{
  "schemaVersion": "1.0",
  "item": {
    "slug": "web-search-exa",
    "name": "Web Search by Exa",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/theishangoswami/web-search-exa",
    "canonicalUrl": "https://clawhub.ai/theishangoswami/web-search-exa",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/web-search-exa",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=web-search-exa",
    "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": "2026-05-07T17:22:31.273Z",
      "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/web-search-exa"
    },
    "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/web-search-exa",
    "agentPageUrl": "https://openagent3.xyz/skills/web-search-exa/agent",
    "manifestUrl": "https://openagent3.xyz/skills/web-search-exa/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/web-search-exa/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": "Exa — Neural Web Search & Research",
        "body": "Exa is a neural search engine. Unlike keyword-based search, it understands meaning — you describe the page you're looking for and it finds it. Returns clean, LLM-ready content with no scraping needed.\n\nMCP server: https://mcp.exa.ai/mcp\nFree tier: generous rate limits, no key needed for basic tools\nAPI key: dashboard.exa.ai/api-keys — unlocks higher limits + all tools\nDocs: exa.ai/docs\nGitHub: github.com/exa-labs/exa-mcp-server"
      },
      {
        "title": "Setup",
        "body": "Add the MCP server to your agent config:\n\n# OpenClaw\nopenclaw mcp add exa --url \"https://mcp.exa.ai/mcp\"\n\nOr in any MCP config JSON:\n\n{\n  \"mcpServers\": {\n    \"exa\": {\n      \"url\": \"https://mcp.exa.ai/mcp\"\n    }\n  }\n}\n\nTo unlock all tools and remove rate limits, append your API key:\n\nhttps://mcp.exa.ai/mcp?exaApiKey=YOUR_EXA_KEY\n\nTo enable specific optional tools:\n\nhttps://mcp.exa.ai/mcp?exaApiKey=YOUR_KEY&tools=web_search_exa,web_search_advanced_exa,people_search_exa,crawling_exa,company_research_exa,get_code_context_exa,deep_researcher_start,deep_researcher_check,deep_search_exa"
      },
      {
        "title": "Default tools (available without API key)",
        "body": "ToolWhat it doesweb_search_exaGeneral-purpose web search — clean content, fastget_code_context_exaCode examples + docs from GitHub, Stack Overflow, official docscompany_research_exaCompany overview, news, funding, competitors"
      },
      {
        "title": "Optional tools (enable via tools param, need API key for some)",
        "body": "ToolWhat it doesweb_search_advanced_exaFull-control search: domain filters, date ranges, categories, content modescrawling_exaExtract full page content from a known URL — handles JS, PDFs, complex layoutspeople_search_exaFind LinkedIn profiles, professional backgrounds, expertsdeep_researcher_startKick off an async multi-step research agent → detailed reportdeep_researcher_checkPoll status / retrieve results from deep researchdeep_search_exaSingle-call deep search with synthesized answer + citations (needs API key)"
      },
      {
        "title": "web_search_exa",
        "body": "Fast general search. Describe what you're looking for in natural language.\n\nParameters:\n\nquery (string, required) — describe the page you want to find\nnumResults (int) — number of results, default 10\ntype — auto (best quality), fast (lower latency), deep (multi-step reasoning)\nlivecrawl — fallback (default) or preferred (always fetch fresh)\ncontextMaxCharacters (int) — cap the returned content size\n\nweb_search_exa {\n  \"query\": \"blog posts about using vector databases for recommendation systems\",\n  \"numResults\": 8\n}\n\nweb_search_exa {\n  \"query\": \"latest OpenAI announcements March 2026\",\n  \"numResults\": 5,\n  \"type\": \"fast\"\n}"
      },
      {
        "title": "web_search_advanced_exa",
        "body": "The power-user tool. Everything web_search_exa does, plus domain filters, date filters, category targeting, and content extraction modes.\n\nExtra parameters beyond basic search:\n\nParameterTypeWhat it doesincludeDomainsstring[]Only return results from these domains (max 1200)excludeDomainsstring[]Block results from these domainscategorystringTarget content type — see table belowstartPublishedDatestringISO date, results published after thisendPublishedDatestringISO date, results published before thismaxAgeHoursintContent freshness — 0 = always livecrawl, -1 = cache only, 24 = cache if <24hcontents.highlightsobjectExtractive snippets relevant to query. Set maxCharacters to control sizecontents.textobjectFull page as clean markdown. Set maxCharacters to capcontents.summaryobjectLLM-generated summary. Supports query and JSON schema for structured extraction\n\nCategories:\n\nCategoryBest forcompanyCompany pages, LinkedIn company profilespeopleLinkedIn profiles, professional bios, personal sitesresearch paperarXiv, academic papers, peer-reviewed researchnewsCurrent events, journalismtweetPosts from X/Twitterpersonal siteBlogs, personal pagesfinancial reportSEC filings, earnings reports"
      },
      {
        "title": "Examples",
        "body": "Research papers:\n\nweb_search_advanced_exa {\n  \"query\": \"transformer architecture improvements for long-context windows\",\n  \"category\": \"research paper\",\n  \"numResults\": 15,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 3000 } }\n}\n\nCompany list building with structured extraction:\n\nweb_search_advanced_exa {\n  \"query\": \"Series A B2B SaaS companies in climate tech founded after 2022\",\n  \"category\": \"company\",\n  \"numResults\": 25,\n  \"contents\": {\n    \"summary\": {\n      \"query\": \"company name, what they do, funding stage, location\",\n      \"schema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"name\": { \"type\": \"string\" },\n          \"description\": { \"type\": \"string\" },\n          \"funding\": { \"type\": \"string\" },\n          \"location\": { \"type\": \"string\" }\n        }\n      }\n    }\n  }\n}\n\nPeople search — find candidates with specific profiles:\n\nweb_search_advanced_exa {\n  \"query\": \"machine learning engineers at fintech startups in NYC with experience in fraud detection\",\n  \"category\": \"people\",\n  \"numResults\": 20,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 2000 } }\n}\n\nFinding pages similar to a known URL:\nUse the URL itself as the query — Exa will find semantically similar pages:\n\nweb_search_advanced_exa {\n  \"query\": \"https://linkedin.com/in/some-candidate-profile\",\n  \"numResults\": 15,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 2000 } }\n}\n\nRecent news with freshness control:\n\nweb_search_advanced_exa {\n  \"query\": \"AI regulation policy updates\",\n  \"category\": \"news\",\n  \"maxAgeHours\": 72,\n  \"numResults\": 10,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 4000 } }\n}\n\nScoped domain search:\n\nweb_search_advanced_exa {\n  \"query\": \"authentication best practices\",\n  \"includeDomains\": [\"owasp.org\", \"auth0.com\", \"docs.github.com\"],\n  \"numResults\": 10,\n  \"contents\": { \"text\": { \"maxCharacters\": 5000 } }\n}"
      },
      {
        "title": "company_research_exa",
        "body": "One-call company research. Returns business overview, recent news, funding, and competitive landscape.\n\ncompany_research_exa { \"query\": \"Stripe payments company overview and recent news\" }\n\ncompany_research_exa { \"query\": \"what does Anduril Industries do and who are their competitors\" }"
      },
      {
        "title": "people_search_exa",
        "body": "Find professionals by role, company, location, expertise. Returns LinkedIn profiles and bios.\n\npeople_search_exa { \"query\": \"VP of Engineering at healthcare startups in San Francisco\" }\n\npeople_search_exa { \"query\": \"AI researchers specializing in multimodal models\" }"
      },
      {
        "title": "get_code_context_exa",
        "body": "Search GitHub repos, Stack Overflow, and documentation for code examples and API usage patterns.\n\nget_code_context_exa { \"query\": \"how to implement rate limiting in Express.js with Redis\" }\n\nget_code_context_exa { \"query\": \"Python asyncio connection pooling example with aiohttp\" }"
      },
      {
        "title": "crawling_exa",
        "body": "Extract clean content from a specific URL. Handles JavaScript-rendered pages, PDFs, and complex layouts. Returns markdown.\n\ncrawling_exa { \"url\": \"https://arxiv.org/abs/2301.07041\" }\n\nGood for when you already have the URL and want to read the page."
      },
      {
        "title": "deep_researcher_start + deep_researcher_check",
        "body": "Long-running async research. Exa's research agent searches, reads, and compiles a detailed report.\n\nStart a research task:\n\ndeep_researcher_start {\n  \"query\": \"competitive landscape of AI code generation tools in 2026 — key players, pricing, technical approaches, market share\"\n}\n\nCheck status (use the researchId from the start response):\n\ndeep_researcher_check { \"researchId\": \"abc123...\" }\n\nPoll deep_researcher_check until status is completed. The final response includes the full report."
      },
      {
        "title": "deep_search_exa",
        "body": "Single-call deep search: expands your query across multiple angles, searches, reads results, and returns a synthesized answer with grounded citations. Requires API key.\n\ndeep_search_exa { \"query\": \"what are the leading approaches to multimodal RAG in production systems\" }\n\nSupports structured output via outputSchema:\n\ndeep_search_exa {\n  \"query\": \"top 10 aerospace companies by revenue\",\n  \"type\": \"deep\",\n  \"outputSchema\": {\n    \"type\": \"object\",\n    \"required\": [\"companies\"],\n    \"properties\": {\n      \"companies\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"name\": { \"type\": \"string\" },\n            \"revenue\": { \"type\": \"string\" },\n            \"hq\": { \"type\": \"string\" }\n          }\n        }\n      }\n    }\n  }\n}"
      },
      {
        "title": "Query Craft",
        "body": "Exa is neural — it matches on meaning, not keywords. Write queries like you'd describe the ideal page to a colleague.\n\nDo: \"blog post about using embeddings for product recommendations at scale\"\nDon't: \"embeddings product recommendations\"\n\nDo: \"Stripe payments company San Francisco fintech\"\nDon't: \"Stripe\" (too ambiguous)\n\nUse category when you know the content type — it makes a big difference.\nFor broader coverage, run 2-3 query variations in parallel and deduplicate results.\nFor agentic workflows, use highlights instead of full text — it's 10x more token-efficient while keeping the relevant parts."
      },
      {
        "title": "Token Efficiency",
        "body": "Content modeWhen to usehighlightsAgent workflows, factual lookups, multi-step pipelines — most token-efficienttextDeep analysis, when you need full page contextsummaryQuick overviews, structured extraction with JSON schema\n\nSet maxCharacters on any content mode to control output size."
      },
      {
        "title": "When to Reach for Which Tool",
        "body": "I need to...UseQuick web lookupweb_search_exaResearch papers, academic searchweb_search_advanced_exa + category: \"research paper\"Company intel, competitive analysiscompany_research_exa or advanced + category: \"company\"Find people, candidates, expertspeople_search_exa or advanced + category: \"people\"Code examples, API docsget_code_context_exaRead a specific URLcrawling_exaFind pages similar to a URLweb_search_advanced_exa with URL as queryRecent news / tweetsAdvanced + category: \"news\" or \"tweet\" + maxAgeHoursDetailed research reportdeep_researcher_start → deep_researcher_checkQuick answer with citationsdeep_search_exa\n\nDocs: exa.ai/docs — Dashboard: dashboard.exa.ai — Support: support@exa.ai"
      }
    ],
    "body": "Exa — Neural Web Search & Research\n\nExa is a neural search engine. Unlike keyword-based search, it understands meaning — you describe the page you're looking for and it finds it. Returns clean, LLM-ready content with no scraping needed.\n\nMCP server: https://mcp.exa.ai/mcp Free tier: generous rate limits, no key needed for basic tools API key: dashboard.exa.ai/api-keys — unlocks higher limits + all tools Docs: exa.ai/docs GitHub: github.com/exa-labs/exa-mcp-server\n\nSetup\n\nAdd the MCP server to your agent config:\n\n# OpenClaw\nopenclaw mcp add exa --url \"https://mcp.exa.ai/mcp\"\n\n\nOr in any MCP config JSON:\n\n{\n  \"mcpServers\": {\n    \"exa\": {\n      \"url\": \"https://mcp.exa.ai/mcp\"\n    }\n  }\n}\n\n\nTo unlock all tools and remove rate limits, append your API key:\n\nhttps://mcp.exa.ai/mcp?exaApiKey=YOUR_EXA_KEY\n\n\nTo enable specific optional tools:\n\nhttps://mcp.exa.ai/mcp?exaApiKey=YOUR_KEY&tools=web_search_exa,web_search_advanced_exa,people_search_exa,crawling_exa,company_research_exa,get_code_context_exa,deep_researcher_start,deep_researcher_check,deep_search_exa\n\nTool Reference\nDefault tools (available without API key)\nTool\tWhat it does\nweb_search_exa\tGeneral-purpose web search — clean content, fast\nget_code_context_exa\tCode examples + docs from GitHub, Stack Overflow, official docs\ncompany_research_exa\tCompany overview, news, funding, competitors\nOptional tools (enable via tools param, need API key for some)\nTool\tWhat it does\nweb_search_advanced_exa\tFull-control search: domain filters, date ranges, categories, content modes\ncrawling_exa\tExtract full page content from a known URL — handles JS, PDFs, complex layouts\npeople_search_exa\tFind LinkedIn profiles, professional backgrounds, experts\ndeep_researcher_start\tKick off an async multi-step research agent → detailed report\ndeep_researcher_check\tPoll status / retrieve results from deep research\ndeep_search_exa\tSingle-call deep search with synthesized answer + citations (needs API key)\nweb_search_exa\n\nFast general search. Describe what you're looking for in natural language.\n\nParameters:\n\nquery (string, required) — describe the page you want to find\nnumResults (int) — number of results, default 10\ntype — auto (best quality), fast (lower latency), deep (multi-step reasoning)\nlivecrawl — fallback (default) or preferred (always fetch fresh)\ncontextMaxCharacters (int) — cap the returned content size\nweb_search_exa {\n  \"query\": \"blog posts about using vector databases for recommendation systems\",\n  \"numResults\": 8\n}\n\nweb_search_exa {\n  \"query\": \"latest OpenAI announcements March 2026\",\n  \"numResults\": 5,\n  \"type\": \"fast\"\n}\n\nweb_search_advanced_exa\n\nThe power-user tool. Everything web_search_exa does, plus domain filters, date filters, category targeting, and content extraction modes.\n\nExtra parameters beyond basic search:\n\nParameter\tType\tWhat it does\nincludeDomains\tstring[]\tOnly return results from these domains (max 1200)\nexcludeDomains\tstring[]\tBlock results from these domains\ncategory\tstring\tTarget content type — see table below\nstartPublishedDate\tstring\tISO date, results published after this\nendPublishedDate\tstring\tISO date, results published before this\nmaxAgeHours\tint\tContent freshness — 0 = always livecrawl, -1 = cache only, 24 = cache if <24h\ncontents.highlights\tobject\tExtractive snippets relevant to query. Set maxCharacters to control size\ncontents.text\tobject\tFull page as clean markdown. Set maxCharacters to cap\ncontents.summary\tobject\tLLM-generated summary. Supports query and JSON schema for structured extraction\n\nCategories:\n\nCategory\tBest for\ncompany\tCompany pages, LinkedIn company profiles\npeople\tLinkedIn profiles, professional bios, personal sites\nresearch paper\tarXiv, academic papers, peer-reviewed research\nnews\tCurrent events, journalism\ntweet\tPosts from X/Twitter\npersonal site\tBlogs, personal pages\nfinancial report\tSEC filings, earnings reports\nExamples\n\nResearch papers:\n\nweb_search_advanced_exa {\n  \"query\": \"transformer architecture improvements for long-context windows\",\n  \"category\": \"research paper\",\n  \"numResults\": 15,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 3000 } }\n}\n\n\nCompany list building with structured extraction:\n\nweb_search_advanced_exa {\n  \"query\": \"Series A B2B SaaS companies in climate tech founded after 2022\",\n  \"category\": \"company\",\n  \"numResults\": 25,\n  \"contents\": {\n    \"summary\": {\n      \"query\": \"company name, what they do, funding stage, location\",\n      \"schema\": {\n        \"type\": \"object\",\n        \"properties\": {\n          \"name\": { \"type\": \"string\" },\n          \"description\": { \"type\": \"string\" },\n          \"funding\": { \"type\": \"string\" },\n          \"location\": { \"type\": \"string\" }\n        }\n      }\n    }\n  }\n}\n\n\nPeople search — find candidates with specific profiles:\n\nweb_search_advanced_exa {\n  \"query\": \"machine learning engineers at fintech startups in NYC with experience in fraud detection\",\n  \"category\": \"people\",\n  \"numResults\": 20,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 2000 } }\n}\n\n\nFinding pages similar to a known URL: Use the URL itself as the query — Exa will find semantically similar pages:\n\nweb_search_advanced_exa {\n  \"query\": \"https://linkedin.com/in/some-candidate-profile\",\n  \"numResults\": 15,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 2000 } }\n}\n\n\nRecent news with freshness control:\n\nweb_search_advanced_exa {\n  \"query\": \"AI regulation policy updates\",\n  \"category\": \"news\",\n  \"maxAgeHours\": 72,\n  \"numResults\": 10,\n  \"contents\": { \"highlights\": { \"maxCharacters\": 4000 } }\n}\n\n\nScoped domain search:\n\nweb_search_advanced_exa {\n  \"query\": \"authentication best practices\",\n  \"includeDomains\": [\"owasp.org\", \"auth0.com\", \"docs.github.com\"],\n  \"numResults\": 10,\n  \"contents\": { \"text\": { \"maxCharacters\": 5000 } }\n}\n\ncompany_research_exa\n\nOne-call company research. Returns business overview, recent news, funding, and competitive landscape.\n\ncompany_research_exa { \"query\": \"Stripe payments company overview and recent news\" }\n\ncompany_research_exa { \"query\": \"what does Anduril Industries do and who are their competitors\" }\n\npeople_search_exa\n\nFind professionals by role, company, location, expertise. Returns LinkedIn profiles and bios.\n\npeople_search_exa { \"query\": \"VP of Engineering at healthcare startups in San Francisco\" }\n\npeople_search_exa { \"query\": \"AI researchers specializing in multimodal models\" }\n\nget_code_context_exa\n\nSearch GitHub repos, Stack Overflow, and documentation for code examples and API usage patterns.\n\nget_code_context_exa { \"query\": \"how to implement rate limiting in Express.js with Redis\" }\n\nget_code_context_exa { \"query\": \"Python asyncio connection pooling example with aiohttp\" }\n\ncrawling_exa\n\nExtract clean content from a specific URL. Handles JavaScript-rendered pages, PDFs, and complex layouts. Returns markdown.\n\ncrawling_exa { \"url\": \"https://arxiv.org/abs/2301.07041\" }\n\n\nGood for when you already have the URL and want to read the page.\n\ndeep_researcher_start + deep_researcher_check\n\nLong-running async research. Exa's research agent searches, reads, and compiles a detailed report.\n\nStart a research task:\n\ndeep_researcher_start {\n  \"query\": \"competitive landscape of AI code generation tools in 2026 — key players, pricing, technical approaches, market share\"\n}\n\n\nCheck status (use the researchId from the start response):\n\ndeep_researcher_check { \"researchId\": \"abc123...\" }\n\n\nPoll deep_researcher_check until status is completed. The final response includes the full report.\n\ndeep_search_exa\n\nSingle-call deep search: expands your query across multiple angles, searches, reads results, and returns a synthesized answer with grounded citations. Requires API key.\n\ndeep_search_exa { \"query\": \"what are the leading approaches to multimodal RAG in production systems\" }\n\n\nSupports structured output via outputSchema:\n\ndeep_search_exa {\n  \"query\": \"top 10 aerospace companies by revenue\",\n  \"type\": \"deep\",\n  \"outputSchema\": {\n    \"type\": \"object\",\n    \"required\": [\"companies\"],\n    \"properties\": {\n      \"companies\": {\n        \"type\": \"array\",\n        \"items\": {\n          \"type\": \"object\",\n          \"properties\": {\n            \"name\": { \"type\": \"string\" },\n            \"revenue\": { \"type\": \"string\" },\n            \"hq\": { \"type\": \"string\" }\n          }\n        }\n      }\n    }\n  }\n}\n\nQuery Craft\n\nExa is neural — it matches on meaning, not keywords. Write queries like you'd describe the ideal page to a colleague.\n\nDo: \"blog post about using embeddings for product recommendations at scale\" Don't: \"embeddings product recommendations\"\n\nDo: \"Stripe payments company San Francisco fintech\" Don't: \"Stripe\" (too ambiguous)\n\nUse category when you know the content type — it makes a big difference.\nFor broader coverage, run 2-3 query variations in parallel and deduplicate results.\nFor agentic workflows, use highlights instead of full text — it's 10x more token-efficient while keeping the relevant parts.\nToken Efficiency\nContent mode\tWhen to use\nhighlights\tAgent workflows, factual lookups, multi-step pipelines — most token-efficient\ntext\tDeep analysis, when you need full page context\nsummary\tQuick overviews, structured extraction with JSON schema\n\nSet maxCharacters on any content mode to control output size.\n\nWhen to Reach for Which Tool\nI need to...\tUse\nQuick web lookup\tweb_search_exa\nResearch papers, academic search\tweb_search_advanced_exa + category: \"research paper\"\nCompany intel, competitive analysis\tcompany_research_exa or advanced + category: \"company\"\nFind people, candidates, experts\tpeople_search_exa or advanced + category: \"people\"\nCode examples, API docs\tget_code_context_exa\nRead a specific URL\tcrawling_exa\nFind pages similar to a URL\tweb_search_advanced_exa with URL as query\nRecent news / tweets\tAdvanced + category: \"news\" or \"tweet\" + maxAgeHours\nDetailed research report\tdeep_researcher_start → deep_researcher_check\nQuick answer with citations\tdeep_search_exa\n\nDocs: exa.ai/docs — Dashboard: dashboard.exa.ai — Support: support@exa.ai"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/theishangoswami/web-search-exa",
    "publisherUrl": "https://clawhub.ai/theishangoswami/web-search-exa",
    "owner": "theishangoswami",
    "version": "2.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/web-search-exa",
    "downloadUrl": "https://openagent3.xyz/downloads/web-search-exa",
    "agentUrl": "https://openagent3.xyz/skills/web-search-exa/agent",
    "manifestUrl": "https://openagent3.xyz/skills/web-search-exa/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/web-search-exa/agent.md"
  }
}