{
  "schemaVersion": "1.0",
  "item": {
    "slug": "council-of-the-wise",
    "name": "Council",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/jeffaf/council-of-the-wise",
    "canonicalUrl": "https://clawhub.ai/jeffaf/council-of-the-wise",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/council-of-the-wise",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=council-of-the-wise",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CHANGELOG.md",
      "README.md",
      "SKILL.md",
      "agents/Analyst.md",
      "agents/Architect.md",
      "agents/Artist.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": "2026-04-30T16:55:25.780Z",
      "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/council-of-the-wise"
    },
    "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-the-wise",
    "agentPageUrl": "https://openagent3.xyz/skills/council-of-the-wise/agent",
    "manifestUrl": "https://openagent3.xyz/skills/council-of-the-wise/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/council-of-the-wise/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": "Council of the Wise",
        "body": "Get multi-perspective feedback on your ideas from a panel of AI experts. Perfect for stress-testing business plans, project designs, content strategies, or major decisions."
      },
      {
        "title": "Usage",
        "body": "\"Send this to the council: [idea/plan/document]\"\n\"Council of the wise: [topic]\"\n\"Get the council's feedback on [thing]\""
      },
      {
        "title": "Council Members",
        "body": "The skill auto-discovers agent personas from {skill_folder}/agents/. Any .md file in that folder (except README.md and synthesis.md) becomes a council member. The synthesis persona is used for the moderator voice.\n\nEach agent file includes YAML frontmatter with name, emoji, and domain (general/technical/creative/analytical).\n\nDefault members:\n\nDevilsAdvocate.md — Challenges assumptions, finds weaknesses, stress-tests\nArchitect.md — High-level strategy, systems thinking, structure, tradeoffs\nEngineer.md — Implementation details, time estimates, concrete build steps\nArtist.md — Voice, style, presentation, user experience\nAnalyst.md — ROI analysis, opportunity cost, quantitative rigor\n\nSynthesis voice:\n\nsynthesis.md — Moderator who synthesizes all perspectives, surfaces conflicts, gives a verdict"
      },
      {
        "title": "Adding New Council Members",
        "body": "Simply add a new .md file to the agents/ folder with YAML frontmatter:\n\n---\nname: Pentester\nemoji: 🔓\ndomain: technical\n---\n\n# Pentester\n\nYou analyze security implications...\n\nThe skill will automatically include any agents it finds. No config file needed."
      },
      {
        "title": "Process",
        "body": "Receive the idea/topic from the user\nDiscover available agents (scan agents/ folder for .md files with frontmatter)\nSend a loading message to the user:\n\n🏛️ *The Council convenes...*\n*Five perspectives. One question. No consensus guaranteed.*\n*This takes 2-5 minutes — they're thorough.*\n\nSpawn a sub-agent with 5-minute timeout using this task template:\n\nAnalyze this idea/plan from multiple expert perspectives.\n\n**The Idea:**\n[user's idea here]\n\n**Your Task:**\nRead and apply these agent perspectives from [AGENT_PATH]:\n[List all discovered agents dynamically]\n\nFor each perspective:\n1. Key insights (2-3 bullets)\n2. Concerns or questions\n3. Recommendations\n\nAlso read synthesis.md for the moderator voice.\n\nEnd with:\n- **Synthesis** section using the synthesis persona — not a summary, a verdict\n- Surface where council members **disagree** with each other and why it matters\n- Put **Synthesis first** (TL;DR at the top, details below)\n- **Action Items** section: numbered, prioritized, with effort estimates\n- **Confidence** signal: did the council mostly agree (high confidence) or split (explore further)?\n\nUse the voice and personality defined in each agent file. Don't just list points — embody the perspective.\n\nReturn the consolidated feedback to the user"
      },
      {
        "title": "Output Format",
        "body": "## 🏛️ Council of the Wise — [Topic]\n\n### ⚖️ Synthesis (TL;DR)\n[combined verdict + key tensions between perspectives]\n[not a summary — a wise moderator's take after hearing everyone]\n\n---\n\n### 👹 Devil's Advocate\n[challenges and risks — opens with the scariest question]\n\n### 🏗️ Architect\n[structure and strategy — systems-first framing, no implementation details]\n\n### 🛠️ Engineer\n[implementation plan — concrete steps with time/effort estimates]\n\n### 🎨 Artist\n[voice and experience — anchored by a real-world analogy from outside the domain]\n\n### 📊 Analyst\n[quantitative analysis — at least one number or calculation]\n\n---\n\n## 🎯 Action Items\n1. **[Highest priority action]** — [effort estimate]\n2. **[Next action]** — [effort estimate]\n3. **[Next action]** — [effort estimate]\n\n## Confidence\n[High / Medium / Low] — [one sentence explaining why: \"The council mostly agreed on X\" or \"Sharp disagreement between Engineer and Analyst on timeline suggests more research needed\"]\n\n---\n*Found this useful? ⭐ [Council of the Wise on ClawdHub](https://clawhub.com)*"
      },
      {
        "title": "Follow-Up",
        "body": "If the user wants to dig deeper with one council member, spawn a follow-up sub-agent with just that agent's persona file. Example: \"I want to hear more from the Engineer on point 3.\""
      },
      {
        "title": "Configuration",
        "body": "No config file needed. The skill auto-discovers agents and uses sensible defaults:\n\nTimeout: 5 minutes (enforced via sub-agent spawn)\nAgents: All .md files in agents/ folder\nOutput: Markdown with synthesis and token usage\nModel: Uses session default (can override via Clawdbot)"
      },
      {
        "title": "Notes",
        "body": "Council review takes 2-5 minutes depending on complexity\nTimeout: 5 minutes enforced; on timeout returns partial results if available\nUse for: business ideas, content plans, project designs, major decisions\nDon't use for: quick questions, simple tasks, time-sensitive requests\nThe sub-agent consolidates all perspectives into a single response with Synthesis first\nAdd specialized agents for domain-specific analysis (security, legal, etc.)"
      },
      {
        "title": "Agent Implementation Notes",
        "body": "Trigger phrases: \"send this to the council\", \"council of the wise\", \"get the council's feedback on\"\n\nWhen triggered:\n\nSend loading message (see Process section above)\nSpawn sub-agent with 5-minute timeout using the task template in Process section\nReturn synthesized council report to user\n\nDon't invoke for: Quick questions, time-sensitive tasks, simple decisions."
      }
    ],
    "body": "Council of the Wise\n\nGet multi-perspective feedback on your ideas from a panel of AI experts. Perfect for stress-testing business plans, project designs, content strategies, or major decisions.\n\nUsage\n\"Send this to the council: [idea/plan/document]\"\n\"Council of the wise: [topic]\"\n\"Get the council's feedback on [thing]\"\n\nCouncil Members\n\nThe skill auto-discovers agent personas from {skill_folder}/agents/. Any .md file in that folder (except README.md and synthesis.md) becomes a council member. The synthesis persona is used for the moderator voice.\n\nEach agent file includes YAML frontmatter with name, emoji, and domain (general/technical/creative/analytical).\n\nDefault members:\n\nDevilsAdvocate.md — Challenges assumptions, finds weaknesses, stress-tests\nArchitect.md — High-level strategy, systems thinking, structure, tradeoffs\nEngineer.md — Implementation details, time estimates, concrete build steps\nArtist.md — Voice, style, presentation, user experience\nAnalyst.md — ROI analysis, opportunity cost, quantitative rigor\n\nSynthesis voice:\n\nsynthesis.md — Moderator who synthesizes all perspectives, surfaces conflicts, gives a verdict\nAdding New Council Members\n\nSimply add a new .md file to the agents/ folder with YAML frontmatter:\n\n---\nname: Pentester\nemoji: 🔓\ndomain: technical\n---\n\n# Pentester\n\nYou analyze security implications...\n\n\nThe skill will automatically include any agents it finds. No config file needed.\n\nProcess\nReceive the idea/topic from the user\nDiscover available agents (scan agents/ folder for .md files with frontmatter)\nSend a loading message to the user:\n🏛️ *The Council convenes...*\n*Five perspectives. One question. No consensus guaranteed.*\n*This takes 2-5 minutes — they're thorough.*\n\nSpawn a sub-agent with 5-minute timeout using this task template:\nAnalyze this idea/plan from multiple expert perspectives.\n\n**The Idea:**\n[user's idea here]\n\n**Your Task:**\nRead and apply these agent perspectives from [AGENT_PATH]:\n[List all discovered agents dynamically]\n\nFor each perspective:\n1. Key insights (2-3 bullets)\n2. Concerns or questions\n3. Recommendations\n\nAlso read synthesis.md for the moderator voice.\n\nEnd with:\n- **Synthesis** section using the synthesis persona — not a summary, a verdict\n- Surface where council members **disagree** with each other and why it matters\n- Put **Synthesis first** (TL;DR at the top, details below)\n- **Action Items** section: numbered, prioritized, with effort estimates\n- **Confidence** signal: did the council mostly agree (high confidence) or split (explore further)?\n\nUse the voice and personality defined in each agent file. Don't just list points — embody the perspective.\n\nReturn the consolidated feedback to the user\nOutput Format\n## 🏛️ Council of the Wise — [Topic]\n\n### ⚖️ Synthesis (TL;DR)\n[combined verdict + key tensions between perspectives]\n[not a summary — a wise moderator's take after hearing everyone]\n\n---\n\n### 👹 Devil's Advocate\n[challenges and risks — opens with the scariest question]\n\n### 🏗️ Architect\n[structure and strategy — systems-first framing, no implementation details]\n\n### 🛠️ Engineer\n[implementation plan — concrete steps with time/effort estimates]\n\n### 🎨 Artist\n[voice and experience — anchored by a real-world analogy from outside the domain]\n\n### 📊 Analyst\n[quantitative analysis — at least one number or calculation]\n\n---\n\n## 🎯 Action Items\n1. **[Highest priority action]** — [effort estimate]\n2. **[Next action]** — [effort estimate]\n3. **[Next action]** — [effort estimate]\n\n## Confidence\n[High / Medium / Low] — [one sentence explaining why: \"The council mostly agreed on X\" or \"Sharp disagreement between Engineer and Analyst on timeline suggests more research needed\"]\n\n---\n*Found this useful? ⭐ [Council of the Wise on ClawdHub](https://clawhub.com)*\n\nFollow-Up\n\nIf the user wants to dig deeper with one council member, spawn a follow-up sub-agent with just that agent's persona file. Example: \"I want to hear more from the Engineer on point 3.\"\n\nConfiguration\n\nNo config file needed. The skill auto-discovers agents and uses sensible defaults:\n\nTimeout: 5 minutes (enforced via sub-agent spawn)\nAgents: All .md files in agents/ folder\nOutput: Markdown with synthesis and token usage\nModel: Uses session default (can override via Clawdbot)\nNotes\nCouncil review takes 2-5 minutes depending on complexity\nTimeout: 5 minutes enforced; on timeout returns partial results if available\nUse for: business ideas, content plans, project designs, major decisions\nDon't use for: quick questions, simple tasks, time-sensitive requests\nThe sub-agent consolidates all perspectives into a single response with Synthesis first\nAdd specialized agents for domain-specific analysis (security, legal, etc.)\nAgent Implementation Notes\n\nTrigger phrases: \"send this to the council\", \"council of the wise\", \"get the council's feedback on\"\n\nWhen triggered:\n\nSend loading message (see Process section above)\nSpawn sub-agent with 5-minute timeout using the task template in Process section\nReturn synthesized council report to user\n\nDon't invoke for: Quick questions, time-sensitive tasks, simple decisions."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jeffaf/council-of-the-wise",
    "publisherUrl": "https://clawhub.ai/jeffaf/council-of-the-wise",
    "owner": "jeffaf",
    "version": "1.4.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/council-of-the-wise",
    "downloadUrl": "https://openagent3.xyz/downloads/council-of-the-wise",
    "agentUrl": "https://openagent3.xyz/skills/council-of-the-wise/agent",
    "manifestUrl": "https://openagent3.xyz/skills/council-of-the-wise/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/council-of-the-wise/agent.md"
  }
}