{
  "schemaVersion": "1.0",
  "item": {
    "slug": "openclaw-agent-browser",
    "name": "Agent Browser",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/bodietron/openclaw-agent-browser",
    "canonicalUrl": "https://clawhub.ai/bodietron/openclaw-agent-browser",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/openclaw-agent-browser",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=openclaw-agent-browser",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/commands.md",
      "scripts/setup.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/openclaw-agent-browser"
    },
    "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/openclaw-agent-browser",
    "agentPageUrl": "https://openagent3.xyz/skills/openclaw-agent-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-agent-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-agent-browser/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": "Setup",
        "body": "Run scripts/setup.sh to install agent-browser and Chromium. Requires Node.js."
      },
      {
        "title": "Core Workflow",
        "body": "Every browser automation follows this pattern:\n\nNavigate: agent-browser open <url>\nSnapshot: agent-browser snapshot -i (get element refs like @e1, @e2)\nInteract: Use refs to click, fill, select\nRe-snapshot: After navigation or DOM changes, get fresh refs\n\nagent-browser open https://example.com/form\nagent-browser snapshot -i\n# Output: @e1 [input type=\"email\"], @e2 [input type=\"password\"], @e3 [button] \"Submit\"\n\nagent-browser fill @e1 \"user@example.com\"\nagent-browser fill @e2 \"password123\"\nagent-browser click @e3\nagent-browser wait --load networkidle\nagent-browser snapshot -i  # Check result"
      },
      {
        "title": "Command Chaining",
        "body": "Chain with && when you don't need intermediate output:\n\nagent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i\n\nRun separately when you need to parse output first (e.g., snapshot to discover refs)."
      },
      {
        "title": "Essential Commands",
        "body": "# Navigate\nagent-browser open <url>\nagent-browser close\n\n# See the page (always do this first)\nagent-browser snapshot -i              # Interactive elements with refs\nagent-browser snapshot -i -C           # Include onclick divs\n\n# Interact using @refs\nagent-browser click @e1\nagent-browser fill @e2 \"text\"\nagent-browser select @e1 \"option\"\nagent-browser press Enter\nagent-browser scroll down 500\n\n# Get info\nagent-browser get text @e1\nagent-browser get url\nagent-browser get title\n\n# Wait\nagent-browser wait @e1                 # For element\nagent-browser wait --load networkidle  # For network idle\n\n# Capture\nagent-browser screenshot page.png\nagent-browser screenshot --full        # Full page\nagent-browser pdf output.pdf\n\nFor the full command reference, see references/commands.md."
      },
      {
        "title": "Ref Lifecycle (Important)",
        "body": "Refs (@e1, @e2) are invalidated when the page changes. Always re-snapshot after:\n\nClicking links/buttons that navigate\nForm submissions\nDynamic content loading (dropdowns, modals)"
      },
      {
        "title": "Form Submission",
        "body": "agent-browser open https://example.com/signup\nagent-browser snapshot -i\nagent-browser fill @e1 \"Jane Doe\"\nagent-browser fill @e2 \"jane@example.com\"\nagent-browser select @e3 \"California\"\nagent-browser click @e5\nagent-browser wait --load networkidle"
      },
      {
        "title": "Login with State Persistence",
        "body": "agent-browser open https://app.example.com/login\nagent-browser snapshot -i\nagent-browser fill @e1 \"$USERNAME\" && agent-browser fill @e2 \"$PASSWORD\"\nagent-browser click @e3\nagent-browser wait --url \"**/dashboard\"\nagent-browser state save auth.json\n\n# Reuse later\nagent-browser state load auth.json\nagent-browser open https://app.example.com/dashboard"
      },
      {
        "title": "Data Extraction",
        "body": "agent-browser open https://example.com/products\nagent-browser snapshot -i\nagent-browser get text @e5\nagent-browser get text body > page.txt"
      },
      {
        "title": "Screenshot & Diff",
        "body": "agent-browser screenshot baseline.png\n# ... changes happen ...\nagent-browser diff screenshot --baseline baseline.png"
      },
      {
        "title": "Parallel Sessions",
        "body": "agent-browser --session site1 open https://site-a.com\nagent-browser --session site2 open https://site-b.com\nagent-browser session list"
      },
      {
        "title": "Security (Optional)",
        "body": "export AGENT_BROWSER_CONTENT_BOUNDARIES=1          # Wrap output for AI safety\nexport AGENT_BROWSER_ALLOWED_DOMAINS=\"example.com\"  # Domain allowlist\nexport AGENT_BROWSER_MAX_OUTPUT=50000               # Prevent context flooding"
      },
      {
        "title": "Cleanup",
        "body": "Always close sessions when done: agent-browser close"
      }
    ],
    "body": "Browser Automation with agent-browser\nSetup\n\nRun scripts/setup.sh to install agent-browser and Chromium. Requires Node.js.\n\nCore Workflow\n\nEvery browser automation follows this pattern:\n\nNavigate: agent-browser open <url>\nSnapshot: agent-browser snapshot -i (get element refs like @e1, @e2)\nInteract: Use refs to click, fill, select\nRe-snapshot: After navigation or DOM changes, get fresh refs\nagent-browser open https://example.com/form\nagent-browser snapshot -i\n# Output: @e1 [input type=\"email\"], @e2 [input type=\"password\"], @e3 [button] \"Submit\"\n\nagent-browser fill @e1 \"user@example.com\"\nagent-browser fill @e2 \"password123\"\nagent-browser click @e3\nagent-browser wait --load networkidle\nagent-browser snapshot -i  # Check result\n\nCommand Chaining\n\nChain with && when you don't need intermediate output:\n\nagent-browser open https://example.com && agent-browser wait --load networkidle && agent-browser snapshot -i\n\n\nRun separately when you need to parse output first (e.g., snapshot to discover refs).\n\nEssential Commands\n# Navigate\nagent-browser open <url>\nagent-browser close\n\n# See the page (always do this first)\nagent-browser snapshot -i              # Interactive elements with refs\nagent-browser snapshot -i -C           # Include onclick divs\n\n# Interact using @refs\nagent-browser click @e1\nagent-browser fill @e2 \"text\"\nagent-browser select @e1 \"option\"\nagent-browser press Enter\nagent-browser scroll down 500\n\n# Get info\nagent-browser get text @e1\nagent-browser get url\nagent-browser get title\n\n# Wait\nagent-browser wait @e1                 # For element\nagent-browser wait --load networkidle  # For network idle\n\n# Capture\nagent-browser screenshot page.png\nagent-browser screenshot --full        # Full page\nagent-browser pdf output.pdf\n\n\nFor the full command reference, see references/commands.md.\n\nRef Lifecycle (Important)\n\nRefs (@e1, @e2) are invalidated when the page changes. Always re-snapshot after:\n\nClicking links/buttons that navigate\nForm submissions\nDynamic content loading (dropdowns, modals)\nCommon Patterns\nForm Submission\nagent-browser open https://example.com/signup\nagent-browser snapshot -i\nagent-browser fill @e1 \"Jane Doe\"\nagent-browser fill @e2 \"jane@example.com\"\nagent-browser select @e3 \"California\"\nagent-browser click @e5\nagent-browser wait --load networkidle\n\nLogin with State Persistence\nagent-browser open https://app.example.com/login\nagent-browser snapshot -i\nagent-browser fill @e1 \"$USERNAME\" && agent-browser fill @e2 \"$PASSWORD\"\nagent-browser click @e3\nagent-browser wait --url \"**/dashboard\"\nagent-browser state save auth.json\n\n# Reuse later\nagent-browser state load auth.json\nagent-browser open https://app.example.com/dashboard\n\nData Extraction\nagent-browser open https://example.com/products\nagent-browser snapshot -i\nagent-browser get text @e5\nagent-browser get text body > page.txt\n\nScreenshot & Diff\nagent-browser screenshot baseline.png\n# ... changes happen ...\nagent-browser diff screenshot --baseline baseline.png\n\nParallel Sessions\nagent-browser --session site1 open https://site-a.com\nagent-browser --session site2 open https://site-b.com\nagent-browser session list\n\nSecurity (Optional)\nexport AGENT_BROWSER_CONTENT_BOUNDARIES=1          # Wrap output for AI safety\nexport AGENT_BROWSER_ALLOWED_DOMAINS=\"example.com\"  # Domain allowlist\nexport AGENT_BROWSER_MAX_OUTPUT=50000               # Prevent context flooding\n\nCleanup\n\nAlways close sessions when done: agent-browser close"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/bodietron/openclaw-agent-browser",
    "publisherUrl": "https://clawhub.ai/bodietron/openclaw-agent-browser",
    "owner": "bodietron",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/openclaw-agent-browser",
    "downloadUrl": "https://openagent3.xyz/downloads/openclaw-agent-browser",
    "agentUrl": "https://openagent3.xyz/skills/openclaw-agent-browser/agent",
    "manifestUrl": "https://openagent3.xyz/skills/openclaw-agent-browser/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/openclaw-agent-browser/agent.md"
  }
}