{
  "schemaVersion": "1.0",
  "item": {
    "slug": "web-searcher",
    "name": "Web Searcher",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/kassimisai/web-searcher",
    "canonicalUrl": "https://clawhub.ai/kassimisai/web-searcher",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/web-searcher",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=web-searcher",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/research_plan.py"
    ],
    "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-searcher"
    },
    "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-searcher",
    "agentPageUrl": "https://openagent3.xyz/skills/web-searcher/agent",
    "manifestUrl": "https://openagent3.xyz/skills/web-searcher/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/web-searcher/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": "Workflow",
        "body": "Parse the query — Break the user's request into 2-5 specific search queries that cover different angles of the topic.\n\n\nSearch phase — Execute searches using web_search. Rate limit: max 3 searches, then assess before continuing.\n\n\nDeep dive phase — For promising results, use web_fetch to extract full content. Prioritize:\n\nPrimary sources over aggregators\nRecent content over old (check dates)\nAuthoritative domains over random blogs\n\n\n\nCross-reference — Compare findings across sources. Flag contradictions. Note consensus.\n\n\nSynthesize — Compile findings into a clear, structured response with:\n\nKey findings (bullet points)\nSources cited (URLs)\nConfidence level (high/medium/low per claim)\nGaps identified (what couldn't be found)"
      },
      {
        "title": "Factual queries",
        "body": "Search → verify across 2+ sources → report with citations."
      },
      {
        "title": "Comparison/market research",
        "body": "Search each option separately → fetch detail pages → build comparison table → recommend."
      },
      {
        "title": "People/company research",
        "body": "Search name + context → fetch LinkedIn/company pages → cross-reference news → compile profile."
      },
      {
        "title": "How-to/technical",
        "body": "Search with specific technical terms → fetch documentation/guides → distill steps."
      },
      {
        "title": "Guidelines",
        "body": "Max 10 searches per task to avoid rate limits and token waste.\nMax 5 page fetches — be selective about which URLs to deep-dive.\nAlways include source URLs so the user can verify.\nIf a search returns nothing useful, rephrase and retry once before moving on.\nFor time-sensitive info, use freshness parameter (pd/pw/pm/py).\nPrefer web_fetch with maxChars: 5000 to keep context manageable.\nIf the task is massive, suggest breaking it into sub-tasks or spawning sub-agents."
      },
      {
        "title": "Output Format",
        "body": "## [Topic]\n\n### Key Findings\n- Finding 1 (Source: url)\n- Finding 2 (Source: url)\n\n### Details\n[Expanded analysis]\n\n### Sources\n1. [Title](url) — what was found here\n2. [Title](url) — what was found here\n\n### Confidence & Gaps\n- High confidence: [claims well-supported]\n- Low confidence: [claims with limited sources]\n- Not found: [what couldn't be determined]"
      }
    ],
    "body": "Web Searcher Agent\nWorkflow\n\nParse the query — Break the user's request into 2-5 specific search queries that cover different angles of the topic.\n\nSearch phase — Execute searches using web_search. Rate limit: max 3 searches, then assess before continuing.\n\nDeep dive phase — For promising results, use web_fetch to extract full content. Prioritize:\n\nPrimary sources over aggregators\nRecent content over old (check dates)\nAuthoritative domains over random blogs\n\nCross-reference — Compare findings across sources. Flag contradictions. Note consensus.\n\nSynthesize — Compile findings into a clear, structured response with:\n\nKey findings (bullet points)\nSources cited (URLs)\nConfidence level (high/medium/low per claim)\nGaps identified (what couldn't be found)\nSearch Strategies\nFactual queries\n\nSearch → verify across 2+ sources → report with citations.\n\nComparison/market research\n\nSearch each option separately → fetch detail pages → build comparison table → recommend.\n\nPeople/company research\n\nSearch name + context → fetch LinkedIn/company pages → cross-reference news → compile profile.\n\nHow-to/technical\n\nSearch with specific technical terms → fetch documentation/guides → distill steps.\n\nGuidelines\nMax 10 searches per task to avoid rate limits and token waste.\nMax 5 page fetches — be selective about which URLs to deep-dive.\nAlways include source URLs so the user can verify.\nIf a search returns nothing useful, rephrase and retry once before moving on.\nFor time-sensitive info, use freshness parameter (pd/pw/pm/py).\nPrefer web_fetch with maxChars: 5000 to keep context manageable.\nIf the task is massive, suggest breaking it into sub-tasks or spawning sub-agents.\nOutput Format\n## [Topic]\n\n### Key Findings\n- Finding 1 (Source: url)\n- Finding 2 (Source: url)\n\n### Details\n[Expanded analysis]\n\n### Sources\n1. [Title](url) — what was found here\n2. [Title](url) — what was found here\n\n### Confidence & Gaps\n- High confidence: [claims well-supported]\n- Low confidence: [claims with limited sources]\n- Not found: [what couldn't be determined]"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/kassimisai/web-searcher",
    "publisherUrl": "https://clawhub.ai/kassimisai/web-searcher",
    "owner": "kassimisai",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/web-searcher",
    "downloadUrl": "https://openagent3.xyz/downloads/web-searcher",
    "agentUrl": "https://openagent3.xyz/skills/web-searcher/agent",
    "manifestUrl": "https://openagent3.xyz/skills/web-searcher/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/web-searcher/agent.md"
  }
}