{
  "schemaVersion": "1.0",
  "item": {
    "slug": "truth-search",
    "name": "truth-search",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/prismheart/truth-search",
    "canonicalUrl": "https://clawhub.ai/prismheart/truth-search",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/truth-search",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=truth-search",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/search.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": "2026-05-07T17:22:31.273Z",
      "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/truth-search"
    },
    "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/truth-search",
    "agentPageUrl": "https://openagent3.xyz/skills/truth-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/truth-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/truth-search/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": "Cloudsways TruthSearch Skill",
        "body": "Search the web and extract intelligent fragments or full-text content directly into the LLM context."
      },
      {
        "title": "Quick Setup",
        "body": "Get your Access Key: Sign up at Cloudsways\nSet environment variable:\n\nexport CLOUDSWAYS_AK=\"your-access-key\"\n\nThat's it! The skill is ready to use."
      },
      {
        "title": "Method 1: Using the Script",
        "body": "cd ~/scripts/search\n./scripts/search.sh '{\"q\": \"your search query\"}'\n\nExamples:\n\n# Basic search\n./scripts/search.sh '{\"q\": \"latest AI developments\"}'\n\n# Search with time filter and pagination\n./scripts/search.sh '{\"q\": \"OpenAI news\", \"freshness\": \"Week\", \"count\": 20}'\n\n# Deep research (extracts full content and dynamic key fragments)\n./scripts/search.sh '{\"q\": \"Agentic AI architecture\", \"enableContent\": true, \"mainText\": true}'"
      },
      {
        "title": "Method 2: Direct API Call (Recommended for Windows)",
        "body": "If the script has issues, use curl directly:\n\ncurl -s -G \\\n  --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your search query\" \\\n  --data-urlencode \"count=20\" \\\n  --data-urlencode \"freshness=Week\"\n\nReal-world example:\n\ncurl -s -G \\\n  --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=latest AI news February 2026\" \\\n  --data-urlencode \"count=20\" \\\n  --data-urlencode \"freshness=Week\" \\\n  --data-urlencode \"enableContent=true\" \\\n  --data-urlencode \"mainText=true\""
      },
      {
        "title": "Endpoint",
        "body": "GET https://truthapi.cloudsway.net/api/search/smart"
      },
      {
        "title": "Headers",
        "body": "HeaderTypeValueDescriptionAuthorizationString {YOUR_AK}Your assigned AccessKey"
      },
      {
        "title": "Request Parameters",
        "body": "ParameterRequiredTypeDefaultDescriptionqYesString-Search query term (cannot be empty)countNoInteger10Number of results. MUST be one of: 10, 20, 30, 40, or 50freshnessNoStringnullTime filter: Day (24hrs), Week, or MonthoffsetNoInteger0Pagination offset (skip N results)enableContentNoBooleanfalseExtract full text contentcontentTypeNoStringTEXTFormat: HTML, MARKDOWN, or TEXTcontentTimeoutNoFloat3.0Timeout in seconds (max: 10.0, min: 0.1)mainTextNoBooleanfalseReturn dynamic summary fragments (requires enableContent: true)\n\n⚠️ Important Notes:\n\ncount must be exactly 10, 20, 30, 40, or 50 - other values will cause errors\nmainText only works when enableContent is set to true\nFor real-time news/stock data, results are cached for 10 minutes by default"
      },
      {
        "title": "Response Format",
        "body": "The API returns JSON with the following structure:\n\n{\n  \"queryContext\": {\n    \"originalQuery\": \"your search query\"\n  },\n  \"webPages\": {\n    \"value\": [\n      {\n        \"name\": \"Article Title\",\n        \"url\": \"https://example.com/article\",\n        \"datePublished\": \"2026-02-27T15:46:11.0000000\",\n        \"snippet\": \"Short summary of the webpage...\",\n        \"mainText\": \"Dynamic summary fragments relevant to your query...\",\n        \"content\": \"Full webpage text content...\",\n        \"score\": 0.85\n      }\n    ]\n  }\n}\n\nField Descriptions:\n\nname: Page title\nurl: Full URL to the source\ndatePublished: Publication timestamp\nsnippet: Always included - short content summary\nmainText: Only if enableContent=true + mainText=true - smart query-relevant excerpts\ncontent: Only if enableContent=true - full page text\nscore: Relevance score (0-1)"
      },
      {
        "title": "Content Strategy",
        "body": "Choose the right field based on your needs:\n\nFieldLatencyToken CostUse Casesnippet⚡ Fastest💰 LowQuick overviews, browsing resultsmainText⚡⚡ Medium💰💰 MediumPrecise answers, focused researchcontent⚡⚡⚡ Slower💰💰💰 HighDeep analysis, full context needed"
      },
      {
        "title": "Recommended Settings by Use Case",
        "body": "Quick Research (default)\n\n{\"q\": \"topic\", \"count\": 10}\n\nReturns snippet only - fast and efficient.\n\nFocused Research (recommended)\n\n{\"q\": \"topic\", \"count\": 20, \"freshness\": \"Week\", \"enableContent\": true, \"mainText\": true}\n\nReturns snippet + smart excerpts - best balance of speed, cost, and relevance.\n\nDeep Research (comprehensive)\n\n{\"q\": \"topic\", \"count\": 20, \"enableContent\": true, \"contentType\": \"MARKDOWN\"}\n\nReturns full content - most comprehensive but highest token usage."
      },
      {
        "title": "Script JSON Parsing Errors",
        "body": "If you get \"Invalid JSON input\" errors on Windows, use the direct curl method instead:\n\ncurl -s -G \\\n  --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query here\""
      },
      {
        "title": "SSL/Connection Issues",
        "body": "Do not use the -k flag in curl. Ensure that SSL verification is enabled for security."
      },
      {
        "title": "Count Parameter Error",
        "body": "If you see error about count parameter, ensure it's exactly 10, 20, 30, 40, or 50:\n\n# ❌ Wrong: count=15\n# ✅ Correct: count=20"
      },
      {
        "title": "Environment Variable Not Set",
        "body": "Check if your AK is configured:\n\necho $CLOUDSWAYS_AK\n\nIf empty, set it:\n\nexport CLOUDSWAYS_AK=\"your-access-key\""
      },
      {
        "title": "Common Commands",
        "body": "# Basic search\ncurl -s -G --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query\"\n\n# Recent news (past week)\ncurl -s -G --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query\" \\\n  --data-urlencode \"freshness=Week\" \\\n  --data-urlencode \"count=20\"\n\n# Deep research with excerpts\ncurl -s -G --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query\" \\\n  --data-urlencode \"enableContent=true\" \\\n  --data-urlencode \"mainText=true\" \\\n  --data-urlencode \"count=20\""
      },
      {
        "title": "Parameter Cheat Sheet",
        "body": "count: 10, 20, 30, 40, or 50 only\nfreshness: Day, Week, or Month\ncontentType: TEXT, HTML, or MARKDOWN\ncontentTimeout: 0.1 to 10.0 seconds"
      },
      {
        "title": "Support",
        "body": "Documentation: Cloudsways Docs\nSign up: Cloudsways Sign Up\nIssues: Report in Claude Code skill repository\n\nLast Updated: 2026-02-28"
      }
    ],
    "body": "Cloudsways TruthSearch Skill\n\nSearch the web and extract intelligent fragments or full-text content directly into the LLM context.\n\nQuick Setup\nGet your Access Key: Sign up at Cloudsways\nSet environment variable:\nexport CLOUDSWAYS_AK=\"your-access-key\"\n\n\nThat's it! The skill is ready to use.\n\nQuick Start\nMethod 1: Using the Script\ncd ~/scripts/search\n./scripts/search.sh '{\"q\": \"your search query\"}'\n\n\nExamples:\n\n# Basic search\n./scripts/search.sh '{\"q\": \"latest AI developments\"}'\n\n# Search with time filter and pagination\n./scripts/search.sh '{\"q\": \"OpenAI news\", \"freshness\": \"Week\", \"count\": 20}'\n\n# Deep research (extracts full content and dynamic key fragments)\n./scripts/search.sh '{\"q\": \"Agentic AI architecture\", \"enableContent\": true, \"mainText\": true}'\n\nMethod 2: Direct API Call (Recommended for Windows)\n\nIf the script has issues, use curl directly:\n\ncurl -s -G \\\n  --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your search query\" \\\n  --data-urlencode \"count=20\" \\\n  --data-urlencode \"freshness=Week\"\n\n\nReal-world example:\n\ncurl -s -G \\\n  --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=latest AI news February 2026\" \\\n  --data-urlencode \"count=20\" \\\n  --data-urlencode \"freshness=Week\" \\\n  --data-urlencode \"enableContent=true\" \\\n  --data-urlencode \"mainText=true\"\n\nAPI Reference\nEndpoint\nGET https://truthapi.cloudsway.net/api/search/smart\n\nHeaders\nHeader\tType\tValue\tDescription\nAuthorization\tString\t{YOUR_AK}\tYour assigned AccessKey\nRequest Parameters\nParameter\tRequired\tType\tDefault\tDescription\nq\tYes\tString\t-\tSearch query term (cannot be empty)\ncount\tNo\tInteger\t10\tNumber of results. MUST be one of: 10, 20, 30, 40, or 50\nfreshness\tNo\tString\tnull\tTime filter: Day (24hrs), Week, or Month\noffset\tNo\tInteger\t0\tPagination offset (skip N results)\nenableContent\tNo\tBoolean\tfalse\tExtract full text content\ncontentType\tNo\tString\tTEXT\tFormat: HTML, MARKDOWN, or TEXT\ncontentTimeout\tNo\tFloat\t3.0\tTimeout in seconds (max: 10.0, min: 0.1)\nmainText\tNo\tBoolean\tfalse\tReturn dynamic summary fragments (requires enableContent: true)\n\n⚠️ Important Notes:\n\ncount must be exactly 10, 20, 30, 40, or 50 - other values will cause errors\nmainText only works when enableContent is set to true\nFor real-time news/stock data, results are cached for 10 minutes by default\nResponse Format\n\nThe API returns JSON with the following structure:\n\n{\n  \"queryContext\": {\n    \"originalQuery\": \"your search query\"\n  },\n  \"webPages\": {\n    \"value\": [\n      {\n        \"name\": \"Article Title\",\n        \"url\": \"https://example.com/article\",\n        \"datePublished\": \"2026-02-27T15:46:11.0000000\",\n        \"snippet\": \"Short summary of the webpage...\",\n        \"mainText\": \"Dynamic summary fragments relevant to your query...\",\n        \"content\": \"Full webpage text content...\",\n        \"score\": 0.85\n      }\n    ]\n  }\n}\n\n\nField Descriptions:\n\nname: Page title\nurl: Full URL to the source\ndatePublished: Publication timestamp\nsnippet: Always included - short content summary\nmainText: Only if enableContent=true + mainText=true - smart query-relevant excerpts\ncontent: Only if enableContent=true - full page text\nscore: Relevance score (0-1)\nContent Strategy\n\nChoose the right field based on your needs:\n\nField\tLatency\tToken Cost\tUse Case\nsnippet\t⚡ Fastest\t💰 Low\tQuick overviews, browsing results\nmainText\t⚡⚡ Medium\t💰💰 Medium\tPrecise answers, focused research\ncontent\t⚡⚡⚡ Slower\t💰💰💰 High\tDeep analysis, full context needed\nRecommended Settings by Use Case\n\nQuick Research (default)\n\n{\"q\": \"topic\", \"count\": 10}\n\n\nReturns snippet only - fast and efficient.\n\nFocused Research (recommended)\n\n{\"q\": \"topic\", \"count\": 20, \"freshness\": \"Week\", \"enableContent\": true, \"mainText\": true}\n\n\nReturns snippet + smart excerpts - best balance of speed, cost, and relevance.\n\nDeep Research (comprehensive)\n\n{\"q\": \"topic\", \"count\": 20, \"enableContent\": true, \"contentType\": \"MARKDOWN\"}\n\n\nReturns full content - most comprehensive but highest token usage.\n\nTroubleshooting\nScript JSON Parsing Errors\n\nIf you get \"Invalid JSON input\" errors on Windows, use the direct curl method instead:\n\ncurl -s -G \\\n  --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query here\"\n\nSSL/Connection Issues\n\nDo not use the -k flag in curl. Ensure that SSL verification is enabled for security.\n\nCount Parameter Error\n\nIf you see error about count parameter, ensure it's exactly 10, 20, 30, 40, or 50:\n\n# ❌ Wrong: count=15\n# ✅ Correct: count=20\n\nEnvironment Variable Not Set\n\nCheck if your AK is configured:\n\necho $CLOUDSWAYS_AK\n\n\nIf empty, set it:\n\nexport CLOUDSWAYS_AK=\"your-access-key\"\n\nQuick Reference\nCommon Commands\n# Basic search\ncurl -s -G --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query\"\n\n# Recent news (past week)\ncurl -s -G --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query\" \\\n  --data-urlencode \"freshness=Week\" \\\n  --data-urlencode \"count=20\"\n\n# Deep research with excerpts\ncurl -s -G --url \"https://truthapi.cloudsway.net/api/search/smart\" \\\n  --header \"Authorization:  ${CLOUDSWAYS_AK}\" \\\n  --data-urlencode \"q=your query\" \\\n  --data-urlencode \"enableContent=true\" \\\n  --data-urlencode \"mainText=true\" \\\n  --data-urlencode \"count=20\"\n\nParameter Cheat Sheet\ncount: 10, 20, 30, 40, or 50 only\nfreshness: Day, Week, or Month\ncontentType: TEXT, HTML, or MARKDOWN\ncontentTimeout: 0.1 to 10.0 seconds\nSupport\nDocumentation: Cloudsways Docs\nSign up: Cloudsways Sign Up\nIssues: Report in Claude Code skill repository\n\nLast Updated: 2026-02-28"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/prismheart/truth-search",
    "publisherUrl": "https://clawhub.ai/prismheart/truth-search",
    "owner": "prismheart",
    "version": "1.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/truth-search",
    "downloadUrl": "https://openagent3.xyz/downloads/truth-search",
    "agentUrl": "https://openagent3.xyz/skills/truth-search/agent",
    "manifestUrl": "https://openagent3.xyz/skills/truth-search/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/truth-search/agent.md"
  }
}