{
  "schemaVersion": "1.0",
  "item": {
    "slug": "gemini-computer-use",
    "name": "Gemini Computer Use",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/am-will/gemini-computer-use",
    "canonicalUrl": "https://clawhub.ai/am-will/gemini-computer-use",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/gemini-computer-use",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=gemini-computer-use",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/google-computer-use.md",
      "scripts/computer_use_agent.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": "2026-04-30T16:55:25.780Z",
      "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/gemini-computer-use"
    },
    "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/gemini-computer-use",
    "agentPageUrl": "https://openagent3.xyz/skills/gemini-computer-use/agent",
    "manifestUrl": "https://openagent3.xyz/skills/gemini-computer-use/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/gemini-computer-use/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": "Quick start",
        "body": "Source the env file and set your API key:\ncp env.example env.sh\n$EDITOR env.sh\nsource env.sh\n\n\n\nCreate a virtual environment and install dependencies:\npython -m venv .venv\nsource .venv/bin/activate\npip install google-genai playwright\nplaywright install chromium\n\n\n\nRun the agent script with a prompt:\npython scripts/computer_use_agent.py \\\n  --prompt \"Find the latest blog post title on example.com\" \\\n  --start-url \"https://example.com\" \\\n  --turn-limit 6"
      },
      {
        "title": "Browser selection",
        "body": "Default: Playwright's bundled Chromium (no env vars required).\nChoose a channel (Chrome/Edge) with COMPUTER_USE_BROWSER_CHANNEL.\nUse a custom Chromium-based executable (e.g., Brave) with COMPUTER_USE_BROWSER_EXECUTABLE.\n\nIf both are set, COMPUTER_USE_BROWSER_EXECUTABLE takes precedence."
      },
      {
        "title": "Core workflow (agent loop)",
        "body": "Capture a screenshot and send the user goal + screenshot to the model.\nParse function_call actions in the response.\nExecute each action in Playwright.\nIf a safety_decision is require_confirmation, prompt the user before executing.\nSend function_response objects containing the latest URL + screenshot.\nRepeat until the model returns only text (no actions) or you hit the turn limit."
      },
      {
        "title": "Operational guidance",
        "body": "Run in a sandboxed browser profile or container.\nUse --exclude to block risky actions you do not want the model to take.\nKeep the viewport at 1440x900 unless you have a reason to change it."
      },
      {
        "title": "Resources",
        "body": "Script: scripts/computer_use_agent.py\nReference notes: references/google-computer-use.md\nEnv template: env.example"
      }
    ],
    "body": "Gemini Computer Use\nQuick start\n\nSource the env file and set your API key:\n\ncp env.example env.sh\n$EDITOR env.sh\nsource env.sh\n\n\nCreate a virtual environment and install dependencies:\n\npython -m venv .venv\nsource .venv/bin/activate\npip install google-genai playwright\nplaywright install chromium\n\n\nRun the agent script with a prompt:\n\npython scripts/computer_use_agent.py \\\n  --prompt \"Find the latest blog post title on example.com\" \\\n  --start-url \"https://example.com\" \\\n  --turn-limit 6\n\nBrowser selection\nDefault: Playwright's bundled Chromium (no env vars required).\nChoose a channel (Chrome/Edge) with COMPUTER_USE_BROWSER_CHANNEL.\nUse a custom Chromium-based executable (e.g., Brave) with COMPUTER_USE_BROWSER_EXECUTABLE.\n\nIf both are set, COMPUTER_USE_BROWSER_EXECUTABLE takes precedence.\n\nCore workflow (agent loop)\nCapture a screenshot and send the user goal + screenshot to the model.\nParse function_call actions in the response.\nExecute each action in Playwright.\nIf a safety_decision is require_confirmation, prompt the user before executing.\nSend function_response objects containing the latest URL + screenshot.\nRepeat until the model returns only text (no actions) or you hit the turn limit.\nOperational guidance\nRun in a sandboxed browser profile or container.\nUse --exclude to block risky actions you do not want the model to take.\nKeep the viewport at 1440x900 unless you have a reason to change it.\nResources\nScript: scripts/computer_use_agent.py\nReference notes: references/google-computer-use.md\nEnv template: env.example"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/am-will/gemini-computer-use",
    "publisherUrl": "https://clawhub.ai/am-will/gemini-computer-use",
    "owner": "am-will",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/gemini-computer-use",
    "downloadUrl": "https://openagent3.xyz/downloads/gemini-computer-use",
    "agentUrl": "https://openagent3.xyz/skills/gemini-computer-use/agent",
    "manifestUrl": "https://openagent3.xyz/skills/gemini-computer-use/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/gemini-computer-use/agent.md"
  }
}