{
  "schemaVersion": "1.0",
  "item": {
    "slug": "bmad-orchestrator",
    "name": "BMAD Orchestrator",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/henrikrexed/bmad-orchestrator",
    "canonicalUrl": "https://clawhub.ai/henrikrexed/bmad-orchestrator",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/bmad-orchestrator",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=bmad-orchestrator",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/bmad-commands.md",
      "references/tmux-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/bmad-orchestrator"
    },
    "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/bmad-orchestrator",
    "agentPageUrl": "https://openagent3.xyz/skills/bmad-orchestrator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/bmad-orchestrator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/bmad-orchestrator/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": "BMAD Orchestrator",
        "body": "Orchestrate the 4-phase BMAD Method (Breakthrough Method of Agile AI Driven Development) across OpenClaw ↔ Claude Code."
      },
      {
        "title": "Architecture",
        "body": "Phases 1-3 (Interactive): Run through OpenClaw chat with the user. You facilitate brainstorming, refine the PRD, debate architecture. The user's ideas matter most here.\nParty Mode: At key decision points, suggest running party mode on Claude Code — multiple BMAD agents debate the topic and produce richer output.\nPhase 4 (Automated): Delegate to Claude Code via tmux on the dev VM. Monitor progress, report back."
      },
      {
        "title": "Prerequisites",
        "body": "Claude Code installed on dev VM (accessible via SSH)\nBMAD framework installed in the project (_bmad/ directory with agents, workflows, commands)\ntmux available on the dev VM"
      },
      {
        "title": "State Tracking",
        "body": "Track workflow state in _bmad-output/orchestrator-state.yaml:\n\nproject: <name>\nvm_host: <ip>\nvm_user: <user>\nproject_path: <path>\ntmux_socket: /tmp/openclaw-tmux-sockets/openclaw.sock\ntmux_session: bmad-<project>\ncurrent_phase: 1|2|3|4\ncurrent_workflow: <workflow-name>\nartifacts:\n  brainstorming_report: null|path\n  product_brief: null|path  \n  prd: null|path\n  ux_spec: null|path\n  architecture: null|path\n  epics: null|path\n  sprint_status: null|path\n  project_context: null|path"
      },
      {
        "title": "1.1 Brainstorming (bmad-brainstorming)",
        "body": "Run this conversationally with the user in OpenClaw chat:\n\nAsk: \"What project are we building? Give me the elevator pitch.\"\nExplore the problem space — ask about users, pain points, existing solutions\nChallenge assumptions — play devil's advocate\nSuggest Party Mode: \"Want me to run party mode on Claude Code? The BMAD agents (analyst, architect, PM, dev) will debate your idea and surface things we might miss.\"\nIf party mode → send /bmad-brainstorming to Claude Code, capture output, share highlights\nSynthesize into key decisions and themes\nProduce: brainstorming-report.md"
      },
      {
        "title": "1.2 Research (bmad-bmm-research) — Optional",
        "body": "If the project needs market/technical/domain validation:\n\nDiscuss with user what needs validation\nSend research workflow to Claude Code for heavy lifting\nReview findings together"
      },
      {
        "title": "1.3 Product Brief (bmad-bmm-create-product-brief)",
        "body": "Start from brainstorming output\nWalk through with user: vision, target users, success metrics, scope\nSuggest Party Mode: \"The PM and analyst agents can stress-test this brief. Run it?\"\nIf party mode → send command, capture debate highlights\nIterate until user approves\nProduce: product-brief.md"
      },
      {
        "title": "2.1 PRD (bmad-bmm-create-prd)",
        "body": "Load product brief as context\nWalk through requirements with user section by section:\n\nFunctional requirements (FRs)\nNon-functional requirements (NFRs)\nUser journeys\nSuccess metrics\n\n\nSuggest Party Mode: \"PM + architect + QA can review these requirements together. Good time to catch gaps.\"\nIf party mode → send command, share findings\nIterate until user signs off\nProduce: prd.md"
      },
      {
        "title": "2.2 UX Design (bmad-bmm-create-ux-design) — If applicable",
        "body": "Only for projects with UI. Skip for backend/infrastructure tools."
      },
      {
        "title": "3.1 Architecture (bmad-bmm-create-architecture)",
        "body": "Load PRD as context\nDiscuss technical decisions with user:\n\nLanguage/framework choices\nDeployment model\nKey patterns and trade-offs\nADRs (Architecture Decision Records)\n\n\nSuggest Party Mode: \"Architect + dev + QA debating the architecture will surface implementation risks early.\"\nIf party mode → send command, share the debate\nIterate with user\nProduce: architecture.md with ADRs"
      },
      {
        "title": "3.2 Epics & Stories (bmad-bmm-create-epics-and-stories)",
        "body": "Load architecture + PRD\nPresent epic breakdown to user for review\nDiscuss story sizing, priorities, dependencies\nProduce: epics.md with stories"
      },
      {
        "title": "3.3 Readiness Check (bmad-bmm-check-implementation-readiness)",
        "body": "Send to Claude Code for automated gate check\nShare result: PASS / CONCERNS / FAIL\nIf CONCERNS/FAIL → discuss with user, fix gaps\nProduce: readiness report"
      },
      {
        "title": "3.4 Project Context (bmad-bmm-generate-project-context)",
        "body": "Send to Claude Code after architecture is finalized\nReview output with user\nProduce: project-context.md"
      },
      {
        "title": "4.0 Setup",
        "body": "See references/tmux-setup.md for tmux session initialization."
      },
      {
        "title": "4.1 Sprint Planning",
        "body": "Send to Claude Code:\n\n/bmad-bmm-sprint-planning\n\nCapture and save sprint-status.yaml."
      },
      {
        "title": "4.2 Story Loop (per epic)",
        "body": "For each epic, for each story:\n\nCreate Story: Send /bmad-bmm-create-story → produces story-[slug].md\nDev Story: Send /bmad-bmm-dev-story → implements code + tests\nCode Review: Send /bmad-bmm-code-review → validates quality\nIf review fails → send fixes back, re-review\nUpdate sprint status\nCommit after each story"
      },
      {
        "title": "4.3 Epic Completion",
        "body": "After all stories in an epic:\n\nSend /bmad-bmm-retrospective for lessons learned\nOptionally run /bmad-bmm-automate for E2E test generation\nCommit and update sprint status"
      },
      {
        "title": "4.4 Monitoring",
        "body": "Set up a cron job to monitor Claude Code progress every 15 minutes.\nReport status updates to user via chat."
      },
      {
        "title": "Party Mode Integration",
        "body": "Party mode simulates a multi-agent discussion in Claude Code. Use it at these moments:\n\nWhenWhyCommandAfter brainstormingSurface blind spots/bmad-party-mode with brainstorming contextAfter product briefStress-test the vision/bmad-party-mode with briefDuring PRD reviewCatch requirement gaps/bmad-party-mode with PRD draftArchitecture decisionsDebate trade-offs/bmad-party-mode with architecture\n\nTo trigger party mode on Claude Code:\n\ntmux send-keys -l -- \"/bmad-party-mode\" && sleep 0.3 && tmux send-keys Enter\n\nCapture output, extract key insights, present to user."
      },
      {
        "title": "Claude Code Commands Reference",
        "body": "See references/bmad-commands.md for the full command list."
      },
      {
        "title": "Quick Flow (Skip Phases 1-3)",
        "body": "For small, well-understood work:\n\n/bmad-bmm-quick-spec → tech-spec.md\n/bmad-bmm-quick-dev → implementation\n\nOnly use when user explicitly says the project is simple and well-understood."
      },
      {
        "title": "Sending Commands to Claude Code",
        "body": "See references/tmux-setup.md for the tmux interaction patterns.\n\nKey rules:\n\nSplit text and Enter with a delay (Claude Code TUI timing)\nUse capture-pane -S -200 to read output\nWait for idle prompt before sending next command\nUse C-c to interrupt if stuck"
      }
    ],
    "body": "BMAD Orchestrator\n\nOrchestrate the 4-phase BMAD Method (Breakthrough Method of Agile AI Driven Development) across OpenClaw ↔ Claude Code.\n\nArchitecture\nPhases 1-3 (Interactive): Run through OpenClaw chat with the user. You facilitate brainstorming, refine the PRD, debate architecture. The user's ideas matter most here.\nParty Mode: At key decision points, suggest running party mode on Claude Code — multiple BMAD agents debate the topic and produce richer output.\nPhase 4 (Automated): Delegate to Claude Code via tmux on the dev VM. Monitor progress, report back.\nPrerequisites\nClaude Code installed on dev VM (accessible via SSH)\nBMAD framework installed in the project (_bmad/ directory with agents, workflows, commands)\ntmux available on the dev VM\nState Tracking\n\nTrack workflow state in _bmad-output/orchestrator-state.yaml:\n\nproject: <name>\nvm_host: <ip>\nvm_user: <user>\nproject_path: <path>\ntmux_socket: /tmp/openclaw-tmux-sockets/openclaw.sock\ntmux_session: bmad-<project>\ncurrent_phase: 1|2|3|4\ncurrent_workflow: <workflow-name>\nartifacts:\n  brainstorming_report: null|path\n  product_brief: null|path  \n  prd: null|path\n  ux_spec: null|path\n  architecture: null|path\n  epics: null|path\n  sprint_status: null|path\n  project_context: null|path\n\nPhase 1: Analysis (Interactive with User)\n1.1 Brainstorming (bmad-brainstorming)\n\nRun this conversationally with the user in OpenClaw chat:\n\nAsk: \"What project are we building? Give me the elevator pitch.\"\nExplore the problem space — ask about users, pain points, existing solutions\nChallenge assumptions — play devil's advocate\nSuggest Party Mode: \"Want me to run party mode on Claude Code? The BMAD agents (analyst, architect, PM, dev) will debate your idea and surface things we might miss.\"\nIf party mode → send /bmad-brainstorming to Claude Code, capture output, share highlights\nSynthesize into key decisions and themes\nProduce: brainstorming-report.md\n1.2 Research (bmad-bmm-research) — Optional\n\nIf the project needs market/technical/domain validation:\n\nDiscuss with user what needs validation\nSend research workflow to Claude Code for heavy lifting\nReview findings together\n1.3 Product Brief (bmad-bmm-create-product-brief)\nStart from brainstorming output\nWalk through with user: vision, target users, success metrics, scope\nSuggest Party Mode: \"The PM and analyst agents can stress-test this brief. Run it?\"\nIf party mode → send command, capture debate highlights\nIterate until user approves\nProduce: product-brief.md\nPhase 2: Planning (Interactive with User)\n2.1 PRD (bmad-bmm-create-prd)\nLoad product brief as context\nWalk through requirements with user section by section:\nFunctional requirements (FRs)\nNon-functional requirements (NFRs)\nUser journeys\nSuccess metrics\nSuggest Party Mode: \"PM + architect + QA can review these requirements together. Good time to catch gaps.\"\nIf party mode → send command, share findings\nIterate until user signs off\nProduce: prd.md\n2.2 UX Design (bmad-bmm-create-ux-design) — If applicable\n\nOnly for projects with UI. Skip for backend/infrastructure tools.\n\nPhase 3: Solutioning (Interactive with User)\n3.1 Architecture (bmad-bmm-create-architecture)\nLoad PRD as context\nDiscuss technical decisions with user:\nLanguage/framework choices\nDeployment model\nKey patterns and trade-offs\nADRs (Architecture Decision Records)\nSuggest Party Mode: \"Architect + dev + QA debating the architecture will surface implementation risks early.\"\nIf party mode → send command, share the debate\nIterate with user\nProduce: architecture.md with ADRs\n3.2 Epics & Stories (bmad-bmm-create-epics-and-stories)\nLoad architecture + PRD\nPresent epic breakdown to user for review\nDiscuss story sizing, priorities, dependencies\nProduce: epics.md with stories\n3.3 Readiness Check (bmad-bmm-check-implementation-readiness)\nSend to Claude Code for automated gate check\nShare result: PASS / CONCERNS / FAIL\nIf CONCERNS/FAIL → discuss with user, fix gaps\nProduce: readiness report\n3.4 Project Context (bmad-bmm-generate-project-context)\nSend to Claude Code after architecture is finalized\nReview output with user\nProduce: project-context.md\nPhase 4: Implementation (Automated via Claude Code)\n4.0 Setup\n\nSee references/tmux-setup.md for tmux session initialization.\n\n4.1 Sprint Planning\n\nSend to Claude Code:\n\n/bmad-bmm-sprint-planning\n\n\nCapture and save sprint-status.yaml.\n\n4.2 Story Loop (per epic)\n\nFor each epic, for each story:\n\nCreate Story: Send /bmad-bmm-create-story → produces story-[slug].md\nDev Story: Send /bmad-bmm-dev-story → implements code + tests\nCode Review: Send /bmad-bmm-code-review → validates quality\nIf review fails → send fixes back, re-review\nUpdate sprint status\nCommit after each story\n4.3 Epic Completion\n\nAfter all stories in an epic:\n\nSend /bmad-bmm-retrospective for lessons learned\nOptionally run /bmad-bmm-automate for E2E test generation\nCommit and update sprint status\n4.4 Monitoring\n\nSet up a cron job to monitor Claude Code progress every 15 minutes. Report status updates to user via chat.\n\nParty Mode Integration\n\nParty mode simulates a multi-agent discussion in Claude Code. Use it at these moments:\n\nWhen\tWhy\tCommand\nAfter brainstorming\tSurface blind spots\t/bmad-party-mode with brainstorming context\nAfter product brief\tStress-test the vision\t/bmad-party-mode with brief\nDuring PRD review\tCatch requirement gaps\t/bmad-party-mode with PRD draft\nArchitecture decisions\tDebate trade-offs\t/bmad-party-mode with architecture\n\nTo trigger party mode on Claude Code:\n\ntmux send-keys -l -- \"/bmad-party-mode\" && sleep 0.3 && tmux send-keys Enter\n\n\nCapture output, extract key insights, present to user.\n\nClaude Code Commands Reference\n\nSee references/bmad-commands.md for the full command list.\n\nQuick Flow (Skip Phases 1-3)\n\nFor small, well-understood work:\n\n/bmad-bmm-quick-spec → tech-spec.md\n/bmad-bmm-quick-dev → implementation\n\nOnly use when user explicitly says the project is simple and well-understood.\n\nSending Commands to Claude Code\n\nSee references/tmux-setup.md for the tmux interaction patterns.\n\nKey rules:\n\nSplit text and Enter with a delay (Claude Code TUI timing)\nUse capture-pane -S -200 to read output\nWait for idle prompt before sending next command\nUse C-c to interrupt if stuck"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/henrikrexed/bmad-orchestrator",
    "publisherUrl": "https://clawhub.ai/henrikrexed/bmad-orchestrator",
    "owner": "henrikrexed",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/bmad-orchestrator",
    "downloadUrl": "https://openagent3.xyz/downloads/bmad-orchestrator",
    "agentUrl": "https://openagent3.xyz/skills/bmad-orchestrator/agent",
    "manifestUrl": "https://openagent3.xyz/skills/bmad-orchestrator/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/bmad-orchestrator/agent.md"
  }
}