[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-browser-de":3,"guides-for-browserbase-browser":572,"similar-k175dd0cx0atq57d86t68p0ftn86mx3n-de":573},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":241,"isFallback":225,"parentExtension":246,"providers":299,"relations":303,"repo":304,"tags":570,"workflow":571},1778683460321.3813,"k175dd0cx0atq57d86t68p0ftn86mx3n",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Supports remote Browserbase sessions with automatic CAPTCHA solving, anti-bot stealth mode, and residential proxies — ideal for scraping protected websites, bypassing bot detection, and interacting with JavaScript-heavy pages.",{"claudeCode":12},"browserbase/skills","browser","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":223,"workflow":239},1778683633116.1218,"kn77zwdwqca9bahhgtq6ncf82986mpc5","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":203,"promptVersionScoring":204,"purpose":205,"rationale":206,"score":207,"summary":208,"tags":209,"targetMarket":216,"tier":217,"useCases":218},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,140,143,146,149,153,156,159,162,165,168,171,175,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states the skill's purpose: to automate web browser interactions via CLI commands using the browse CLI, and specifies when to use it (browsing, data extraction, form filling) and when not to (simple sites). It names the artifact (web pages) and user intent (browse, extract, fill).",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise and self-contained, clearly summarizing the core capability of browser automation and listing trigger phrases within the first 160 characters.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md body is well-structured and under 500 lines, deferring deeper material like detailed command references to separate files such as REFERENCE.md and EXAMPLES.md.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines the main workflow and links to separate files for detailed command references and examples, demonstrating effective progressive disclosure.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill focuses on direct browser interaction commands rather than deep code review or extensive exploration, so 'context: fork' is not applicable.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","Sufficient end-to-end examples are provided, covering data extraction, form filling, multi-step navigation, and escalation to remote mode, with plausible inputs and outputs.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The documentation addresses failure modes like 'Chrome not found' and 'No active page', providing clear symptoms and recovery steps.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","The skill primarily uses its own CLI tool ('browse') and does not explicitly rely on an external MCP server with a fallback path.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The documentation implicitly supports halting on unexpected states by providing troubleshooting steps for common issues like 'Chrome not found' or 'No active page', guiding the user to resolve them before proceeding.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill operates as a standalone browser automation tool and does not implicitly rely on other skills, with explicit instructions for setting up its own dependencies.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description directly names the problem of automating web browser interactions via CLI commands and for specific use cases like scraping protected websites.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill offers significant value over basic prompting by providing a dedicated CLI tool for complex browser automation, including advanced features like remote sessions with CAPTCHA solving and stealth mode.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The extension is production-ready, with clear setup instructions, support for both local and remote browser sessions, and coverage for the complete lifecycle of browser interaction tasks.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill focuses solely on browser automation via the 'browse' CLI and does not extend into unrelated domains.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The displayed description is accurate, concise, and accurately reflects the capabilities of the browse CLI tool, including its remote session features.",{"category":22,"check":77,"severity":24,"summary":78},"Scoped tools","The skill exposes a set of narrow, verb-noun specialized commands for browser interaction (e.g., 'open', 'click', 'get text') rather than a single generalist execution tool.",{"category":30,"check":80,"severity":24,"summary":81},"Configuration & parameter reference","All parameters and environment variables for the 'browse' CLI are documented in the REFERENCE.md file, including their purpose and usage.",{"category":70,"check":83,"severity":24,"summary":84},"Tool naming","All exposed tool names (e.g., 'open', 'snapshot', 'click', 'fill') are descriptive, verb-noun specific, and within the declared domain of browser automation.",{"category":70,"check":86,"severity":24,"summary":87},"Minimal I/O surface","Tool parameters are specific (e.g., URL, selector, ref), and outputs are structured (e.g., accessibility tree, text, JSON), requesting only necessary data and returning promised payloads.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The extension is distributed under the MIT license, which is a permissive open-source license, and is clearly stated in the LICENSE.txt file and SKILL.md.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The repository shows recent commits, with the last push date being 2026-05-13, indicating active maintenance.",{"category":93,"check":97,"severity":24,"summary":98},"Dependency Management","The skill requires the '@browserbasehq/browse-cli' package, which is a standard Node.js package. The setup instructions in README.md and SKILL.md guide users on installation via npm.",{"category":100,"check":101,"severity":24,"summary":102},"Security","Secret Management","The extension handles secrets (BROWSERBASE_API_KEY) via environment variables, and the documentation clearly states this without echoing resolved secrets to stdout or debug logs.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The skill's interaction with web pages is through a structured CLI tool ('browse') which handles user input as commands and data, mitigating risks of injection through untrusted content.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill bundles the 'browse' CLI and relies on npm for dependency management. It does not fetch remote scripts or markdown at runtime for execution.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The 'browse' CLI operates within its own isolated browser instances (local or Browserbase remote sessions), ensuring that operations do not affect the user's filesystem or other project folders outside of its intended scope.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","There are no indications of detached-process spawns or retry loops around denied tool calls within the 'browse' CLI's operation.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill's outbound calls are primarily to Browserbase for remote sessions, which is documented. Sensitive data like API keys are handled via environment variables and not submitted by default.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled documentation and scripts appear to be free of hidden steering tricks, control characters, or invisible Unicode sequences.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The skill's functionality is provided by the 'browse' CLI, which is installed via npm and is not obfuscated. No runtime code fetching or eval is used.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","The skill does not make assumptions about the user's project file structure beyond requiring the 'browse' CLI to be installed. It operates on URLs provided by the user.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","The repository has 2 open issues and 0 closed issues in the last 90 days, indicating active but potentially new engagement.",{"category":133,"check":134,"severity":24,"summary":135},"Versioning","Release Management","The SKILL.md frontmatter includes a license and installation instructions, and the README references the 'browserbase/skills' marketplace. While a specific version number isn't explicitly called out for the skill itself, the underlying CLI is managed via npm, implying versioning.",{"category":137,"check":138,"severity":24,"summary":139},"Execution","Validation","The 'browse' CLI tool, as described in the documentation, takes structured inputs like URLs, selectors, and refs, implying internal validation and sanitization.",{"category":100,"check":141,"severity":24,"summary":142},"Unguarded Destructive Operations","The 'browse' CLI's primary operations (navigation, interaction) are not destructive. Actions like 'stop' are confirmation-based or signal clear intent.",{"category":49,"check":144,"severity":24,"summary":145},"Error Handling","The documentation provides specific error messages and recovery steps for common issues, indicating that errors are caught and reported meaningfully.",{"category":49,"check":147,"severity":39,"summary":148},"Logging","This skill is primarily a CLI wrapper; logging is handled by the underlying 'browse' CLI and its session management, not through a dedicated audit log within the skill itself.",{"category":150,"check":151,"severity":24,"summary":152},"Compliance","GDPR","The skill interacts with web pages, which may contain personal data, but it does so via the 'browse' CLI. Data exfiltration is guarded, and no personal data is explicitly submitted to third parties by the skill itself.",{"category":150,"check":154,"severity":24,"summary":155},"Target market","The extension is designed for general web automation and is not geographically or legally restricted, thus its target market is global.",{"category":57,"check":157,"severity":24,"summary":158},"Runtime stability","The skill requires the 'browse' CLI and Node.js, which are common environments. Instructions are provided for installing Chrome, ensuring cross-platform compatibility.",{"category":30,"check":160,"severity":24,"summary":161},"README","The README file exists and clearly introduces the Browserbase skills, including the browser skill, its installation, and usage examples.",{"category":70,"check":163,"severity":24,"summary":164},"Tool surface size","The 'browse' CLI exposes a manageable number of commands (around 20+ detailed in REFERENCE.md), which is within the acceptable range for a functional tool.",{"category":22,"check":166,"severity":24,"summary":167},"Overlapping near-synonym tools","The tool names are distinct and cover specific actions (e.g., 'open', 'snapshot', 'click', 'fill'), avoiding near-synonyms that could confuse the model.",{"category":30,"check":169,"severity":24,"summary":170},"Phantom features","All advertised features in the README and SKILL.md, such as local/remote browser interaction, form filling, and data extraction, are supported by the implemented 'browse' CLI commands.",{"category":172,"check":173,"severity":24,"summary":174},"Install","Installation instruction","The README provides clear installation instructions for various platforms (npm, Claude Code) and includes example invocations and setup steps for authentication.",{"category":176,"check":177,"severity":24,"summary":178},"Errors","Actionable error messages","Error messages and troubleshooting sections in the documentation provide clear explanations of failures (e.g., 'Chrome not found', 'No active page') and offer specific remediation steps.",{"category":137,"check":180,"severity":24,"summary":181},"Pinned dependencies","The primary dependency '@browserbasehq/browse-cli' is managed by npm, which allows for version pinning. The installation instructions guide users to install this package.",{"category":70,"check":183,"severity":39,"summary":184},"Dry-run preview","The core operations of the 'browse' CLI are focused on interaction and data retrieval rather than destructive changes, making a 'dry-run' mode not directly applicable to most commands.",{"category":186,"check":187,"severity":24,"summary":188},"Protocol","Idempotent retry & timeouts","While not explicitly stated as 'idempotent,' the CLI commands focus on discrete actions. Timeouts are implicitly handled by the browser and underlying network requests. The documentation provides guidance for handling failures.",{"category":150,"check":190,"severity":24,"summary":191},"Telemetry opt-in","The skill does not appear to emit telemetry by default. Handling of API keys is via environment variables, and any potential telemetry within the CLI itself is not described as opt-out.",1778683632920,"This skill provides capabilities to automate web browser interactions using a CLI tool called 'browse'. It supports both local browser instances and remote Browserbase sessions, which include features like CAPTCHA solving, stealth mode, and residential proxies for accessing protected websites.",[195,196,197,198,199],"Automate browser interactions via CLI commands","Support for remote Browserbase sessions","Automatic CAPTCHA solving","Anti-bot stealth mode","Residential proxies for protected websites",[201,202],"Directly interacting with local filesystems beyond browser cache/profiles","Performing actions not directly related to web browser interaction","3.0.0","4.4.0","To automate web browser interactions using natural language commands, ideal for tasks like scraping protected websites, interacting with web applications, and bypassing bot detection.","High-quality documentation and clear, scoped CLI commands with robust examples. Minor areas like explicit dry-run and advanced error structuring are not applicable or are implicitly handled.",95,"A robust skill for browser automation via a CLI tool, offering local and advanced remote session capabilities.",[210,211,212,213,214,215],"browser-automation","web-scraping","cli","web-interaction","remote-sessions","captcha-solving","global","verified",[219,220,221,222],"Use when the user asks to browse websites","Use when the user asks to extract data from websites","Use when the user asks to fill forms or click buttons","Use for interacting with JavaScript-heavy web applications",{"codeQuality":224,"collectedAt":226,"documentation":227,"maintenance":230,"popularity":236,"security":237,"testCoverage":238},{"hasLockfile":225},true,1778683610848,{"descriptionLength":228,"readmeSize":229},472,4101,{"closedIssues90d":8,"forks":231,"hasChangelog":232,"openIssues90d":233,"pushedAt":234,"stars":235},214,false,2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":225,"smitheryVerified":232},{"hasCi":232,"hasTests":232},{"updatedAt":240},1778683633116,{"basePath":242,"githubOwner":243,"githubRepo":244,"locale":18,"slug":13,"type":245},"skills/browser","browserbase","skills","skill",{"_creationTime":247,"_id":248,"community":249,"display":250,"identity":254,"parentExtension":257,"providers":284,"relations":295,"tags":296,"workflow":297},1778683460321.38,"k17bx77jb71yrwatep2nb43r0d86m6cb",{"reviewCount":8},{"description":251,"installMethods":252,"name":253,"sourceUrl":14},"Automate web browser interactions using natural language. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications.",{"claudeCode":244},"browse",{"basePath":255,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":256},"","plugin",{"_creationTime":258,"_id":259,"community":260,"display":261,"identity":264,"providers":266,"relations":278,"tags":280,"workflow":281},1778683460321.3796,"k17aawpn1wczwwhv1snb1x3q2h86m1hy",{"reviewCount":8},{"description":262,"installMethods":263,"name":243,"sourceUrl":14},"Browser automation and Browserbase CLI skills",{"claudeCode":12},{"basePath":255,"githubOwner":243,"githubRepo":244,"locale":18,"slug":244,"type":265},"marketplace",{"evaluate":267,"extract":272},{"promptVersionExtension":268,"promptVersionScoring":204,"score":207,"tags":269,"targetMarket":216,"tier":217},"3.1.0",[210,212,211,270,271],"developer-tools","testing",{"commitSha":273,"marketplace":274,"plugin":276},"HEAD",{"name":243,"pluginCount":275},1,{"mcpCount":8,"provider":277,"skillCount":8},"classify",{"repoId":279},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[210,212,270,271,211],{"evaluatedAt":282,"extractAt":283,"updatedAt":282},1778683478405,1778683460321,{"evaluate":285,"extract":292},{"promptVersionExtension":203,"promptVersionScoring":204,"score":286,"tags":287,"targetMarket":216,"tier":217},98,[13,288,289,290,291],"agent","cdp","playwright","automation",{"commitSha":273,"plugin":293},{"mcpCount":8,"provider":277,"skillCount":294},12,{"parentExtensionId":259,"repoId":279},[288,291,13,289,290],{"evaluatedAt":298,"extractAt":283,"updatedAt":298},1778683581384,{"evaluate":300,"extract":302},{"promptVersionExtension":203,"promptVersionScoring":204,"score":207,"tags":301,"targetMarket":216,"tier":217},[210,211,212,213,214,215],{"commitSha":273},{"parentExtensionId":248,"repoId":279},{"_creationTime":305,"_id":279,"identity":306,"providers":307,"workflow":565},1778683454816.9644,{"githubOwner":243,"githubRepo":244,"sourceUrl":14},{"classify":308,"discover":556,"extract":559,"github":560,"npm":564},{"commitSha":273,"extensions":309},[310,320,325,331,337,343,349,374,382,408,417,441,454,477,488,497,511,522,548],{"basePath":255,"description":262,"displayName":243,"installMethods":311,"rationale":312,"selectedPaths":313,"source":319,"sourceLanguage":18,"type":265},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[314,317],{"path":315,"priority":316},".claude-plugin/marketplace.json","mandatory",{"path":318,"priority":316},"README.md","rule",{"basePath":255,"description":251,"displayName":253,"installMethods":321,"rationale":322,"selectedPaths":323,"source":319,"sourceLanguage":18,"type":256},{"claudeCode":244},"inline plugin source from marketplace.json at /",[324],{"path":318,"priority":316},{"basePath":255,"description":326,"displayName":327,"installMethods":328,"rationale":322,"selectedPaths":329,"source":319,"sourceLanguage":18,"type":256},"Deploy serverless browser automation to the cloud using Browserbase Functions. Use when the user wants to deploy automation to run on a schedule, needs a webhook endpoint for browser automation, wants to run automation in the cloud instead of locally, or asks about Browserbase Functions.","functions",{"claudeCode":244},[330],{"path":318,"priority":316},{"basePath":255,"description":332,"displayName":333,"installMethods":334,"rationale":322,"selectedPaths":335,"source":319,"sourceLanguage":18,"type":256},"Use the Browserbase CLI (`bb`) for Browserbase Functions and platform API workflows. Use when the user asks to run `bb`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, or open the Browserbase dashboard from the command line.","browserbase-cli",{"claudeCode":244},[336],{"path":318,"priority":316},{"basePath":255,"description":338,"displayName":339,"installMethods":340,"rationale":322,"selectedPaths":341,"source":319,"sourceLanguage":18,"type":256},"Capture a full DevTools-protocol trace (CDP firehose, screenshots, DOM dumps) alongside any browser automation, then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-flight Browserbase session, or feed structured per-page summaries back into an agent loop.","browser-trace",{"claudeCode":244},[342],{"path":318,"priority":316},{"basePath":255,"description":344,"displayName":345,"installMethods":346,"rationale":322,"selectedPaths":347,"source":319,"sourceLanguage":18,"type":256},"Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access.","safe-browser",{"claudeCode":244},[348],{"path":318,"priority":316},{"basePath":350,"description":351,"displayName":352,"installMethods":353,"rationale":354,"selectedPaths":355,"source":319,"sourceLanguage":18,"type":245},"skills/autobrowse","Self-improving browser automation via the auto-research loop. Iteratively runs a browsing task, reads the trace, and improves the navigation skill (strategy.md) until it reliably passes. Supports parallel runs across multiple tasks using sub-agents. Use when you want to build or improve browser automation skills for specific website tasks.","autobrowse",{"claudeCode":12},"SKILL.md frontmatter at skills/autobrowse/SKILL.md",[356,358,360,362,365,367,369,371],{"path":357,"priority":316},"SKILL.md",{"path":318,"priority":359},"high",{"path":361,"priority":359},"LICENSE.txt",{"path":363,"priority":364},"EXAMPLES.md","medium",{"path":366,"priority":364},"REFERENCE.md",{"path":368,"priority":364},"references/example-skill.md",{"path":370,"priority":364},"references/example-task.md",{"path":372,"priority":373},"scripts/evaluate.mjs","low",{"basePath":242,"description":10,"displayName":13,"installMethods":375,"rationale":376,"selectedPaths":377,"source":319,"sourceLanguage":18,"type":245},{"claudeCode":12},"SKILL.md frontmatter at skills/browser/SKILL.md",[378,379,380,381],{"path":357,"priority":316},{"path":361,"priority":359},{"path":363,"priority":364},{"path":366,"priority":364},{"basePath":383,"description":384,"displayName":339,"installMethods":385,"rationale":386,"selectedPaths":387,"source":319,"sourceLanguage":18,"type":245},"skills/browser-trace","Capture a full DevTools-protocol trace of any browser automation — CDP firehose, screenshots, and DOM dumps — then bisect the stream into per-page searchable buckets. Use when the user wants to debug a failed run, audit network/console/DOM activity, attach a trace to an in-progress session, or feed structured per-page summaries back into an agent loop so its next iteration learns from the last one.",{"claudeCode":12},"SKILL.md frontmatter at skills/browser-trace/SKILL.md",[388,389,390,391,392,394,396,398,400,402,404,406],{"path":357,"priority":316},{"path":361,"priority":359},{"path":363,"priority":364},{"path":366,"priority":364},{"path":393,"priority":373},"scripts/bb-capture.mjs",{"path":395,"priority":373},"scripts/bb-finalize.mjs",{"path":397,"priority":373},"scripts/bisect-cdp.mjs",{"path":399,"priority":373},"scripts/lib.mjs",{"path":401,"priority":373},"scripts/query.mjs",{"path":403,"priority":373},"scripts/snapshot-loop.mjs",{"path":405,"priority":373},"scripts/start-capture.mjs",{"path":407,"priority":373},"scripts/stop-capture.mjs",{"basePath":409,"description":410,"displayName":333,"installMethods":411,"rationale":412,"selectedPaths":413,"source":319,"sourceLanguage":18,"type":245},"skills/browserbase-cli","Use the Browserbase CLI (`bb`) for Browserbase Functions and platform API workflows. Use when the user asks to run `bb`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use `bb browse` only when the user explicitly wants the Browserbase CLI path.",{"claudeCode":12},"SKILL.md frontmatter at skills/browserbase-cli/SKILL.md",[414,415,416],{"path":357,"priority":316},{"path":361,"priority":359},{"path":366,"priority":364},{"basePath":418,"description":419,"displayName":420,"installMethods":421,"rationale":422,"selectedPaths":423,"source":319,"sourceLanguage":18,"type":245},"skills/company-research","Company discovery and deep research skill. Researches a company's product and ICP,\ndiscovers target companies to sell to using Browserbase Search API, deeply researches\neach using a Plan→Research→Synthesize pattern, and scores ICP fit — compiled into\na scored research report and CSV. Supports depth modes (quick/deep/deeper) for\nbalancing scale vs intelligence.\nUse when the user wants to: (1) find companies to sell to, (2) research potential\ncustomers, (3) discover companies matching an ICP, (4) build a target company list,\n(5) do market research on prospects. Triggers: \"find companies to sell to\",\n\"company research\", \"find prospects\", \"ICP research\", \"target companies\",\n\"who should we sell to\", \"market research\", \"lead research\", \"prospect list\".\n","company-research",{"claudeCode":12},"SKILL.md frontmatter at skills/company-research/SKILL.md",[424,425,427,429,431,433,435,437,439],{"path":357,"priority":316},{"path":426,"priority":364},"references/example-research.md",{"path":428,"priority":364},"references/report-template.html",{"path":430,"priority":364},"references/research-patterns.md",{"path":432,"priority":364},"references/workflow.md",{"path":434,"priority":373},"scripts/compile_report.mjs",{"path":436,"priority":373},"scripts/extract_page.mjs",{"path":438,"priority":373},"scripts/list_urls.mjs",{"path":440,"priority":373},"scripts/package.json",{"basePath":442,"description":443,"displayName":444,"installMethods":445,"rationale":446,"selectedPaths":447,"source":319,"sourceLanguage":18,"type":245},"skills/cookie-sync","Sync cookies from local Chrome to a Browserbase persistent context so the browse CLI can access authenticated sites. Use when the user wants to browse as themselves, sync cookies, or log into sites via Browserbase.","cookie-sync",{"claudeCode":12},"SKILL.md frontmatter at skills/cookie-sync/SKILL.md",[448,449,450,451,452],{"path":357,"priority":316},{"path":361,"priority":359},{"path":363,"priority":364},{"path":366,"priority":364},{"path":453,"priority":373},"scripts/cookie-sync.mjs",{"basePath":455,"description":456,"displayName":457,"installMethods":458,"rationale":459,"selectedPaths":460,"source":319,"sourceLanguage":18,"type":245},"skills/event-prospecting","Event prospecting skill. Takes a conference / event speakers URL,\nextracts the people, filters their companies against the user's\nICP, then deep-researches only the speakers at ICP-fit companies.\nOutputs a person-first HTML report where each card answers \"why\nshould the AE talk to this person?\" with all public links and a\none-click DM opener.\nUse when the user wants to: (1) find leads at a specific\nconference, (2) prep for an event, (3) research event speakers,\n(4) build a target list from a sponsor/exhibitor page,\n(5) scrape conference speakers and rank by ICP fit.\nTriggers: \"find leads at {event}\", \"research speakers at\",\n\"prospect this conference\", \"stripe sessions leads\",\n\"ai engineer summit prospects\", \"event prospecting\",\n\"scrape conference speakers\", \"who should I meet at\".\n","event-prospecting",{"claudeCode":12},"SKILL.md frontmatter at skills/event-prospecting/SKILL.md",[461,462,464,465,466,467,468,470,471,473,474,475],{"path":357,"priority":316},{"path":463,"priority":364},"references/event-platforms.md",{"path":426,"priority":364},{"path":428,"priority":364},{"path":430,"priority":364},{"path":432,"priority":364},{"path":469,"priority":373},"scripts/__fixtures__/stripe-snapshot.json",{"path":434,"priority":373},{"path":472,"priority":373},"scripts/extract_event.mjs",{"path":436,"priority":373},{"path":440,"priority":373},{"path":476,"priority":373},"scripts/recon.mjs",{"basePath":478,"description":479,"displayName":480,"installMethods":481,"rationale":482,"selectedPaths":483,"source":319,"sourceLanguage":18,"type":245},"skills/fetch","Use this skill when the user wants to retrieve a URL without a full browser session: fetch HTML or JSON from static pages, inspect status codes or headers, follow redirects, or get page source for simple scraping. Prefer it over a browser when JavaScript rendering and page interaction are not needed. Supports proxies and redirect control.","fetch",{"claudeCode":12},"SKILL.md frontmatter at skills/fetch/SKILL.md",[484,485,486,487],{"path":357,"priority":316},{"path":361,"priority":359},{"path":363,"priority":364},{"path":366,"priority":364},{"basePath":489,"description":490,"displayName":327,"installMethods":491,"rationale":492,"selectedPaths":493,"source":319,"sourceLanguage":18,"type":245},"skills/functions","Deploy serverless browser automation as cloud functions using Browserbase. Use when the user wants to deploy browser automation to run on a schedule or cron, create a webhook endpoint for browser tasks, run automation in the cloud instead of locally, or asks about Browserbase Functions.",{"claudeCode":12},"SKILL.md frontmatter at skills/functions/SKILL.md",[494,495,496],{"path":357,"priority":316},{"path":361,"priority":359},{"path":366,"priority":364},{"basePath":498,"description":499,"displayName":345,"installMethods":500,"rationale":501,"selectedPaths":502,"source":319,"sourceLanguage":18,"type":245},"skills/safe-browser","Build local constrained-browser agents with a safe_browser tool that owns CDP, enforces a domain allowlist with Fetch interception, and lets a runtime Claude Agent SDK agent complete browsing tasks without raw browser, shell, or CDP access. Use when the user wants an agent to browse or scrape while staying on approved domains, demo blocked off-domain navigation, or generate a safe browser client.",{"claudeCode":12},"SKILL.md frontmatter at skills/safe-browser/SKILL.md",[503,504,505,507,509],{"path":357,"priority":316},{"path":361,"priority":359},{"path":506,"priority":373},"templates/claude-agent-sdk/.gitignore",{"path":508,"priority":373},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":510,"priority":373},"templates/claude-agent-sdk/package.json",{"basePath":512,"description":513,"displayName":514,"installMethods":515,"rationale":516,"selectedPaths":517,"source":319,"sourceLanguage":18,"type":245},"skills/search","Use this skill when the user wants to search the web without a full browser session: find URLs, titles, and metadata for a query. Prefer it over a browser when you just need search results, not page content. Returns structured results with titles, URLs, authors, and dates.","search",{"claudeCode":12},"SKILL.md frontmatter at skills/search/SKILL.md",[518,519,520,521],{"path":357,"priority":316},{"path":361,"priority":359},{"path":363,"priority":364},{"path":366,"priority":364},{"basePath":523,"description":524,"displayName":525,"installMethods":526,"rationale":527,"selectedPaths":528,"source":319,"sourceLanguage":18,"type":245},"skills/ui-test","AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness, accessibility, responsive layout, and UX heuristics. Use when the user asks to test UI changes, QA a pull request, audit accessibility, or run exploratory testing. Supports local browser (localhost) and remote Browserbase (deployed sites).","ui-test",{"claudeCode":12},"SKILL.md frontmatter at skills/ui-test/SKILL.md",[529,530,531,532,533,535,537,539,541,543,545,546],{"path":357,"priority":316},{"path":318,"priority":359},{"path":361,"priority":359},{"path":363,"priority":364},{"path":534,"priority":364},"references/adversarial-patterns.md",{"path":536,"priority":364},"references/browser-recipes.md",{"path":538,"priority":364},"references/design-consistency.md",{"path":540,"priority":364},"references/design-system.example.md",{"path":542,"priority":364},"references/exploratory-testing.md",{"path":544,"priority":364},"references/parallel-testing.md",{"path":428,"priority":364},{"path":547,"priority":364},"references/ux-heuristics.md",{"basePath":255,"displayName":549,"installMethods":550,"rationale":551,"selectedPaths":552,"source":319,"sourceLanguage":18,"type":212},"browserbase-skills",{"npm":549},"cli ecosystem detected at /",[553,555],{"path":554,"priority":316},"package.json",{"path":318,"priority":316},{"sources":557},[558],"manual",{"npmPackage":549},{"closedIssues90d":8,"description":561,"forks":231,"homepage":562,"openIssues90d":233,"pushedAt":234,"readmeSize":229,"stars":235,"topics":563},"Browserbase's official collection of agent skills to access the web.","https://www.browserbase.com/SKILL.md",[],{"downloads":8},{"classifiedAt":566,"discoverAt":567,"extractAt":568,"githubAt":568,"npmAt":569,"updatedAt":566},1778683460101,1778683454817,1778683457134,1778683458753,[210,215,212,214,213,211],{"evaluatedAt":240,"extractAt":283,"updatedAt":240},[],[574,602,629,648,676,702],{"_creationTime":575,"_id":576,"community":577,"display":578,"identity":584,"providers":589,"relations":594,"tags":597,"workflow":598},1778697373439.756,"k1735p8vnc44y3ntfepns5m0nx86npbs",{"reviewCount":8},{"description":579,"installMethods":580,"name":582,"sourceUrl":583},"Browser-automatisierungs-CLI für KI-Agenten. Verwenden Sie diese, wenn der Benutzer mit Websites interagieren muss, einschließlich der Navigation auf Seiten, dem Ausfüllen von Formularen, dem Klicken auf Schaltflächen, dem Aufnehmen von Screenshots, dem Extrahieren von Daten, dem Testen von Webanwendungen oder der Automatisierung beliebiger Browseraufgaben. Auslöser sind Anfragen wie \"öffne eine Website\", \"fülle ein Formular aus\", \"klicke auf eine Schaltfläche\", \"mache einen Screenshot\", \"scrappe Daten von einer Seite\", \"teste diese Web-App\", \"melde dich bei einer Seite an\", \"automatisiere Browser-Aktionen\" oder jede Aufgabe, die eine programmatische Webinteraktion erfordert.",{"claudeCode":581},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":585,"githubOwner":586,"githubRepo":587,"locale":588,"slug":582,"type":245},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice","de",{"evaluate":590,"extract":593},{"promptVersionExtension":203,"promptVersionScoring":204,"score":591,"tags":592,"targetMarket":216,"tier":217},100,[210,211,271,212,291],{"commitSha":273},{"repoId":595,"translatedFrom":596},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[291,210,212,271,211],{"evaluatedAt":599,"extractAt":600,"updatedAt":601},1778697222051,1778697205743,1778697373439,{"_creationTime":603,"_id":604,"community":605,"display":606,"identity":612,"providers":616,"relations":623,"tags":625,"workflow":626},1778696993586.7058,"k174ty9vbfgj7cv3v2szdwjgh986mrsf",{"reviewCount":8},{"description":607,"installMethods":608,"name":610,"sourceUrl":611},"Search ChatGPT and extract the full response + hydration JSON that powers the UI.\nAttaches to a running Chrome instance (port 9222 by default), opens ChatGPT,\nsubmits a query, waits for the streamed response, and returns structured data:\nmessages, product cards, hydration JSON, and API calls.\nUse when asked to \"search chatgpt\", \"ask chatgpt\", \"chatgpt search\",\n\"get chatgpt response\", or \"scrape chatgpt\".\n",{"claudeCode":609},"SeifBenayed/claude-code-sdk","chatgpt-search","https://github.com/SeifBenayed/claude-code-sdk",{"basePath":613,"githubOwner":614,"githubRepo":615,"locale":18,"slug":610,"type":245},".claude/skills/chatgpt-search","SeifBenayed","claude-code-sdk",{"evaluate":617,"extract":622},{"promptVersionExtension":203,"promptVersionScoring":204,"score":591,"tags":618,"targetMarket":216,"tier":217},[619,620,210,621,211],"chatgpt","scraping","data-extraction",{"commitSha":273},{"repoId":624},"kd78s53c1852h5p7c3qem663xs86njab",[210,619,621,620,211],{"evaluatedAt":627,"extractAt":628,"updatedAt":627},1778697026743,1778696993586,{"_creationTime":630,"_id":631,"community":632,"display":633,"identity":636,"providers":637,"relations":644,"tags":645,"workflow":646},1778683460321.381,"k1707rtzme0qezretvp3gmtfvn86n1k1",{"reviewCount":8},{"description":351,"installMethods":634,"name":635,"sourceUrl":14},{"claudeCode":12},"AutoBrowse",{"basePath":350,"githubOwner":243,"githubRepo":244,"locale":18,"slug":352,"type":245},{"evaluate":638,"extract":642},{"promptVersionExtension":203,"promptVersionScoring":204,"score":591,"tags":639,"targetMarket":216,"tier":217},[210,211,640,271,641],"llm-agent","node-js",{"commitSha":273,"license":643},"MIT",{"parentExtensionId":248,"repoId":279},[210,640,641,271,211],{"evaluatedAt":647,"extractAt":283,"updatedAt":647},1778683610531,{"_creationTime":649,"_id":650,"community":651,"display":652,"identity":658,"providers":662,"relations":669,"tags":672,"workflow":673},1778696691708.3125,"k1704t5mbdhdjkqqyvh15rz98986n4b0",{"reviewCount":8},{"description":653,"installMethods":654,"name":656,"sourceUrl":657},"Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model",{"claudeCode":655},"ruvnet/ruflo","browser-extract","https://github.com/ruvnet/ruflo",{"basePath":659,"githubOwner":660,"githubRepo":661,"locale":18,"slug":656,"type":245},"plugins/ruflo-browser/skills/browser-extract","ruvnet","ruflo",{"evaluate":663,"extract":668},{"promptVersionExtension":203,"promptVersionScoring":204,"score":664,"tags":665,"targetMarket":216,"tier":217},99,[211,621,210,666,667],"security","pii-detection",{"commitSha":273},{"parentExtensionId":670,"repoId":671},"k171keecmm9hg25jek1v0vqawd86ntq2","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[210,621,667,666,211],{"evaluatedAt":674,"extractAt":675,"updatedAt":674},1778699898275,1778696691708,{"_creationTime":677,"_id":678,"community":679,"display":680,"identity":685,"providers":689,"relations":694,"tags":697,"workflow":698},1778698644808.435,"k179zdfeah0b0cr5pvznget1cx86mkmf",{"reviewCount":8},{"description":681,"installMethods":682,"name":582,"sourceUrl":684},"Interagieren Sie mit Slack-Arbeitsbereichen mithilfe von Browser-Automatisierung. Verwenden Sie dies, wenn der Benutzer ungelesene Kanäle überprüfen, Slack navigieren, Nachrichten senden, Daten extrahieren, Informationen finden, Konversationen durchsuchen oder jede Slack-Aufgabe automatisieren muss. Trigger sind \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\" oder jede Aufgabe, die programmatische Slack-Interaktion erfordert.",{"claudeCode":683},"vercel-labs/agent-browser","https://github.com/vercel-labs/agent-browser",{"basePath":686,"githubOwner":687,"githubRepo":582,"locale":588,"slug":688,"type":245},"skill-data/slack","vercel-labs","slack",{"evaluate":690,"extract":692},{"promptVersionExtension":203,"promptVersionScoring":204,"score":664,"tags":691,"targetMarket":216,"tier":217},[210,688,212,291,211],{"commitSha":273,"license":693},"Apache-2.0",{"repoId":695,"translatedFrom":696},"kd74a6sfc26xa0ec2tpntj8r2986mn0a","k175jjsqj2p1he1cnp97qv600x86m87w",[291,210,212,688,211],{"evaluatedAt":699,"extractAt":700,"updatedAt":701},1778698509141,1778698388091,1778698644808,{"_creationTime":703,"_id":704,"community":705,"display":706,"identity":712,"providers":715,"relations":720,"tags":724,"workflow":725},1778696989496.538,"k1776jcwjkmjfcm2gv94xeezz586m1tg",{"reviewCount":8},{"description":707,"installMethods":708,"name":710,"sourceUrl":711},"Browserautomatisierung mit persistentem Seitenzustand. Verwenden Sie dies, wenn Benutzer aufgefordert werden, Websites zu navigieren, Formulare auszufüllen, Screenshots zu erstellen, Webdaten zu extrahieren, Webanwendungen zu testen oder Browser-Workflows zu automatisieren. Auslöser-Phrasen sind \"gehe zu [URL]\", \"klicke auf\", \"fülle das Formular aus\", \"mache einen Screenshot\", \"scrapen\", \"automatisieren\", \"teste die Website\", \"melde dich an\" oder jede Anfrage zur Browserinteraktion.",{"claudeCode":709},"SawyerHood/dev-browser","dev-browser","https://github.com/SawyerHood/dev-browser",{"basePath":713,"githubOwner":714,"githubRepo":710,"locale":588,"slug":710,"type":245},"skills/dev-browser","SawyerHood",{"evaluate":716,"extract":719},{"promptVersionExtension":203,"promptVersionScoring":204,"score":664,"tags":717,"targetMarket":216,"tier":217},[210,290,718,271,211],"javascript",{"commitSha":273},{"parentExtensionId":721,"repoId":722,"translatedFrom":723},"k172vf4sjqdwht2n7b64bmf7wn86mzzp","kd778ksdnkgy1969578mg8f30986nddw","k17535f2wgbtzrzc5n55ps9f3586mr7p",[210,718,290,271,211],{"evaluatedAt":726,"extractAt":727,"updatedAt":728},1778696938150,1778696896101,1778696989496]