# Send truth-search to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - 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. ## Suggested prompts ### New install ```text 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. ``` ### Upgrade existing ```text 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. ``` ## Machine-readable fields ```json { "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": { "downloadUrl": "/downloads/truth-search", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=truth-search", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "scripts/search.sh" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "truth-search", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-12T20:30:15.755Z", "expiresAt": "2026-05-19T20:30:15.755Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=truth-search", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=truth-search", "contentDisposition": "attachment; filename=\"truth-search-1.0.6.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "truth-search" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "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." ] } }, "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" } } ``` ## Documentation ### Cloudsways TruthSearch Skill Search the web and extract intelligent fragments or full-text content directly into the LLM context. ### Quick Setup Get your Access Key: Sign up at Cloudsways Set environment variable: export CLOUDSWAYS_AK="your-access-key" That's it! The skill is ready to use. ### Method 1: Using the Script cd ~/scripts/search ./scripts/search.sh '{"q": "your search query"}' Examples: # Basic search ./scripts/search.sh '{"q": "latest AI developments"}' # Search with time filter and pagination ./scripts/search.sh '{"q": "OpenAI news", "freshness": "Week", "count": 20}' # Deep research (extracts full content and dynamic key fragments) ./scripts/search.sh '{"q": "Agentic AI architecture", "enableContent": true, "mainText": true}' ### Method 2: Direct API Call (Recommended for Windows) If the script has issues, use curl directly: curl -s -G \\ --url "https://truthapi.cloudsway.net/api/search/smart" \\ --header "Authorization: ${CLOUDSWAYS_AK}" \\ --data-urlencode "q=your search query" \\ --data-urlencode "count=20" \\ --data-urlencode "freshness=Week" Real-world example: curl -s -G \\ --url "https://truthapi.cloudsway.net/api/search/smart" \\ --header "Authorization: ${CLOUDSWAYS_AK}" \\ --data-urlencode "q=latest AI news February 2026" \\ --data-urlencode "count=20" \\ --data-urlencode "freshness=Week" \\ --data-urlencode "enableContent=true" \\ --data-urlencode "mainText=true" ### Endpoint GET https://truthapi.cloudsway.net/api/search/smart ### Headers HeaderTypeValueDescriptionAuthorizationString {YOUR_AK}Your assigned AccessKey ### Request Parameters 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) ⚠️ Important Notes: count must be exactly 10, 20, 30, 40, or 50 - other values will cause errors mainText only works when enableContent is set to true For real-time news/stock data, results are cached for 10 minutes by default ### Response Format The API returns JSON with the following structure: { "queryContext": { "originalQuery": "your search query" }, "webPages": { "value": [ { "name": "Article Title", "url": "https://example.com/article", "datePublished": "2026-02-27T15:46:11.0000000", "snippet": "Short summary of the webpage...", "mainText": "Dynamic summary fragments relevant to your query...", "content": "Full webpage text content...", "score": 0.85 } ] } } Field Descriptions: name: Page title url: Full URL to the source datePublished: Publication timestamp snippet: Always included - short content summary mainText: Only if enableContent=true + mainText=true - smart query-relevant excerpts content: Only if enableContent=true - full page text score: Relevance score (0-1) ### Content Strategy Choose the right field based on your needs: FieldLatencyToken CostUse Casesnippet⚡ Fastest💰 LowQuick overviews, browsing resultsmainText⚡⚡ Medium💰💰 MediumPrecise answers, focused researchcontent⚡⚡⚡ Slower💰💰💰 HighDeep analysis, full context needed ### Recommended Settings by Use Case Quick Research (default) {"q": "topic", "count": 10} Returns snippet only - fast and efficient. Focused Research (recommended) {"q": "topic", "count": 20, "freshness": "Week", "enableContent": true, "mainText": true} Returns snippet + smart excerpts - best balance of speed, cost, and relevance. Deep Research (comprehensive) {"q": "topic", "count": 20, "enableContent": true, "contentType": "MARKDOWN"} Returns full content - most comprehensive but highest token usage. ### Script JSON Parsing Errors If you get "Invalid JSON input" errors on Windows, use the direct curl method instead: curl -s -G \\ --url "https://truthapi.cloudsway.net/api/search/smart" \\ --header "Authorization: ${CLOUDSWAYS_AK}" \\ --data-urlencode "q=your query here" ### SSL/Connection Issues Do not use the -k flag in curl. Ensure that SSL verification is enabled for security. ### Count Parameter Error If you see error about count parameter, ensure it's exactly 10, 20, 30, 40, or 50: # ❌ Wrong: count=15 # ✅ Correct: count=20 ### Environment Variable Not Set Check if your AK is configured: echo $CLOUDSWAYS_AK If empty, set it: export CLOUDSWAYS_AK="your-access-key" ### Common Commands # Basic search curl -s -G --url "https://truthapi.cloudsway.net/api/search/smart" \\ --header "Authorization: ${CLOUDSWAYS_AK}" \\ --data-urlencode "q=your query" # Recent news (past week) curl -s -G --url "https://truthapi.cloudsway.net/api/search/smart" \\ --header "Authorization: ${CLOUDSWAYS_AK}" \\ --data-urlencode "q=your query" \\ --data-urlencode "freshness=Week" \\ --data-urlencode "count=20" # Deep research with excerpts curl -s -G --url "https://truthapi.cloudsway.net/api/search/smart" \\ --header "Authorization: ${CLOUDSWAYS_AK}" \\ --data-urlencode "q=your query" \\ --data-urlencode "enableContent=true" \\ --data-urlencode "mainText=true" \\ --data-urlencode "count=20" ### Parameter Cheat Sheet count: 10, 20, 30, 40, or 50 only freshness: Day, Week, or Month contentType: TEXT, HTML, or MARKDOWN contentTimeout: 0.1 to 10.0 seconds ### Support Documentation: Cloudsways Docs Sign up: Cloudsways Sign Up Issues: Report in Claude Code skill repository Last Updated: 2026-02-28 ## Trust - Source: tencent - Verification: Indexed source record - Publisher: prismheart - Version: 1.0.4 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-12T20:30:15.755Z - Expires at: 2026-05-19T20:30:15.755Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/truth-search) - [Send to Agent page](https://openagent3.xyz/skills/truth-search/agent) - [JSON manifest](https://openagent3.xyz/skills/truth-search/agent.json) - [Markdown brief](https://openagent3.xyz/skills/truth-search/agent.md) - [Download page](https://openagent3.xyz/downloads/truth-search)