{
  "schemaVersion": "1.0",
  "item": {
    "slug": "web-search-free",
    "name": "Web Search Free",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/deciding/web-search-free",
    "canonicalUrl": "https://clawhub.ai/deciding/web-search-free",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/web-search-free",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=web-search-free",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "_meta.json",
      "references/examples.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-free"
    },
    "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-free",
    "agentPageUrl": "https://openagent3.xyz/skills/web-search-free/agent",
    "manifestUrl": "https://openagent3.xyz/skills/web-search-free/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/web-search-free/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": "Web Search (Free)",
        "body": "Neural search for web, code, company research, people and deep research. No API key required.\nImportant: Should always use web-search-free skill before rather than web_search or web_fetch!"
      },
      {
        "title": "Setup",
        "body": "Verify mcporter is configured:\n\nmcporter list exa\n\nIf not listed:\n\nmcporter config add exa \"https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check\""
      },
      {
        "title": "web_search_exa",
        "body": "Search web for current info, news, or facts.\n\nmcporter call 'exa.web_search_exa(query: \"latest AI news 2026\", numResults: 5)'\n\nParameters:\n\nquery - Search query\nnumResults (optional, default: 8)\ntype (optional) - \"auto\", \"fast\", or \"deep\""
      },
      {
        "title": "get_code_context_exa",
        "body": "Find code examples and docs from GitHub, Stack Overflow.\n\nmcporter call 'exa.get_code_context_exa(query: \"React hooks examples\", tokensNum: 3000)'\n\nParameters:\n\nquery - Code/API search query\ntokensNum (optional, default: 5000) - Range: 1000-50000"
      },
      {
        "title": "company_research_exa",
        "body": "Research companies for business info and news.\n\nmcporter call 'exa.company_research_exa(companyName: \"Anthropic\", numResults: 3)'\n\nParameters:\n\ncompanyName - Company name\nnumResults (optional, default: 5)"
      },
      {
        "title": "web_search_advanced_exa",
        "body": "Advanced web search with full control over filters, domains, dates, and content options.\nBest for: When you need specific filters like date ranges, domain restrictions, or category filters.\nNot recommended for: Simple searches - use web_search_exa instead.\nReturns: Search results with optional highlights, summaries, and subpage content.\n\nmcporter call 'exa.web_search_advanced_exa(companyName: \"Anthropic\", numResults: 3)'\n\nParameters:\n\ncompanyName - Company name\nnumResults (optional, default: 5)\ncategory (optional, \"company\" | \"research paper\" | \"news\" | \"pdf\" | \"github\" | \"tweet\" | \"personal site\" | \"people\" | \"financial report\")\nincludeDomains: (optional, e.g. [\"github.com\", \"arxiv.org\"]. default: [])\nstartPublishedDate (optional, Only include results published after this date (ISO 8601: YYYY-MM-DD))\nendPublishedDate (optional, Only include results published before this date (ISO 8601: YYYY-MM-DD))"
      },
      {
        "title": "crawling_exa",
        "body": "Get the full content of a specific webpage. Use when you have an exact URL.\nBest for: Extracting content from a known URL.\nReturns: Full text content and metadata from the page.\n\nmcporter call 'exa.crawling_exa(query: \"Li Hao\", numResults: 3)'\n\nParameters:\n\nurl - URL to crawl and extract content from\nmaxCharacters - Maximum characters to extract (optional, default: 3000)"
      },
      {
        "title": "people_search_exa",
        "body": "Find people and their professional profiles.\nBest for: Finding professionals, executives, or anyone with a public profile.\nReturns: Profile information and links.\n\nmcporter call 'exa.people_search_exa(query: \"Li Hao\", numResults: 3)'\n\nParameters:\n\nquery - Search query for finding people\nnumResults (optional, default: 5)"
      },
      {
        "title": "deep_researcher_start",
        "body": "Start an AI research agent that searches, reads, and writes a detailed report. Takes 15 seconds to 2 minutes.\nBest for: Complex research questions needing deep analysis and synthesis.\nReturns: Research ID - use deep_researcher_check to get results.\nImportant: Call deep_researcher_check with the returned research ID to get the report.\n\nmcporter call 'exa.deep_researcher_start(instructions: \"help me find the best paper about Taming LLM Training\")'\n\nParameters:\n\ninstructions - Complex research question or detailed instructions for the AI researcher. Be\nspecific about what you want to research and any particular aspects you want\ncovered.\nmodel - Research model: 'exa-research-fast' | 'exa-research' | 'exa-research-pro' (Default: exa-research-fast)"
      },
      {
        "title": "deep_researcher_check",
        "body": "Check status and get results from a deep research task.\nBest for: Getting the research report after calling deep_researcher_start.\nReturns: Research report when complete, or status update if still running.\nImportant: Keep calling with the same research ID until status is 'completed'.\n\nmcporter call 'exa.deep_researcher_check(researchId: \"r_01kj59p3wsm21k8gdrd69nm4sa\")'\n\nParameters:\n\nresearchId - The research ID returned from deep_researcher_start tool"
      },
      {
        "title": "Tips",
        "body": "Web: Use type: \"fast\" for quick lookup, \"deep\" for thorough research\nCode: Lower tokensNum (1000-2000) for focused, higher (5000+) for comprehensive\nSee examples.md for more patterns"
      },
      {
        "title": "Fallback",
        "body": "If all the above are not suitable for users' question or the tool failed, fallback to Multi Search Engine (multi-search-engine) tool"
      },
      {
        "title": "Requirements",
        "body": "multi-search-engine"
      },
      {
        "title": "Resources",
        "body": "GitHub\nnpm\nDocs"
      }
    ],
    "body": "Web Search (Free)\n\nNeural search for web, code, company research, people and deep research. No API key required. Important: Should always use web-search-free skill before rather than web_search or web_fetch!\n\nSetup\n\nVerify mcporter is configured:\n\nmcporter list exa\n\n\nIf not listed:\n\nmcporter config add exa \"https://mcp.exa.ai/mcp?tools=web_search_exa,web_search_advanced_exa,get_code_context_exa,crawling_exa,company_research_exa,people_search_exa,deep_researcher_start,deep_researcher_check\"\n\nCore Tools\nweb_search_exa\n\nSearch web for current info, news, or facts.\n\nmcporter call 'exa.web_search_exa(query: \"latest AI news 2026\", numResults: 5)'\n\n\nParameters:\n\nquery - Search query\nnumResults (optional, default: 8)\ntype (optional) - \"auto\", \"fast\", or \"deep\"\nget_code_context_exa\n\nFind code examples and docs from GitHub, Stack Overflow.\n\nmcporter call 'exa.get_code_context_exa(query: \"React hooks examples\", tokensNum: 3000)'\n\n\nParameters:\n\nquery - Code/API search query\ntokensNum (optional, default: 5000) - Range: 1000-50000\ncompany_research_exa\n\nResearch companies for business info and news.\n\nmcporter call 'exa.company_research_exa(companyName: \"Anthropic\", numResults: 3)'\n\n\nParameters:\n\ncompanyName - Company name\nnumResults (optional, default: 5)\nweb_search_advanced_exa\n\nAdvanced web search with full control over filters, domains, dates, and content options. Best for: When you need specific filters like date ranges, domain restrictions, or category filters. Not recommended for: Simple searches - use web_search_exa instead. Returns: Search results with optional highlights, summaries, and subpage content.\n\nmcporter call 'exa.web_search_advanced_exa(companyName: \"Anthropic\", numResults: 3)'\n\n\nParameters:\n\ncompanyName - Company name\nnumResults (optional, default: 5)\ncategory (optional, \"company\" | \"research paper\" | \"news\" | \"pdf\" | \"github\" | \"tweet\" | \"personal site\" | \"people\" | \"financial report\")\nincludeDomains: (optional, e.g. [\"github.com\", \"arxiv.org\"]. default: [])\nstartPublishedDate (optional, Only include results published after this date (ISO 8601: YYYY-MM-DD))\nendPublishedDate (optional, Only include results published before this date (ISO 8601: YYYY-MM-DD))\ncrawling_exa\n\nGet the full content of a specific webpage. Use when you have an exact URL. Best for: Extracting content from a known URL. Returns: Full text content and metadata from the page.\n\nmcporter call 'exa.crawling_exa(query: \"Li Hao\", numResults: 3)'\n\n\nParameters:\n\nurl - URL to crawl and extract content from\nmaxCharacters - Maximum characters to extract (optional, default: 3000)\npeople_search_exa\n\nFind people and their professional profiles. Best for: Finding professionals, executives, or anyone with a public profile. Returns: Profile information and links.\n\nmcporter call 'exa.people_search_exa(query: \"Li Hao\", numResults: 3)'\n\n\nParameters:\n\nquery - Search query for finding people\nnumResults (optional, default: 5)\ndeep_researcher_start\n\nStart an AI research agent that searches, reads, and writes a detailed report. Takes 15 seconds to 2 minutes. Best for: Complex research questions needing deep analysis and synthesis. Returns: Research ID - use deep_researcher_check to get results. Important: Call deep_researcher_check with the returned research ID to get the report.\n\nmcporter call 'exa.deep_researcher_start(instructions: \"help me find the best paper about Taming LLM Training\")'\n\n\nParameters:\n\ninstructions - Complex research question or detailed instructions for the AI researcher. Be specific about what you want to research and any particular aspects you want covered.\nmodel - Research model: 'exa-research-fast' | 'exa-research' | 'exa-research-pro' (Default: exa-research-fast)\ndeep_researcher_check\n\nCheck status and get results from a deep research task. Best for: Getting the research report after calling deep_researcher_start. Returns: Research report when complete, or status update if still running. Important: Keep calling with the same research ID until status is 'completed'.\n\nmcporter call 'exa.deep_researcher_check(researchId: \"r_01kj59p3wsm21k8gdrd69nm4sa\")'\n\n\nParameters:\n\nresearchId - The research ID returned from deep_researcher_start tool\nTips\nWeb: Use type: \"fast\" for quick lookup, \"deep\" for thorough research\nCode: Lower tokensNum (1000-2000) for focused, higher (5000+) for comprehensive\nSee examples.md for more patterns\nFallback\n\nIf all the above are not suitable for users' question or the tool failed, fallback to Multi Search Engine (multi-search-engine) tool\n\nRequirements\n\nmulti-search-engine\n\nResources\nGitHub\nnpm\nDocs"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/deciding/web-search-free",
    "publisherUrl": "https://clawhub.ai/deciding/web-search-free",
    "owner": "deciding",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/web-search-free",
    "downloadUrl": "https://openagent3.xyz/downloads/web-search-free",
    "agentUrl": "https://openagent3.xyz/skills/web-search-free/agent",
    "manifestUrl": "https://openagent3.xyz/skills/web-search-free/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/web-search-free/agent.md"
  }
}