{
  "schemaVersion": "1.0",
  "item": {
    "slug": "council-of-wisdom",
    "name": "Council of Wisdom",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/adelpro/council-of-wisdom",
    "canonicalUrl": "https://clawhub.ai/adelpro/council-of-wisdom",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/council-of-wisdom",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=council-of-wisdom",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "agents/complexity-assessor.md",
      "agents/intent-decoder.md",
      "agents/risk-checker.md",
      "agents/system-designer.md",
      "agents/tone-designer.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/council-of-wisdom"
    },
    "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/council-of-wisdom",
    "agentPageUrl": "https://openagent3.xyz/skills/council-of-wisdom/agent",
    "manifestUrl": "https://openagent3.xyz/skills/council-of-wisdom/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/council-of-wisdom/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": "Council of Wisdom",
        "body": "A multi-agent deliberation hub with 3 core agents and extensible extended agents."
      },
      {
        "title": "Auto-Trigger",
        "body": "Decision words: should I, should we, better to, which option\nRisk signals: dangerous, risk, worried, concerned, scared\nComplex words: analyze, compare, think, help me\nExplicit: council:, ask the council"
      },
      {
        "title": "Auto-Skip",
        "body": "hello, hi, hey, thanks, thank you\nwhat time, weather, temperature\nyes, no, ok, sure\ndefine, what is"
      },
      {
        "title": "Architecture",
        "body": "Query → Check Skip List\n           │\n           ▼ (if not skipped)\n    ┌──────────────────┐\n    │  CORE AGENTS    │ (always run)\n    │ - Intent Decoder│\n    │ - Risk Checker  │\n    │ - Tone Designer │\n    └──────────────────┘\n           │\n           ▼ (if extended triggered)\n    ┌──────────────────┐\n    │ EXTENDED AGENTS │ (included)\n    └──────────────────┘\n           │\n           ▼\n    ┌──────────────────┐\n    │ WORKSPACE SKILLS │ (if needed)\n    └──────────────────┘\n           │\n           ▼\n    Enriched Response"
      },
      {
        "title": "Intent Decoder",
        "body": "What does the user actually want?"
      },
      {
        "title": "Risk Checker",
        "body": "What could go wrong?"
      },
      {
        "title": "Tone Designer",
        "body": "How should this feel?"
      },
      {
        "title": "Extended Agents (Included)",
        "body": "AgentTrigger KeywordsSystem Designerapi, database, architecture, systemComplexity Assessorcomplex, analyze, compareValues Guardianethical, moral, values, fair"
      },
      {
        "title": "Calling Workspace Skills",
        "body": "The council can call skills from your workspace when specialized knowledge is needed.\n\nExample:\n\nQuery about Quran → call quran-search-engine-mcp\nQuery about GitHub → call github-mcp\nQuery about security → call penetration-tester agent\n\nTo add workspace skills:\n\nSkills go in workspace/skills/\nAgents go in workspace/agents/\nThe council detects keywords and calls them when needed"
      },
      {
        "title": "Adding Custom Extended Agents",
        "body": "Create a new .md file in agents/ folder:\n\n# Your Agent Name\n\nTrigger: keyword1, keyword2\n\nYour analysis..."
      },
      {
        "title": "Implicit Mode (Default)",
        "body": "Skill runs silently. Apply analysis to shape response."
      },
      {
        "title": "Explicit Mode (When Asked)",
        "body": "Use council: prefix to see full analysis."
      },
      {
        "title": "Simple Rules (80% of Value)",
        "body": "IF query contains: dangerous, risk, worried, scared\nTHEN: Risk Checker flag = high\n\nIF query contains: frustrated, angry, upset\nTHEN: Tone = empathetic"
      },
      {
        "title": "SEO",
        "body": "Keywords: multi-agent, AI router, agent council, decision support, AI deliberation, extensible hub, workspace skills\n\nUse cases: personal AI assistant, decision making, risk assessment"
      }
    ],
    "body": "Council of Wisdom\n\nA multi-agent deliberation hub with 3 core agents and extensible extended agents.\n\nWhen to Activate\nAuto-Trigger\nDecision words: should I, should we, better to, which option\nRisk signals: dangerous, risk, worried, concerned, scared\nComplex words: analyze, compare, think, help me\nExplicit: council:, ask the council\nAuto-Skip\nhello, hi, hey, thanks, thank you\nwhat time, weather, temperature\nyes, no, ok, sure\ndefine, what is\n\nArchitecture\nQuery → Check Skip List\n           │\n           ▼ (if not skipped)\n    ┌──────────────────┐\n    │  CORE AGENTS    │ (always run)\n    │ - Intent Decoder│\n    │ - Risk Checker  │\n    │ - Tone Designer │\n    └──────────────────┘\n           │\n           ▼ (if extended triggered)\n    ┌──────────────────┐\n    │ EXTENDED AGENTS │ (included)\n    └──────────────────┘\n           │\n           ▼\n    ┌──────────────────┐\n    │ WORKSPACE SKILLS │ (if needed)\n    └──────────────────┘\n           │\n           ▼\n    Enriched Response\n\nCore Agents (Always Run)\nIntent Decoder\n\nWhat does the user actually want?\n\nRisk Checker\n\nWhat could go wrong?\n\nTone Designer\n\nHow should this feel?\n\nExtended Agents (Included)\nAgent\tTrigger Keywords\nSystem Designer\tapi, database, architecture, system\nComplexity Assessor\tcomplex, analyze, compare\nValues Guardian\tethical, moral, values, fair\nCalling Workspace Skills\n\nThe council can call skills from your workspace when specialized knowledge is needed.\n\nExample:\n\nQuery about Quran → call quran-search-engine-mcp\nQuery about GitHub → call github-mcp\nQuery about security → call penetration-tester agent\n\nTo add workspace skills:\n\nSkills go in workspace/skills/\nAgents go in workspace/agents/\nThe council detects keywords and calls them when needed\nAdding Custom Extended Agents\n\nCreate a new .md file in agents/ folder:\n\n# Your Agent Name\n\nTrigger: keyword1, keyword2\n\nYour analysis...\n\nOutput\nImplicit Mode (Default)\n\nSkill runs silently. Apply analysis to shape response.\n\nExplicit Mode (When Asked)\n\nUse council: prefix to see full analysis.\n\nSimple Rules (80% of Value)\nIF query contains: dangerous, risk, worried, scared\nTHEN: Risk Checker flag = high\n\nIF query contains: frustrated, angry, upset\nTHEN: Tone = empathetic\n\nSEO\n\nKeywords: multi-agent, AI router, agent council, decision support, AI deliberation, extensible hub, workspace skills\n\nUse cases: personal AI assistant, decision making, risk assessment"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/adelpro/council-of-wisdom",
    "publisherUrl": "https://clawhub.ai/adelpro/council-of-wisdom",
    "owner": "adelpro",
    "version": "1.3.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/council-of-wisdom",
    "downloadUrl": "https://openagent3.xyz/downloads/council-of-wisdom",
    "agentUrl": "https://openagent3.xyz/skills/council-of-wisdom/agent",
    "manifestUrl": "https://openagent3.xyz/skills/council-of-wisdom/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/council-of-wisdom/agent.md"
  }
}