{
  "schemaVersion": "1.0",
  "item": {
    "slug": "llmcouncil-router",
    "name": "LLM Council Router",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/ashtiwariasu/llmcouncil-router",
    "canonicalUrl": "https://clawhub.ai/ashtiwariasu/llmcouncil-router",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/llmcouncil-router",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=llmcouncil-router",
    "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/llmcouncil-router"
    },
    "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/llmcouncil-router",
    "agentPageUrl": "https://openagent3.xyz/skills/llmcouncil-router/agent",
    "manifestUrl": "https://openagent3.xyz/skills/llmcouncil-router/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/llmcouncil-router/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": "LLM Council Router",
        "body": "Route any prompt to the best-performing LLM. The API finds the top model for a given query based on thousands of peer-reviewed council deliberations — then you call that model directly."
      },
      {
        "title": "Base URL",
        "body": "https://clawbot.llmcouncil.ai"
      },
      {
        "title": "Authentication",
        "body": "Use the X-API-Key header with your LLM Council API key.\n\nX-API-Key: clwb_YOUR_KEY_HERE\n\nGet a free key at llmcouncil.ai/developers."
      },
      {
        "title": "Endpoint: POST /v1/route",
        "body": "Find the best-performing model for a query."
      },
      {
        "title": "Request",
        "body": "{\n  \"query\": \"Explain quantum entanglement simply\",\n  \"k\": 20\n}\n\nFieldTypeRequiredDescriptionquerystringYesThe prompt or question to routekintegerNoNumber of past evaluations to consider (default: 20)"
      },
      {
        "title": "Response",
        "body": "{\n  \"query\": \"Explain quantum entanglement simply\",\n  \"nearest_councils\": 20,\n  \"model\": \"anthropic/claude-sonnet-4\",\n  \"relevance\": 0.8234,\n  \"confidence\": 0.65,\n  \"model_rankings\": [\n    { \"rank\": 1, \"model\": \"anthropic/claude-sonnet-4\", \"nearby_wins\": 13, \"nearby_appearances\": 20 },\n    { \"rank\": 2, \"model\": \"openai/gpt-4.1\", \"nearby_wins\": 5, \"nearby_appearances\": 18 }\n  ]\n}\n\nFieldTypeDescriptionmodelstringTop recommended model ID (matches OpenRouter catalogue)relevancefloat (0–1)How closely matched evaluations relate to your query. Above 0.75 is strong.confidencefloat (0–1)How decisively the top model outperforms alternatives. Higher = clearer winner.nearest_councilsintegerNumber of relevant past evaluations usedmodel_rankingsarrayAll models ranked by performance across matched evaluations"
      },
      {
        "title": "How to use this skill",
        "body": "When the user asks you to find the best model for a task, or when you need to decide which LLM to use:\n\nCall the routing API with the user's query:\n\ncurl -X POST https://clawbot.llmcouncil.ai/v1/route \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $LLMCOUNCIL_API_KEY\" \\\n  -d '{\"query\": \"USER_QUERY_HERE\"}'\n\nRead the response — the model field is the best-performing model for that query type.\n\n\nChain with OpenRouter — model IDs match the OpenRouter catalogue directly, no mapping needed:\n\nimport requests, os\n\n# Step 1: Get the best model from LLM Council\nroute = requests.post(\n    \"https://clawbot.llmcouncil.ai/v1/route\",\n    headers={\"X-API-Key\": os.environ[\"LLMCOUNCIL_API_KEY\"]},\n    json={\"query\": \"Write a Python web scraper\"},\n).json()\n\nbest_model = route[\"model\"]       # e.g. \"anthropic/claude-sonnet-4\"\nconfidence = route[\"confidence\"]   # e.g. 0.85\n\n# Step 2: Call that model via OpenRouter\nanswer = requests.post(\n    \"https://openrouter.ai/api/v1/chat/completions\",\n    headers={\"Authorization\": f\"Bearer {os.environ['OPENROUTER_API_KEY']}\"},\n    json={\n        \"model\": best_model,\n        \"messages\": [{\"role\": \"user\", \"content\": \"Write a Python web scraper\"}],\n    },\n).json()\n\nprint(answer[\"choices\"][0][\"message\"][\"content\"])"
      },
      {
        "title": "Rate Limits",
        "body": "TierDaily LimitAttributionFree100 requests/dayRequiredPro10,000 requests/dayNone"
      },
      {
        "title": "When to use this",
        "body": "User asks \"which model is best for X?\"\nYou need to pick the optimal model for a specific task type\nYou want data-driven model selection instead of guessing\nYou want to chain model routing with OpenRouter for automatic best-model dispatch"
      }
    ],
    "body": "LLM Council Router\n\nRoute any prompt to the best-performing LLM. The API finds the top model for a given query based on thousands of peer-reviewed council deliberations — then you call that model directly.\n\nBase URL\nhttps://clawbot.llmcouncil.ai\n\nAuthentication\n\nUse the X-API-Key header with your LLM Council API key.\n\nX-API-Key: clwb_YOUR_KEY_HERE\n\n\nGet a free key at llmcouncil.ai/developers.\n\nEndpoint: POST /v1/route\n\nFind the best-performing model for a query.\n\nRequest\n{\n  \"query\": \"Explain quantum entanglement simply\",\n  \"k\": 20\n}\n\nField\tType\tRequired\tDescription\nquery\tstring\tYes\tThe prompt or question to route\nk\tinteger\tNo\tNumber of past evaluations to consider (default: 20)\nResponse\n{\n  \"query\": \"Explain quantum entanglement simply\",\n  \"nearest_councils\": 20,\n  \"model\": \"anthropic/claude-sonnet-4\",\n  \"relevance\": 0.8234,\n  \"confidence\": 0.65,\n  \"model_rankings\": [\n    { \"rank\": 1, \"model\": \"anthropic/claude-sonnet-4\", \"nearby_wins\": 13, \"nearby_appearances\": 20 },\n    { \"rank\": 2, \"model\": \"openai/gpt-4.1\", \"nearby_wins\": 5, \"nearby_appearances\": 18 }\n  ]\n}\n\nField\tType\tDescription\nmodel\tstring\tTop recommended model ID (matches OpenRouter catalogue)\nrelevance\tfloat (0–1)\tHow closely matched evaluations relate to your query. Above 0.75 is strong.\nconfidence\tfloat (0–1)\tHow decisively the top model outperforms alternatives. Higher = clearer winner.\nnearest_councils\tinteger\tNumber of relevant past evaluations used\nmodel_rankings\tarray\tAll models ranked by performance across matched evaluations\nHow to use this skill\n\nWhen the user asks you to find the best model for a task, or when you need to decide which LLM to use:\n\nCall the routing API with the user's query:\ncurl -X POST https://clawbot.llmcouncil.ai/v1/route \\\n  -H \"Content-Type: application/json\" \\\n  -H \"X-API-Key: $LLMCOUNCIL_API_KEY\" \\\n  -d '{\"query\": \"USER_QUERY_HERE\"}'\n\n\nRead the response — the model field is the best-performing model for that query type.\n\nChain with OpenRouter — model IDs match the OpenRouter catalogue directly, no mapping needed:\n\nimport requests, os\n\n# Step 1: Get the best model from LLM Council\nroute = requests.post(\n    \"https://clawbot.llmcouncil.ai/v1/route\",\n    headers={\"X-API-Key\": os.environ[\"LLMCOUNCIL_API_KEY\"]},\n    json={\"query\": \"Write a Python web scraper\"},\n).json()\n\nbest_model = route[\"model\"]       # e.g. \"anthropic/claude-sonnet-4\"\nconfidence = route[\"confidence\"]   # e.g. 0.85\n\n# Step 2: Call that model via OpenRouter\nanswer = requests.post(\n    \"https://openrouter.ai/api/v1/chat/completions\",\n    headers={\"Authorization\": f\"Bearer {os.environ['OPENROUTER_API_KEY']}\"},\n    json={\n        \"model\": best_model,\n        \"messages\": [{\"role\": \"user\", \"content\": \"Write a Python web scraper\"}],\n    },\n).json()\n\nprint(answer[\"choices\"][0][\"message\"][\"content\"])\n\nRate Limits\nTier\tDaily Limit\tAttribution\nFree\t100 requests/day\tRequired\nPro\t10,000 requests/day\tNone\nWhen to use this\nUser asks \"which model is best for X?\"\nYou need to pick the optimal model for a specific task type\nYou want data-driven model selection instead of guessing\nYou want to chain model routing with OpenRouter for automatic best-model dispatch"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/ashtiwariasu/llmcouncil-router",
    "publisherUrl": "https://clawhub.ai/ashtiwariasu/llmcouncil-router",
    "owner": "ashtiwariasu",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/llmcouncil-router",
    "downloadUrl": "https://openagent3.xyz/downloads/llmcouncil-router",
    "agentUrl": "https://openagent3.xyz/skills/llmcouncil-router/agent",
    "manifestUrl": "https://openagent3.xyz/skills/llmcouncil-router/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/llmcouncil-router/agent.md"
  }
}