      {
        "title": "Merge strategy",
        "body": "Results from all departments are:\n\nCollected via sessions_history with a 30-second deadline\nDeduplicated by objective_key\nMerged in dependency order (Strategy → Engineering → Quality → Ops)\nFormatted according to delivery_format"
      },
      {
        "title": "Operating Protocol (Anthropic-style)",
        "body": "Based on real Anthropic team practices — \"How Anthropic teams use Claude Code\""
      },
      {
        "title": "Phase 1 — Parallel dispatch (never sequential)",
        "body": "Fan-out simultaneously to all departments via sessions_send. Never wait for one department\nbefore launching the next. Each session receives the full handoff contract and maintains its\nown complete context. Store all reply_session refs for convergence.\n\nObjective received →\n  sessions_send(engineering) ‖ sessions_send(quality) ‖ sessions_send(ops) ‖ sessions_send(strategy)\n→ wait(deadline=30s)\n→ collect via sessions_history"
      },
      {
        "title": "Phase 2 — Iterative loop on blockers",
        "body": "If a department returns status: blocked, do NOT resolve it yourself. Spawn a joint\nresolution session with the two conflicting departments and let them iterate:\n\nengineering blocked by legal →\n  sessions_spawn(participants=[engineering, legal], objective=\"resolve_blocker\") →\n  wait(max_iterations=2) →\n  collect resolution\n\nMaximum 2 re-delegation cycles before escalating to CEO with explicit blocker report."
      },
      {
        "title": "Phase 3 — Convergence with partial acceptance",
        "body": "30-second hard deadline. After deadline: accept partial results, mark missing department\noutputs as status: timeout, include them in final report as open items.\nNever block delivery on a single department."
      },
      {
        "title": "Phase 4 — Validate before merge",
        "body": "Before merging each department output into the final deliverable:\n\nCheck output satisfies its definition_of_done\nIf DoD not met: flag as quality: partial — do not silently drop\nMerge in dependency order only: Strategy → Engineering → Quality → Ops"
      },
      {
        "title": "Phase 5 — Deliver + document",
        "body": "After every completed orchestration, automatically append:\n\nRun summary (1 paragraph)\nDepartments that delivered / timed out / were blocked\nArchitecture/process decisions made\nSuggestions for improving the next similar run\n\nAll final outputs carry the mandatory disclaimer:\n\n⚠️ Contenu généré par IA — validation humaine requise avant utilisation en production."
      },
      {
        "title": "Phase 6 — Git checkpoints (when Engineering is involved)",
        "body": "Require Engineering to commit after each sub-task — not only at end of run.\nReject PRs that are not draft + labelled needs-review.\nNever allow direct merge to main."
      },
      {
        "title": "Security",
        "body": "All inter-session calls use reply_session: \"main\" to avoid orphaned sessions\nsessions_spawn is rate-limited: max 20 spawns per orchestration run\nPayloads are validated against the handoff schema before dispatch\nNo external network calls — pure Gateway WebSocket routing"
      },
      {
        "title": "Example prompt",
        "body": "Use the firm-orchestration skill to:\n  objective: \"Audit the authentication module\"\n  departments: [\"quality\", \"engineering\"]\n  constraints: [\"read-only access only\", \"no production changes\"]\n  definition_of_done: \"Security report with CVSS scores and fix recommendations\"\n  delivery_format: \"markdown_report\""
      },
      {
        "title": "💎 Support",
        "body": "Si ce skill vous est utile, vous pouvez soutenir le développement :\n\nDogecoin : DQBggqFNWsRNTPb6kkiwppnMo1Hm8edfWq"
      }
    ],
    "body": "firm-orchestration\n\nThis skill implements the A2A (Agent-to-Agent) pyramid pattern for OpenClaw.\n\nArchitecture\nCEO Agent (orchestrator)\n ├── Department Strategy\n │   └── Service Planning → Employee Analyst\n ├── Department Engineering\n │   └── Service Backend  → Employee Implementer\n ├── Department Quality\n │   └── Service Testing  → Employee Auditor\n └── Department Operations\n     └── Service Release  → Employee Coordinator\n\nUsage\n\nSend this to your OpenClaw session to trigger a full firm orchestration run:\n\n@firm-orchestration run\n  objective: \"Build a payment API\"\n  departments: [\"engineering\", \"quality\"]\n  delivery_format: \"github_pr\"\n\nTools activated\nTool\tPurpose\nsessions_list\tDiscover active department/service sessions\nsessions_spawn\tSpawn missing sessions per pyramid level\nsessions_send\tDelegate objectives down the hierarchy\nsessions_history\tCollect results from child sessions\nHandoff contract\n\nEach delegation payload follows this schema:\n\n{\n  \"from\": \"ceo\",\n  \"to\": \"department:engineering\",\n  \"objective\": \"...\",\n  \"constraints\": [\"...\", \"...\"],\n  \"definition_of_done\": \"...\",\n  \"context_ref\": \"memory:delivery/latest\",\n  \"reply_session\": \"main\"\n}\n\nMerge strategy\n\nResults from all departments are:\n\nCollected via sessions_history with a 30-second deadline\nDeduplicated by objective_key\nMerged in dependency order (Strategy → Engineering → Quality → Ops)\nFormatted according to delivery_format\nOperating Protocol (Anthropic-style)\n\nBased on real Anthropic team practices — \"How Anthropic teams use Claude Code\"\n\nPhase 1 — Parallel dispatch (never sequential)\n\nFan-out simultaneously to all departments via sessions_send. Never wait for one department before launching the next. Each session receives the full handoff contract and maintains its own complete context. Store all reply_session refs for convergence.\n\nObjective received →\n  sessions_send(engineering) ‖ sessions_send(quality) ‖ sessions_send(ops) ‖ sessions_send(strategy)\n→ wait(deadline=30s)\n→ collect via sessions_history\n\nPhase 2 — Iterative loop on blockers\n\nIf a department returns status: blocked, do NOT resolve it yourself. Spawn a joint resolution session with the two conflicting departments and let them iterate:\n\nengineering blocked by legal →\n  sessions_spawn(participants=[engineering, legal], objective=\"resolve_blocker\") →\n  wait(max_iterations=2) →\n  collect resolution\n\n\nMaximum 2 re-delegation cycles before escalating to CEO with explicit blocker report.\n\nPhase 3 — Convergence with partial acceptance\n\n30-second hard deadline. After deadline: accept partial results, mark missing department outputs as status: timeout, include them in final report as open items. Never block delivery on a single department.\n\nPhase 4 — Validate before merge\n\nBefore merging each department output into the final deliverable:\n\nCheck output satisfies its definition_of_done\nIf DoD not met: flag as quality: partial — do not silently drop\nMerge in dependency order only: Strategy → Engineering → Quality → Ops\nPhase 5 — Deliver + document\n\nAfter every completed orchestration, automatically append:\n\nRun summary (1 paragraph)\nDepartments that delivered / timed out / were blocked\nArchitecture/process decisions made\nSuggestions for improving the next similar run\n\nAll final outputs carry the mandatory disclaimer:\n\n⚠️ Contenu généré par IA — validation humaine requise avant utilisation en production.\n\nPhase 6 — Git checkpoints (when Engineering is involved)\n\nRequire Engineering to commit after each sub-task — not only at end of run. Reject PRs that are not draft + labelled needs-review. Never allow direct merge to main.\n\nSecurity\nAll inter-session calls use reply_session: \"main\" to avoid orphaned sessions\nsessions_spawn is rate-limited: max 20 spawns per orchestration run\nPayloads are validated against the handoff schema before dispatch\nNo external network calls — pure Gateway WebSocket routing\nExample prompt\nUse the firm-orchestration skill to:\n  objective: \"Audit the authentication module\"\n  departments: [\"quality\", \"engineering\"]\n  constraints: [\"read-only access only\", \"no production changes\"]\n  definition_of_done: \"Security report with CVSS scores and fix recommendations\"\n  delivery_format: \"markdown_report\"\n\n💎 Support\n\nSi ce skill vous est utile, vous pouvez soutenir le développement :\n\nDogecoin : DQBggqFNWsRNTPb6kkiwppnMo1Hm8edfWq"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/romainsantoli-web/firm-orchestration",
    "publisherUrl": "https://clawhub.ai/romainsantoli-web/firm-orchestration",
    "owner": "romainsantoli-web",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/firm-orchestration",
    "downloadUrl": "https://openagent3.xyz/downloads/firm-orchestration",
    "agentUrl": "https://openagent3.xyz/skills/firm-orchestration/agent",
    "manifestUrl": "https://openagent3.xyz/skills/firm-orchestration/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/firm-orchestration/agent.md"
  }
}