{ "schemaVersion": "1.0", "item": { "slug": "browse", "name": "Browserbase", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/pkiv/browse", "canonicalUrl": "https://clawhub.ai/pkiv/browse", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/browse", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browse", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "EXAMPLES.md", "LICENSE.txt", "REFERENCE.md", "SKILL.md" ], "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", "slug": "browse", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-01T02:43:37.272Z", "expiresAt": "2026-05-08T02:43:37.272Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browse", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=browse", "contentDisposition": "attachment; filename=\"browse-2.0.2.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "browse" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/browse" }, "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/browse", "agentPageUrl": "https://openagent3.xyz/skills/browse/agent", "manifestUrl": "https://openagent3.xyz/skills/browse/agent.json", "briefUrl": "https://openagent3.xyz/skills/browse/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 Automation", "body": "Automate browser interactions using the browse CLI with Claude." }, { "title": "Setup check", "body": "Before running any browser commands, verify the CLI is available:\n\nwhich browse || npm install -g @browserbasehq/browse-cli" }, { "title": "Environment Selection (Local vs Remote)", "body": "The CLI automatically selects between local and remote browser environments based on available configuration:" }, { "title": "Local mode (default)", "body": "Uses local Chrome — no API keys needed\nBest for: development, simple pages, trusted sites with no bot protection" }, { "title": "Remote mode (Browserbase)", "body": "Activated when BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID are set\nProvides: anti-bot stealth, automatic CAPTCHA solving, residential proxies, session persistence\nUse remote mode when: the target site has bot detection, CAPTCHAs, IP rate limiting, Cloudflare protection, or requires geo-specific access\nGet credentials at https://browserbase.com/settings" }, { "title": "When to choose which", "body": "Simple browsing (docs, wikis, public APIs): local mode is fine\nProtected sites (login walls, CAPTCHAs, anti-scraping): use remote mode\nIf local mode fails with bot detection or access denied: switch to remote mode" }, { "title": "Commands", "body": "All commands work identically in both modes. The daemon auto-starts on first command." }, { "title": "Navigation", "body": "browse open # Go to URL (aliases: goto)\nbrowse reload # Reload current page\nbrowse back # Go back in history\nbrowse forward # Go forward in history" }, { "title": "Page state (prefer snapshot over screenshot)", "body": "browse snapshot # Get accessibility tree with element refs (fast, structured)\nbrowse screenshot [path] # Take visual screenshot (slow, uses vision tokens)\nbrowse get url # Get current URL\nbrowse get title # Get page title\nbrowse get text # Get text content (use \"body\" for all text)\nbrowse get html # Get HTML content of element\nbrowse get value # Get form field value\n\nUse browse snapshot as your default for understanding page state — it returns the accessibility tree with element refs you can use to interact. Only use browse screenshot when you need visual context (layout, images, debugging)." }, { "title": "Interaction", "body": "browse click # Click element by ref from snapshot (e.g., @0-5)\nbrowse type # Type text into focused element\nbrowse fill # Fill input and press Enter\nbrowse select # Select dropdown option(s)\nbrowse press # Press key (Enter, Tab, Escape, Cmd+A, etc.)\nbrowse drag # Drag from one point to another\nbrowse scroll # Scroll at coordinates\nbrowse highlight # Highlight element on page\nbrowse is visible # Check if element is visible\nbrowse is checked # Check if element is checked\nbrowse wait [arg] # Wait for: load, selector, timeout" }, { "title": "Session management", "body": "browse stop # Stop the browser daemon\nbrowse status # Check daemon status (includes env)\nbrowse env # Show current environment (local or remote)\nbrowse env local # Switch to local Chrome\nbrowse env remote # Switch to Browserbase (requires API keys)\nbrowse pages # List all open tabs\nbrowse tab_switch # Switch to tab by index\nbrowse tab_close [index] # Close tab" }, { "title": "Typical workflow", "body": "browse open — navigate to the page\nbrowse snapshot — read the accessibility tree to understand page structure and get element refs\nbrowse click / browse type / browse fill — interact using refs from snapshot\nbrowse snapshot — confirm the action worked\nRepeat 3-4 as needed\nbrowse stop — close the browser when done" }, { "title": "Quick Example", "body": "browse open https://example.com\nbrowse snapshot # see page structure + element refs\nbrowse click @0-5 # click element with ref 0-5\nbrowse get title\nbrowse stop" }, { "title": "Mode Comparison", "body": "FeatureLocalBrowserbaseSpeedFasterSlightly slowerSetupChrome requiredAPI key requiredStealth modeNoYes (custom Chromium, anti-bot fingerprinting)CAPTCHA solvingNoYes (automatic reCAPTCHA/hCaptcha)Residential proxiesNoYes (201 countries, geo-targeting)Session persistenceNoYes (cookies/auth persist across sessions)Best forDevelopment/simple pagesProtected sites, bot detection, production scraping" }, { "title": "Best Practices", "body": "Always browse open first before interacting\nUse browse snapshot to check page state — it's fast and gives you element refs\nOnly screenshot when visual context is needed (layout checks, images, debugging)\nUse refs from snapshot to click/interact — e.g., browse click @0-5\nbrowse stop when done to clean up the browser session" }, { "title": "Troubleshooting", "body": "\"No active page\": Run browse stop, then check browse status. If it still says running, kill the zombie daemon with pkill -f \"browse.*daemon\", then retry browse open\nChrome not found: Install Chrome or use browse env remote\nAction fails: Run browse snapshot to see available elements and their refs\nBrowserbase fails: Verify API key and project ID are set" }, { "title": "Switching to Remote Mode", "body": "Switch to remote when you detect: CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile), bot detection pages (\"Checking your browser...\"), HTTP 403/429, empty pages on sites that should have content, or the user asks for it.\n\nDon't switch for simple sites (docs, wikis, public APIs, localhost).\n\nbrowse env remote # switch to Browserbase\nbrowse env local # switch back to local Chrome\n\nThe switch is sticky until you run browse stop or switch again.\n\nFor detailed examples, see EXAMPLES.md.\nFor API reference, see REFERENCE.md." } ], "body": "Browser Automation\n\nAutomate browser interactions using the browse CLI with Claude.\n\nSetup check\n\nBefore running any browser commands, verify the CLI is available:\n\nwhich browse || npm install -g @browserbasehq/browse-cli\n\nEnvironment Selection (Local vs Remote)\n\nThe CLI automatically selects between local and remote browser environments based on available configuration:\n\nLocal mode (default)\nUses local Chrome — no API keys needed\nBest for: development, simple pages, trusted sites with no bot protection\nRemote mode (Browserbase)\nActivated when BROWSERBASE_API_KEY and BROWSERBASE_PROJECT_ID are set\nProvides: anti-bot stealth, automatic CAPTCHA solving, residential proxies, session persistence\nUse remote mode when: the target site has bot detection, CAPTCHAs, IP rate limiting, Cloudflare protection, or requires geo-specific access\nGet credentials at https://browserbase.com/settings\nWhen to choose which\nSimple browsing (docs, wikis, public APIs): local mode is fine\nProtected sites (login walls, CAPTCHAs, anti-scraping): use remote mode\nIf local mode fails with bot detection or access denied: switch to remote mode\nCommands\n\nAll commands work identically in both modes. The daemon auto-starts on first command.\n\nNavigation\nbrowse open # Go to URL (aliases: goto)\nbrowse reload # Reload current page\nbrowse back # Go back in history\nbrowse forward # Go forward in history\n\nPage state (prefer snapshot over screenshot)\nbrowse snapshot # Get accessibility tree with element refs (fast, structured)\nbrowse screenshot [path] # Take visual screenshot (slow, uses vision tokens)\nbrowse get url # Get current URL\nbrowse get title # Get page title\nbrowse get text # Get text content (use \"body\" for all text)\nbrowse get html # Get HTML content of element\nbrowse get value # Get form field value\n\n\nUse browse snapshot as your default for understanding page state — it returns the accessibility tree with element refs you can use to interact. Only use browse screenshot when you need visual context (layout, images, debugging).\n\nInteraction\nbrowse click # Click element by ref from snapshot (e.g., @0-5)\nbrowse type # Type text into focused element\nbrowse fill # Fill input and press Enter\nbrowse select # Select dropdown option(s)\nbrowse press # Press key (Enter, Tab, Escape, Cmd+A, etc.)\nbrowse drag # Drag from one point to another\nbrowse scroll # Scroll at coordinates\nbrowse highlight # Highlight element on page\nbrowse is visible # Check if element is visible\nbrowse is checked # Check if element is checked\nbrowse wait [arg] # Wait for: load, selector, timeout\n\nSession management\nbrowse stop # Stop the browser daemon\nbrowse status # Check daemon status (includes env)\nbrowse env # Show current environment (local or remote)\nbrowse env local # Switch to local Chrome\nbrowse env remote # Switch to Browserbase (requires API keys)\nbrowse pages # List all open tabs\nbrowse tab_switch # Switch to tab by index\nbrowse tab_close [index] # Close tab\n\nTypical workflow\nbrowse open — navigate to the page\nbrowse snapshot — read the accessibility tree to understand page structure and get element refs\nbrowse click / browse type / browse fill — interact using refs from snapshot\nbrowse snapshot — confirm the action worked\nRepeat 3-4 as needed\nbrowse stop — close the browser when done\nQuick Example\nbrowse open https://example.com\nbrowse snapshot # see page structure + element refs\nbrowse click @0-5 # click element with ref 0-5\nbrowse get title\nbrowse stop\n\nMode Comparison\nFeature\tLocal\tBrowserbase\nSpeed\tFaster\tSlightly slower\nSetup\tChrome required\tAPI key required\nStealth mode\tNo\tYes (custom Chromium, anti-bot fingerprinting)\nCAPTCHA solving\tNo\tYes (automatic reCAPTCHA/hCaptcha)\nResidential proxies\tNo\tYes (201 countries, geo-targeting)\nSession persistence\tNo\tYes (cookies/auth persist across sessions)\nBest for\tDevelopment/simple pages\tProtected sites, bot detection, production scraping\nBest Practices\nAlways browse open first before interacting\nUse browse snapshot to check page state — it's fast and gives you element refs\nOnly screenshot when visual context is needed (layout checks, images, debugging)\nUse refs from snapshot to click/interact — e.g., browse click @0-5\nbrowse stop when done to clean up the browser session\nTroubleshooting\n\"No active page\": Run browse stop, then check browse status. If it still says running, kill the zombie daemon with pkill -f \"browse.*daemon\", then retry browse open\nChrome not found: Install Chrome or use browse env remote\nAction fails: Run browse snapshot to see available elements and their refs\nBrowserbase fails: Verify API key and project ID are set\nSwitching to Remote Mode\n\nSwitch to remote when you detect: CAPTCHAs (reCAPTCHA, hCaptcha, Turnstile), bot detection pages (\"Checking your browser...\"), HTTP 403/429, empty pages on sites that should have content, or the user asks for it.\n\nDon't switch for simple sites (docs, wikis, public APIs, localhost).\n\nbrowse env remote # switch to Browserbase\nbrowse env local # switch back to local Chrome\n\n\nThe switch is sticky until you run browse stop or switch again.\n\nFor detailed examples, see EXAMPLES.md. For API reference, see REFERENCE.md." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/pkiv/browse", "publisherUrl": "https://clawhub.ai/pkiv/browse", "owner": "pkiv", "version": "2.0.2", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/browse", "downloadUrl": "https://openagent3.xyz/downloads/browse", "agentUrl": "https://openagent3.xyz/skills/browse/agent", "manifestUrl": "https://openagent3.xyz/skills/browse/agent.json", "briefUrl": "https://openagent3.xyz/skills/browse/agent.md" } }