{
  "schemaVersion": "1.0",
  "item": {
    "slug": "model-council-pro",
    "name": "Model Council Pro",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/aiwithabidi/model-council-pro",
    "canonicalUrl": "https://clawhub.ai/aiwithabidi/model-council-pro",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/model-council-pro",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=model-council-pro",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/model_council.py"
    ],
    "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/model-council-pro"
    },
    "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/model-council-pro",
    "agentPageUrl": "https://openagent3.xyz/skills/model-council-pro/agent",
    "manifestUrl": "https://openagent3.xyz/skills/model-council-pro/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/model-council-pro/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": "Model Council 🏛️",
        "body": "Get consensus from multiple AI models on any question.\n\nSend your query to 3+ different LLMs simultaneously via OpenRouter. A judge model evaluates all responses and produces a winner, reasoning, and synthesized best answer."
      },
      {
        "title": "When to Use",
        "body": "Important decisions — Don't trust one model's opinion\nCode review — Get multiple perspectives on architecture choices\nResearch verification — Cross-check facts across models\nCreative work — Compare writing styles and pick the best\nDebugging — When one model is stuck, others might see the issue"
      },
      {
        "title": "How It Works",
        "body": "Your Question\n    ├──→ Claude Sonnet 4    ──→ Response A\n    ├──→ GPT-4o             ──→ Response B\n    └──→ Gemini 2.0 Flash   ──→ Response C\n                                    │\n                              Judge (Opus) evaluates all\n                                    │\n                              ├── Winner + Reasoning\n                              ├── Synthesized Best Answer\n                              └── Cost Breakdown"
      },
      {
        "title": "Quick Start",
        "body": "# Basic usage\npython3 {baseDir}/scripts/model_council.py \"What's the best database for a real-time analytics dashboard?\"\n\n# Custom models\npython3 {baseDir}/scripts/model_council.py --models \"anthropic/claude-sonnet-4,openai/gpt-4o,google/gemini-2.5-pro\" \"Your question\"\n\n# Custom judge\npython3 {baseDir}/scripts/model_council.py --judge \"openai/gpt-4o\" \"Your question\"\n\n# JSON output\npython3 {baseDir}/scripts/model_council.py --json \"Your question\"\n\n# Set max tokens per response\npython3 {baseDir}/scripts/model_council.py --max-tokens 2000 \"Your question\""
      },
      {
        "title": "Configuration",
        "body": "FlagDefaultDescription--modelsclaude-sonnet-4, gpt-4o, gemini-2.0-flashComma-separated model list--judgeanthropic/claude-opus-4-6Judge model--max-tokens1024Max tokens per council member--jsonfalseOutput as JSON--timeout60Timeout per model (seconds)"
      },
      {
        "title": "Environment",
        "body": "Requires OPENROUTER_API_KEY environment variable."
      },
      {
        "title": "Output Example",
        "body": "═══ MODEL COUNCIL RESULTS ═══\n\nQuestion: What's the best way to handle auth in a microservices architecture?\n\n── Council Member Responses ──\n\n🤖 anthropic/claude-sonnet-4 ($0.0043)\nUse a centralized auth service with JWT tokens...\n\n🤖 openai/gpt-4o ($0.0038)\nImplement OAuth 2.0 with an API gateway...\n\n🤖 google/gemini-2.0-flash-001 ($0.0012)\nConsider using service mesh with mTLS...\n\n── Judge Verdict (anthropic/claude-opus-4-6, $0.0125) ──\n\n🏆 Winner: anthropic/claude-sonnet-4\nReasoning: Most comprehensive and practical approach...\n\n📝 Synthesized Answer:\nThe best approach combines elements from all three...\n\n💰 Total Cost: $0.0218"
      },
      {
        "title": "Credits",
        "body": "Built by M. Abidi | agxntsix.ai\nYouTube | GitHub\nPart of the AgxntSix Skill Suite for OpenClaw agents.\n\n📅 Need help setting up OpenClaw for your business? Book a free consultation"
      }
    ],
    "body": "Model Council 🏛️\n\nGet consensus from multiple AI models on any question.\n\nSend your query to 3+ different LLMs simultaneously via OpenRouter. A judge model evaluates all responses and produces a winner, reasoning, and synthesized best answer.\n\nWhen to Use\nImportant decisions — Don't trust one model's opinion\nCode review — Get multiple perspectives on architecture choices\nResearch verification — Cross-check facts across models\nCreative work — Compare writing styles and pick the best\nDebugging — When one model is stuck, others might see the issue\nHow It Works\nYour Question\n    ├──→ Claude Sonnet 4    ──→ Response A\n    ├──→ GPT-4o             ──→ Response B\n    └──→ Gemini 2.0 Flash   ──→ Response C\n                                    │\n                              Judge (Opus) evaluates all\n                                    │\n                              ├── Winner + Reasoning\n                              ├── Synthesized Best Answer\n                              └── Cost Breakdown\n\nQuick Start\n# Basic usage\npython3 {baseDir}/scripts/model_council.py \"What's the best database for a real-time analytics dashboard?\"\n\n# Custom models\npython3 {baseDir}/scripts/model_council.py --models \"anthropic/claude-sonnet-4,openai/gpt-4o,google/gemini-2.5-pro\" \"Your question\"\n\n# Custom judge\npython3 {baseDir}/scripts/model_council.py --judge \"openai/gpt-4o\" \"Your question\"\n\n# JSON output\npython3 {baseDir}/scripts/model_council.py --json \"Your question\"\n\n# Set max tokens per response\npython3 {baseDir}/scripts/model_council.py --max-tokens 2000 \"Your question\"\n\nConfiguration\nFlag\tDefault\tDescription\n--models\tclaude-sonnet-4, gpt-4o, gemini-2.0-flash\tComma-separated model list\n--judge\tanthropic/claude-opus-4-6\tJudge model\n--max-tokens\t1024\tMax tokens per council member\n--json\tfalse\tOutput as JSON\n--timeout\t60\tTimeout per model (seconds)\nEnvironment\n\nRequires OPENROUTER_API_KEY environment variable.\n\nOutput Example\n═══ MODEL COUNCIL RESULTS ═══\n\nQuestion: What's the best way to handle auth in a microservices architecture?\n\n── Council Member Responses ──\n\n🤖 anthropic/claude-sonnet-4 ($0.0043)\nUse a centralized auth service with JWT tokens...\n\n🤖 openai/gpt-4o ($0.0038)\nImplement OAuth 2.0 with an API gateway...\n\n🤖 google/gemini-2.0-flash-001 ($0.0012)\nConsider using service mesh with mTLS...\n\n── Judge Verdict (anthropic/claude-opus-4-6, $0.0125) ──\n\n🏆 Winner: anthropic/claude-sonnet-4\nReasoning: Most comprehensive and practical approach...\n\n📝 Synthesized Answer:\nThe best approach combines elements from all three...\n\n💰 Total Cost: $0.0218\n\nCredits\n\nBuilt by M. Abidi | agxntsix.ai YouTube | GitHub Part of the AgxntSix Skill Suite for OpenClaw agents.\n\n📅 Need help setting up OpenClaw for your business? Book a free consultation"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/aiwithabidi/model-council-pro",
    "publisherUrl": "https://clawhub.ai/aiwithabidi/model-council-pro",
    "owner": "aiwithabidi",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/model-council-pro",
    "downloadUrl": "https://openagent3.xyz/downloads/model-council-pro",
    "agentUrl": "https://openagent3.xyz/skills/model-council-pro/agent",
    "manifestUrl": "https://openagent3.xyz/skills/model-council-pro/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/model-council-pro/agent.md"
  }
}