{
  "schemaVersion": "1.0",
  "item": {
    "slug": "truthcheck",
    "name": "TruthCheck",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/baiyishr/truthcheck",
    "canonicalUrl": "https://clawhub.ai/baiyishr/truthcheck",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/truthcheck",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=truthcheck",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json"
    ],
    "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": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-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/truthcheck"
    },
    "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/truthcheck",
    "agentPageUrl": "https://openagent3.xyz/skills/truthcheck/agent",
    "manifestUrl": "https://openagent3.xyz/skills/truthcheck/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/truthcheck/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": "TruthCheck Skill",
        "body": "AI content verification CLI. Verify claims, check URLs, and trace misinformation."
      },
      {
        "title": "Verify a claim",
        "body": "truthcheck verify \"claim text\" --llm gemini\n\nReturns TruthScore 0-100 with breakdown (publisher, content, corroboration, fact-checks)\n--llm is optional but improves accuracy\nAdd --json for structured output"
      },
      {
        "title": "Check URL trustworthiness",
        "body": "truthcheck check https://example.com\ntruthcheck check \"text with multiple URLs\"\ntruthcheck check -f file.txt\n\nDetects hallucinated URLs that don't exist\nRates publisher credibility"
      },
      {
        "title": "Trace a claim to its origin",
        "body": "truthcheck trace \"claim text\"           # balanced, ~1-2 min\ntruthcheck trace \"claim text\" --quick   # fast, ~30 sec\ntruthcheck trace \"claim text\" --deep    # thorough, ~3-5 min\n\nFinds original source and builds propagation tree"
      },
      {
        "title": "Look up a publisher",
        "body": "truthcheck lookup \"publisher name\""
      },
      {
        "title": "Sync publisher database",
        "body": "truthcheck sync\n\nRun periodically to keep publisher ratings current."
      },
      {
        "title": "Interpreting TruthScore",
        "body": "ScoreLabelMeaning80-100TRUEStrong evidence supports the claim60-79POSSIBLY TRUESome supporting evidence, inconclusive40-59UNCERTAINMixed or insufficient evidence20-39POSSIBLY FALSEEvidence leans against the claim0-19FALSEStrong evidence contradicts the claim"
      },
      {
        "title": "LLM Integration (Optional)",
        "body": "TruthCheck works without any LLM, but adding --llm improves content analysis accuracy.\n\ntruthcheck verify \"some claim\" --llm gemini    # recommended, fast & free tier\ntruthcheck verify \"some claim\" --llm openai    # GPT models\ntruthcheck verify \"some claim\" --llm anthropic # Claude models\ntruthcheck verify \"some claim\" --llm ollama    # local models, fully offline\n\nPrivacy: API keys are stored in your local environment only. TruthCheck never sends your keys to any external service — they are used solely for direct API calls to the respective LLM provider."
      },
      {
        "title": "Environment Variables",
        "body": "VariableWhen neededDescriptionGEMINI_API_KEY--llm geminiGoogle AI API key (free tier available)OPENAI_API_KEY--llm openaiOpenAI API keyANTHROPIC_API_KEY--llm anthropicAnthropic API keyBRAVE_API_KEY--search braveBrave Search API key\n\nNo keys needed for --llm ollama (runs locally) or default DuckDuckGo search."
      },
      {
        "title": "Tips",
        "body": "Verify commands can take 15-60 seconds depending on search results\nWithout --llm: basic scoring using publisher reputation, corroboration, and fact-checks\nWith --llm: adds AI content analysis for better accuracy\n--search brave gives better search results than default DuckDuckGo\nFor batch verification, loop through claims individually"
      }
    ],
    "body": "TruthCheck Skill\n\nAI content verification CLI. Verify claims, check URLs, and trace misinformation.\n\nCommands\nVerify a claim\ntruthcheck verify \"claim text\" --llm gemini\n\nReturns TruthScore 0-100 with breakdown (publisher, content, corroboration, fact-checks)\n--llm is optional but improves accuracy\nAdd --json for structured output\nCheck URL trustworthiness\ntruthcheck check https://example.com\ntruthcheck check \"text with multiple URLs\"\ntruthcheck check -f file.txt\n\nDetects hallucinated URLs that don't exist\nRates publisher credibility\nTrace a claim to its origin\ntruthcheck trace \"claim text\"           # balanced, ~1-2 min\ntruthcheck trace \"claim text\" --quick   # fast, ~30 sec\ntruthcheck trace \"claim text\" --deep    # thorough, ~3-5 min\n\nFinds original source and builds propagation tree\nLook up a publisher\ntruthcheck lookup \"publisher name\"\n\nSync publisher database\ntruthcheck sync\n\n\nRun periodically to keep publisher ratings current.\n\nInterpreting TruthScore\nScore\tLabel\tMeaning\n80-100\tTRUE\tStrong evidence supports the claim\n60-79\tPOSSIBLY TRUE\tSome supporting evidence, inconclusive\n40-59\tUNCERTAIN\tMixed or insufficient evidence\n20-39\tPOSSIBLY FALSE\tEvidence leans against the claim\n0-19\tFALSE\tStrong evidence contradicts the claim\nLLM Integration (Optional)\n\nTruthCheck works without any LLM, but adding --llm improves content analysis accuracy.\n\ntruthcheck verify \"some claim\" --llm gemini    # recommended, fast & free tier\ntruthcheck verify \"some claim\" --llm openai    # GPT models\ntruthcheck verify \"some claim\" --llm anthropic # Claude models\ntruthcheck verify \"some claim\" --llm ollama    # local models, fully offline\n\n\nPrivacy: API keys are stored in your local environment only. TruthCheck never sends your keys to any external service — they are used solely for direct API calls to the respective LLM provider.\n\nEnvironment Variables\nVariable\tWhen needed\tDescription\nGEMINI_API_KEY\t--llm gemini\tGoogle AI API key (free tier available)\nOPENAI_API_KEY\t--llm openai\tOpenAI API key\nANTHROPIC_API_KEY\t--llm anthropic\tAnthropic API key\nBRAVE_API_KEY\t--search brave\tBrave Search API key\n\nNo keys needed for --llm ollama (runs locally) or default DuckDuckGo search.\n\nTips\nVerify commands can take 15-60 seconds depending on search results\nWithout --llm: basic scoring using publisher reputation, corroboration, and fact-checks\nWith --llm: adds AI content analysis for better accuracy\n--search brave gives better search results than default DuckDuckGo\nFor batch verification, loop through claims individually"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/baiyishr/truthcheck",
    "publisherUrl": "https://clawhub.ai/baiyishr/truthcheck",
    "owner": "baiyishr",
    "version": "0.4.3",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/truthcheck",
    "downloadUrl": "https://openagent3.xyz/downloads/truthcheck",
    "agentUrl": "https://openagent3.xyz/skills/truthcheck/agent",
    "manifestUrl": "https://openagent3.xyz/skills/truthcheck/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/truthcheck/agent.md"
  }
}