{
  "schemaVersion": "1.0",
  "item": {
    "slug": "nadirclaw",
    "name": "NadirClaw",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/doramirdor/nadirclaw",
    "canonicalUrl": "https://clawhub.ai/doramirdor/nadirclaw",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/nadirclaw",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=nadirclaw",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/install.sh"
    ],
    "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/nadirclaw"
    },
    "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/nadirclaw",
    "agentPageUrl": "https://openagent3.xyz/skills/nadirclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/nadirclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/nadirclaw/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": "NadirClaw Skill",
        "body": "NadirClaw is an open-source LLM router that classifies prompts in ~10ms and routes simple ones to cheap/local models while keeping complex work on premium models."
      },
      {
        "title": "Install",
        "body": "pip install nadirclaw"
      },
      {
        "title": "Setup",
        "body": "Run the interactive wizard:\n\nnadirclaw setup\n\nOr auto-configure for OpenClaw:\n\nnadirclaw openclaw onboard\n\nThis writes NadirClaw as a provider in OpenClaw config with model nadirclaw/auto. No restart needed."
      },
      {
        "title": "Start",
        "body": "nadirclaw serve --verbose\n\nRuns on http://localhost:8856. Any OpenAI-compatible tool can use it by pointing to this URL."
      },
      {
        "title": "Point tools at NadirClaw",
        "body": "# OpenClaw (auto)\nnadirclaw openclaw onboard\n\n# Claude Code\nANTHROPIC_BASE_URL=http://localhost:8856/v1 claude\n\n# Any OpenAI-compatible tool\nOPENAI_BASE_URL=http://localhost:8856/v1 <tool>"
      },
      {
        "title": "Routing profiles",
        "body": "Pass x-routing-profile header or use these models:\n\nnadirclaw/auto - smart routing (default)\nnadirclaw/eco - maximize savings\nnadirclaw/premium - always use best model\nnadirclaw/free - Ollama/local only\nnadirclaw/reasoning - chain-of-thought optimized"
      },
      {
        "title": "Monitor savings",
        "body": "nadirclaw savings      # cost savings report\nnadirclaw report       # detailed routing analytics\nnadirclaw dashboard    # live terminal dashboard"
      },
      {
        "title": "Key features",
        "body": "~10ms classification overhead\nSession persistence (no model bouncing mid-conversation)\nRate limit fallback (auto-retry on 429)\nAgentic task detection (forces premium for tool use)\nContext-window filtering (auto-swaps for long conversations)\nSupports: OpenAI, Anthropic, Google Gemini, Ollama, any LiteLLM provider"
      },
      {
        "title": "Troubleshooting",
        "body": "If nadirclaw serve fails, check API keys: nadirclaw setup\nFor Ollama: ensure ollama serve is running first\nLogs: nadirclaw report --last 20 to see recent routing decisions\nRaw debug: nadirclaw serve --verbose --log-raw"
      }
    ],
    "body": "NadirClaw Skill\n\nNadirClaw is an open-source LLM router that classifies prompts in ~10ms and routes simple ones to cheap/local models while keeping complex work on premium models.\n\nInstall\npip install nadirclaw\n\nSetup\n\nRun the interactive wizard:\n\nnadirclaw setup\n\n\nOr auto-configure for OpenClaw:\n\nnadirclaw openclaw onboard\n\n\nThis writes NadirClaw as a provider in OpenClaw config with model nadirclaw/auto. No restart needed.\n\nStart\nnadirclaw serve --verbose\n\n\nRuns on http://localhost:8856. Any OpenAI-compatible tool can use it by pointing to this URL.\n\nPoint tools at NadirClaw\n# OpenClaw (auto)\nnadirclaw openclaw onboard\n\n# Claude Code\nANTHROPIC_BASE_URL=http://localhost:8856/v1 claude\n\n# Any OpenAI-compatible tool\nOPENAI_BASE_URL=http://localhost:8856/v1 <tool>\n\nRouting profiles\n\nPass x-routing-profile header or use these models:\n\nnadirclaw/auto - smart routing (default)\nnadirclaw/eco - maximize savings\nnadirclaw/premium - always use best model\nnadirclaw/free - Ollama/local only\nnadirclaw/reasoning - chain-of-thought optimized\nMonitor savings\nnadirclaw savings      # cost savings report\nnadirclaw report       # detailed routing analytics\nnadirclaw dashboard    # live terminal dashboard\n\nKey features\n~10ms classification overhead\nSession persistence (no model bouncing mid-conversation)\nRate limit fallback (auto-retry on 429)\nAgentic task detection (forces premium for tool use)\nContext-window filtering (auto-swaps for long conversations)\nSupports: OpenAI, Anthropic, Google Gemini, Ollama, any LiteLLM provider\nTroubleshooting\nIf nadirclaw serve fails, check API keys: nadirclaw setup\nFor Ollama: ensure ollama serve is running first\nLogs: nadirclaw report --last 20 to see recent routing decisions\nRaw debug: nadirclaw serve --verbose --log-raw"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/doramirdor/nadirclaw",
    "publisherUrl": "https://clawhub.ai/doramirdor/nadirclaw",
    "owner": "doramirdor",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/nadirclaw",
    "downloadUrl": "https://openagent3.xyz/downloads/nadirclaw",
    "agentUrl": "https://openagent3.xyz/skills/nadirclaw/agent",
    "manifestUrl": "https://openagent3.xyz/skills/nadirclaw/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/nadirclaw/agent.md"
  }
}