{
  "schemaVersion": "1.0",
  "item": {
    "slug": "browser-use-api",
    "name": "Browser Use API",
    "source": "tencent",
    "type": "skill",
    "category": "效率提升",
    "sourceUrl": "https://clawhub.ai/jfrux/browser-use-api",
    "canonicalUrl": "https://clawhub.ai/jfrux/browser-use-api",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/browser-use-api",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browser-use-api",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "scripts/browser-use.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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/browser-use-api"
    },
    "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/browser-use-api",
    "agentPageUrl": "https://openagent3.xyz/skills/browser-use-api/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-use-api/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-use-api/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": "Browser Use",
        "body": "Cloud-based AI browser automation. Send a task in plain English, get structured results."
      },
      {
        "title": "Quick Start",
        "body": "# Submit task\ncurl -s -X POST https://api.browser-use.com/api/v2/tasks \\\n  -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"task\": \"Go to example.com and extract the main heading\"}'\n\n# Poll for result (replace TASK_ID)\ncurl -s \"https://api.browser-use.com/api/v2/tasks/TASK_ID\" \\\n  -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\""
      },
      {
        "title": "Helper Script",
        "body": "Use scripts/browser-use.sh for simpler execution:\n\n# Run task and wait for result\n./scripts/browser-use.sh \"Go to hacker news and get the top 3 stories\"\n\n# Just submit (don't wait)\n./scripts/browser-use.sh --no-wait \"Search Google for AI news\""
      },
      {
        "title": "Create Task",
        "body": "POST https://api.browser-use.com/api/v2/tasks\n\nBody:\n\n{\n  \"task\": \"Plain English description of what to do\",\n  \"llm\": \"gemini-3-flash-preview\"  // optional, default is fast model\n}\n\nResponse:\n\n{\n  \"id\": \"task-uuid\",\n  \"sessionId\": \"session-uuid\"\n}"
      },
      {
        "title": "Get Task Status",
        "body": "GET https://api.browser-use.com/api/v2/tasks/{taskId}\n\nResponse fields:\n\nstatus: pending | started | finished | failed\noutput: Result text when finished\nsteps: Array of actions taken (with screenshots)\ncost: Cost in dollars (e.g., \"0.02\")\nisSuccess: Boolean result"
      },
      {
        "title": "Stop Task",
        "body": "POST https://api.browser-use.com/api/v2/tasks/{taskId}/stop"
      },
      {
        "title": "Pricing",
        "body": "~$0.01-0.05 per task depending on complexity. Check balance:\n\ncurl -s https://api.browser-use.com/api/v2/credits \\\n  -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\""
      },
      {
        "title": "When to Use",
        "body": "Complex multi-step web workflows\nSites that block simple scraping\nForm filling and submissions\nWhen you need screenshots of steps\nWhen local browser control isn't available"
      },
      {
        "title": "When NOT to Use",
        "body": "Simple page fetches (use web_fetch instead)\nWhen you have local browser access (use browser tool)\nRapid/high-volume scraping (use Code Use or local scraping)"
      }
    ],
    "body": "Browser Use\n\nCloud-based AI browser automation. Send a task in plain English, get structured results.\n\nQuick Start\n# Submit task\ncurl -s -X POST https://api.browser-use.com/api/v2/tasks \\\n  -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\"task\": \"Go to example.com and extract the main heading\"}'\n\n# Poll for result (replace TASK_ID)\ncurl -s \"https://api.browser-use.com/api/v2/tasks/TASK_ID\" \\\n  -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\"\n\nHelper Script\n\nUse scripts/browser-use.sh for simpler execution:\n\n# Run task and wait for result\n./scripts/browser-use.sh \"Go to hacker news and get the top 3 stories\"\n\n# Just submit (don't wait)\n./scripts/browser-use.sh --no-wait \"Search Google for AI news\"\n\nAPI Reference\nCreate Task\nPOST https://api.browser-use.com/api/v2/tasks\n\n\nBody:\n\n{\n  \"task\": \"Plain English description of what to do\",\n  \"llm\": \"gemini-3-flash-preview\"  // optional, default is fast model\n}\n\n\nResponse:\n\n{\n  \"id\": \"task-uuid\",\n  \"sessionId\": \"session-uuid\"\n}\n\nGet Task Status\nGET https://api.browser-use.com/api/v2/tasks/{taskId}\n\n\nResponse fields:\n\nstatus: pending | started | finished | failed\noutput: Result text when finished\nsteps: Array of actions taken (with screenshots)\ncost: Cost in dollars (e.g., \"0.02\")\nisSuccess: Boolean result\nStop Task\nPOST https://api.browser-use.com/api/v2/tasks/{taskId}/stop\n\nPricing\n\n~$0.01-0.05 per task depending on complexity. Check balance:\n\ncurl -s https://api.browser-use.com/api/v2/credits \\\n  -H \"X-Browser-Use-API-Key: $BROWSER_USE_API_KEY\"\n\nWhen to Use\nComplex multi-step web workflows\nSites that block simple scraping\nForm filling and submissions\nWhen you need screenshots of steps\nWhen local browser control isn't available\nWhen NOT to Use\nSimple page fetches (use web_fetch instead)\nWhen you have local browser access (use browser tool)\nRapid/high-volume scraping (use Code Use or local scraping)"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/jfrux/browser-use-api",
    "publisherUrl": "https://clawhub.ai/jfrux/browser-use-api",
    "owner": "jfrux",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/browser-use-api",
    "downloadUrl": "https://openagent3.xyz/downloads/browser-use-api",
    "agentUrl": "https://openagent3.xyz/skills/browser-use-api/agent",
    "manifestUrl": "https://openagent3.xyz/skills/browser-use-api/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/browser-use-api/agent.md"
  }
}