{
  "schemaVersion": "1.0",
  "item": {
    "slug": "exa-full",
    "name": "Exa",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/XieShaocong33Ethan/exa-full",
    "canonicalUrl": "https://clawhub.ai/XieShaocong33Ethan/exa-full",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/exa-full",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=exa-full",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "EXAMPLES.md",
      "scripts/content.sh",
      "scripts/search.sh",
      "scripts/research_poll.sh",
      "scripts/research_get.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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-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/exa-full"
    },
    "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/exa-full",
    "agentPageUrl": "https://openagent3.xyz/skills/exa-full/agent",
    "manifestUrl": "https://openagent3.xyz/skills/exa-full/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/exa-full/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 - Search + Research",
        "body": "Use this skill for web search, code-context search, URL content extraction, and async research workflows."
      },
      {
        "title": "What This Skill Does",
        "body": "Run Exa web search with optional category and domain filters.\nRetrieve full page content (and optional subpage crawling).\nFind code and docs context for programming queries.\nRun async research tasks (one-shot or create/poll workflows).\nSupport optional structured outputs via outputSchema."
      },
      {
        "title": "Setup",
        "body": "Set EXA_API_KEY using one of these methods.\n\nexport EXA_API_KEY=\"your-exa-api-key\"\n\n# .env next to SKILL.md\nEXA_API_KEY=your-exa-api-key\n\nBehavior:\n\nIf EXA_API_KEY is missing in the environment, scripts load only EXA_API_KEY from .env.\nOther .env variables are ignored by the loader."
      },
      {
        "title": "Safety and Data Handling",
        "body": "SCHEMA_FILE content is sent to https://api.exa.ai/research/v1 as outputSchema.\nNever use sensitive local files for SCHEMA_FILE (for example: .env, key/cert files, secrets, internal confidential docs).\nresearch_create.sh blocks obvious sensitive paths/suffixes (for example: .env, .pem, .key, .p12, .pfx, id_rsa)."
      },
      {
        "title": "Search",
        "body": "bash scripts/search.sh \"query\"\n\nMain env vars:\n\nNUM=10 (max 100)\nTYPE=auto (auto, neural, fast, deep, instant)\nCATEGORY= (company, research paper, news, tweet, personal site, financial report, people)\nDOMAINS=domain1.com,domain2.com\nEXCLUDE=domain1.com,domain2.com\nSINCE=YYYY-MM-DD\nUNTIL=YYYY-MM-DD\nLOCATION=NL\n\nConstraints:\n\nEXCLUDE is not supported when CATEGORY=company or CATEGORY=people.\nSINCE and UNTIL are not supported when CATEGORY=company or CATEGORY=people.\nWhen CATEGORY=people, DOMAINS accepts LinkedIn domains only (linkedin.com, www.linkedin.com, *.linkedin.com)."
      },
      {
        "title": "Content Extraction",
        "body": "bash scripts/content.sh \"url1\" \"url2\"\n\nMain env vars:\n\nMAX_CHARACTERS=2000\nHIGHLIGHT_SENTENCES=3\nHIGHLIGHTS_PER_URL=2\nSUBPAGES=10\nSUBPAGE_TARGET=\"docs,reference,api\"\nLIVECRAWL=preferred (preferred, always, fallback)\nLIVECRAWL_TIMEOUT=12000"
      },
      {
        "title": "Code Context Search",
        "body": "bash scripts/code.sh \"query\" [num_results]"
      },
      {
        "title": "Research (One-shot)",
        "body": "bash scripts/research.sh \"instructions\"\n\nMain env vars:\n\nMODEL=exa-research or MODEL=exa-research-pro\nSCHEMA_FILE=path/to/schema.json\nPOLL_INTERVAL=2\nMAX_WAIT_SECONDS=240\nEVENTS=true"
      },
      {
        "title": "Research (Create/Poll)",
        "body": "bash scripts/research_create.sh \"instructions\" | jq\nbash scripts/research_poll.sh \"researchId\" | jq"
      },
      {
        "title": "Choose TYPE for Search",
        "body": "Use this decision order:\n\nUser explicitly asks for realtime or autocomplete -> TYPE=instant.\nTask needs broad coverage or deeper synthesis -> TYPE=deep.\nUser asks for speed/quality balance -> TYPE=fast.\nOtherwise -> TYPE=auto (default).\n\nFallback/escalation:\n\nIf too slow or time-sensitive: deep -> auto -> fast -> instant.\nIf too shallow: instant -> fast -> auto -> deep.\nExplicit user requirement always wins.\n\nRecommended pattern:\n\nTYPE=auto bash scripts/search.sh \"query\""
      },
      {
        "title": "Common Pitfalls",
        "body": "Do not pass sensitive files to SCHEMA_FILE.\nDo not combine CATEGORY=people|company with EXCLUDE, SINCE, or UNTIL.\nPrefer https://docs.exa.ai/ for subpage crawling seeds (more reliable than https://exa.ai/docs/reference/)."
      },
      {
        "title": "More Examples",
        "body": "See EXAMPLES.md for grouped command examples and edge-case workflows."
      }
    ],
    "body": "Exa - Search + Research\n\nUse this skill for web search, code-context search, URL content extraction, and async research workflows.\n\nWhat This Skill Does\nRun Exa web search with optional category and domain filters.\nRetrieve full page content (and optional subpage crawling).\nFind code and docs context for programming queries.\nRun async research tasks (one-shot or create/poll workflows).\nSupport optional structured outputs via outputSchema.\nSetup\n\nSet EXA_API_KEY using one of these methods.\n\nexport EXA_API_KEY=\"your-exa-api-key\"\n\n# .env next to SKILL.md\nEXA_API_KEY=your-exa-api-key\n\n\nBehavior:\n\nIf EXA_API_KEY is missing in the environment, scripts load only EXA_API_KEY from .env.\nOther .env variables are ignored by the loader.\nSafety and Data Handling\nSCHEMA_FILE content is sent to https://api.exa.ai/research/v1 as outputSchema.\nNever use sensitive local files for SCHEMA_FILE (for example: .env, key/cert files, secrets, internal confidential docs).\nresearch_create.sh blocks obvious sensitive paths/suffixes (for example: .env, .pem, .key, .p12, .pfx, id_rsa).\nCommand Quick Reference\nSearch\nbash scripts/search.sh \"query\"\n\n\nMain env vars:\n\nNUM=10 (max 100)\nTYPE=auto (auto, neural, fast, deep, instant)\nCATEGORY= (company, research paper, news, tweet, personal site, financial report, people)\nDOMAINS=domain1.com,domain2.com\nEXCLUDE=domain1.com,domain2.com\nSINCE=YYYY-MM-DD\nUNTIL=YYYY-MM-DD\nLOCATION=NL\n\nConstraints:\n\nEXCLUDE is not supported when CATEGORY=company or CATEGORY=people.\nSINCE and UNTIL are not supported when CATEGORY=company or CATEGORY=people.\nWhen CATEGORY=people, DOMAINS accepts LinkedIn domains only (linkedin.com, www.linkedin.com, *.linkedin.com).\nContent Extraction\nbash scripts/content.sh \"url1\" \"url2\"\n\n\nMain env vars:\n\nMAX_CHARACTERS=2000\nHIGHLIGHT_SENTENCES=3\nHIGHLIGHTS_PER_URL=2\nSUBPAGES=10\nSUBPAGE_TARGET=\"docs,reference,api\"\nLIVECRAWL=preferred (preferred, always, fallback)\nLIVECRAWL_TIMEOUT=12000\nCode Context Search\nbash scripts/code.sh \"query\" [num_results]\n\nResearch (One-shot)\nbash scripts/research.sh \"instructions\"\n\n\nMain env vars:\n\nMODEL=exa-research or MODEL=exa-research-pro\nSCHEMA_FILE=path/to/schema.json\nPOLL_INTERVAL=2\nMAX_WAIT_SECONDS=240\nEVENTS=true\nResearch (Create/Poll)\nbash scripts/research_create.sh \"instructions\" | jq\nbash scripts/research_poll.sh \"researchId\" | jq\n\nAgent Decision Rules\nChoose TYPE for Search\n\nUse this decision order:\n\nUser explicitly asks for realtime or autocomplete -> TYPE=instant.\nTask needs broad coverage or deeper synthesis -> TYPE=deep.\nUser asks for speed/quality balance -> TYPE=fast.\nOtherwise -> TYPE=auto (default).\n\nFallback/escalation:\n\nIf too slow or time-sensitive: deep -> auto -> fast -> instant.\nIf too shallow: instant -> fast -> auto -> deep.\nExplicit user requirement always wins.\n\nRecommended pattern:\n\nTYPE=auto bash scripts/search.sh \"query\"\n\nCommon Pitfalls\nDo not pass sensitive files to SCHEMA_FILE.\nDo not combine CATEGORY=people|company with EXCLUDE, SINCE, or UNTIL.\nPrefer https://docs.exa.ai/ for subpage crawling seeds (more reliable than https://exa.ai/docs/reference/).\nMore Examples\n\nSee EXAMPLES.md for grouped command examples and edge-case workflows."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/XieShaocong33Ethan/exa-full",
    "publisherUrl": "https://clawhub.ai/XieShaocong33Ethan/exa-full",
    "owner": "XieShaocong33Ethan",
    "version": "1.2.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/exa-full",
    "downloadUrl": "https://openagent3.xyz/downloads/exa-full",
    "agentUrl": "https://openagent3.xyz/skills/exa-full/agent",
    "manifestUrl": "https://openagent3.xyz/skills/exa-full/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/exa-full/agent.md"
  }
}