[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-functions-de":3,"guides-for-browserbase-functions":577,"similar-k17f1z6rytr3pcs0qb838kebv586mhyh-de":578},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":228,"parentExtension":249,"providers":305,"relations":309,"repo":310,"tags":575,"workflow":576},1778683460321.383,"k17f1z6rytr3pcs0qb838kebv586mhyh",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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},"browserbase/skills","functions","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":226,"workflow":242},1778683808928.1223,"kn7cqe2zn2h3faq4nkdhks6p9h86mf5m","en",{"checks":20,"evaluatedAt":194,"extensionSummary":195,"features":196,"nonGoals":202,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":219,"tier":220,"useCases":221},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,104,107,110,113,116,119,122,126,129,133,137,141,144,147,151,155,158,161,164,167,170,173,177,181,184,187,191],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The description clearly states what the skill does (deploy serverless browser automation using Browserbase) and when to use it (schedule, cron, webhook, cloud execution, or asking about Browserbase Functions), making its purpose and target user evident.",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and usage scenarios within the character limit.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md body is well under 500 lines and uses progressive disclosure by linking to a REFERENCE.md file for deeper material.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The SKILL.md outlines the main procedure and correctly links to a REFERENCE.md file for invocation examples, common patterns, and troubleshooting, adhering to progressive disclosure.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill is not an exploration or audit-style skill and does not involve deep code review or multi-file inspection, so the 'context: fork' setting is not applicable.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The SKILL.md and REFERENCE.md provide clear, end-to-end examples for initializing, developing, deploying, and invoking functions, including code snippets and expected outcomes.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The REFERENCE.md document addresses common failure modes like missing API keys, dev server issues, and function timeouts, providing symptom and recovery steps.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","This skill does not appear to rely on external tools like an MCP server and is self-contained, making the fallback check not applicable.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The skill's prerequisites section and troubleshooting guide imply that missing credentials or dependencies will halt the workflow, reporting an error.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is self-contained and does not implicitly rely on other skills; it focuses solely on Browserbase Functions deployment and invocation.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description directly addresses the user's need to deploy serverless browser automation to the cloud for scheduled tasks, webhooks, or general cloud execution.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill provides a clear workflow for deploying and managing serverless browser automation functions via Browserbase, offering a distinct value proposition beyond generic browser automation.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The skill covers the complete lifecycle from initialization and local development to deployment and invocation, appearing ready for production workflows.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill is focused on deploying and managing serverless browser automation functions using Browserbase, adhering to a single responsibility.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The description is accurate, concise, and clearly reflects the skill's functionality, including usage scenarios.",{"category":22,"check":77,"severity":39,"summary":78},"Scoped tools","This skill does not expose specific tools or commands in the traditional sense; its functionality is accessed via `bb` CLI commands documented within the SKILL.md.",{"category":30,"check":80,"severity":24,"summary":81},"Configuration & parameter reference","Prerequisites clearly list required environment variables and API keys, and the function structure in SKILL.md explains input parameters (`context.params`).",{"category":70,"check":83,"severity":39,"summary":84},"Tool naming","As this skill primarily uses CLI commands and the `defineFn` pattern, there are no distinct user-facing tools with names to evaluate.",{"category":70,"check":86,"severity":24,"summary":87},"Minimal I/O surface","The function structure shows clear input parameters (`context.params`) and a defined JSON-serializable result, with no extraneous data.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The MIT license is clearly provided in a LICENSE.txt file, permitting broad usability.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The `pushedAt` timestamp indicates recent commits within the last 12 months.",{"category":93,"check":97,"severity":24,"summary":98},"Dependency Management","The project uses pnpm and has a `package.json` and likely a lockfile, indicating good dependency management practices.",{"category":100,"check":101,"severity":102,"summary":103},"Security","Secret Management","warning","The `.env` file is mentioned for storing credentials, but it is not included in `.gitignore` and could be committed, posing a risk.",{"category":100,"check":105,"severity":24,"summary":106},"Injection","The skill focuses on deploying code and does not appear to load untrusted third-party data as instructions.",{"category":100,"check":108,"severity":24,"summary":109},"Transitive Supply-Chain Grenades","The skill uses standard package managers (`pnpm`) and CLI commands; there are no indications of runtime fetching of external code or instructions.",{"category":100,"check":111,"severity":24,"summary":112},"Sandbox Isolation","The skill operates within the Browserbase environment and its own bundled code, with no apparent attempts to modify files outside its scope.",{"category":100,"check":114,"severity":24,"summary":115},"Sandbox escape primitives","No detached-process spawns or deny-retry loops were observed in the provided script examples.",{"category":100,"check":117,"severity":24,"summary":118},"Data Exfiltration","The skill focuses on code deployment and execution, with no apparent mechanisms for exfiltrating confidential data.",{"category":100,"check":120,"severity":24,"summary":121},"Hidden Text Tricks","The bundled content appears to be clean, standard TypeScript and Markdown, with no hidden steering tricks.",{"category":123,"check":124,"severity":24,"summary":125},"Hooks","Opaque code execution","The provided code snippets are plain TypeScript and do not involve obfuscation, base64 payloads, or runtime fetching of code.",{"category":57,"check":127,"severity":24,"summary":128},"Structural Assumption","The skill uses relative paths for project structure and clearly states prerequisites, avoiding rigid structural assumptions.",{"category":130,"check":131,"severity":102,"summary":132},"Trust","Issues Attention","In the last 90 days, 2 issues were opened and 0 were closed, indicating slow or no maintainer response to open issues.",{"category":134,"check":135,"severity":24,"summary":136},"Versioning","Release Management","The SKILL.md frontmatter includes a license but no explicit version number. However, the `pushedAt` date suggests recent activity and installation via `browserbase/skills` implies a managed version.",{"category":138,"check":139,"severity":24,"summary":140},"Execution","Validation","The function structure defines input parameters and expects a JSON-serializable result, implying validation at the function level.",{"category":100,"check":142,"severity":24,"summary":143},"Unguarded Destructive Operations","Deploying functions is a state-changing operation but is performed via CLI commands which typically prompt for confirmation or have clear triggers.",{"category":49,"check":145,"severity":24,"summary":146},"Error Handling","The example function in SKILL.md and the REFERENCE.md show try-catch blocks for handling errors during browser automation and return structured results.",{"category":49,"check":148,"severity":149,"summary":150},"Logging","info","The development workflow mentions using `console.log()` for debugging, indicating basic logging, but a formal audit log is not explicitly described.",{"category":152,"check":153,"severity":24,"summary":154},"Compliance","GDPR","The skill deploys code; it does not directly operate on or submit personal data, making GDPR compliance not applicable.",{"category":152,"check":156,"severity":24,"summary":157},"Target market","The skill is global in scope and does not contain any regional or jurisdictional limitations.",{"category":57,"check":159,"severity":24,"summary":160},"Runtime stability","The skill relies on Node.js and pnpm, with clear instructions for installation and setup, indicating good cross-platform compatibility.",{"category":30,"check":162,"severity":24,"summary":163},"README","The README.md provides a clear overview of the Browserbase skills and installation instructions.",{"category":70,"check":165,"severity":39,"summary":166},"Tool surface size","This skill itself does not expose individual tools but rather enables the deployment and management of functions via CLI commands.",{"category":22,"check":168,"severity":39,"summary":169},"Overlapping near-synonym tools","This skill does not expose multiple tools with overlapping functionality.",{"category":30,"check":171,"severity":24,"summary":172},"Phantom features","All advertised features related to deploying and managing functions are supported by the CLI commands and code examples provided.",{"category":174,"check":175,"severity":24,"summary":176},"Install","Installation instruction","The README provides clear installation instructions for various agents, including specific steps for Claude Code and manual installation.",{"category":178,"check":179,"severity":24,"summary":180},"Errors","Actionable error messages","The REFERENCE.md and examples show structured error handling and provide guidance on remediation for common issues like missing credentials or timeouts.",{"category":138,"check":182,"severity":24,"summary":183},"Pinned dependencies","The use of pnpm and `package.json` implies dependency pinning, and the explicit mention of `pnpm install` suggests lockfiles are used.",{"category":70,"check":185,"severity":39,"summary":186},"Dry-run preview","The primary function of this skill is code deployment, not a state-changing operation that would typically require a dry-run preview.",{"category":188,"check":189,"severity":24,"summary":190},"Protocol","Idempotent retry & timeouts","The REFERENCE.md mentions function timeouts and suggests handling them, implying a design aware of potential retries and timeouts.",{"category":152,"check":192,"severity":24,"summary":193},"Telemetry opt-in","There is no mention of telemetry being collected or opt-out mechanisms; the skill appears to operate without intrusive telemetry.",1778683808791,"This skill enables users to deploy serverless browser automation using Browserbase Functions and the `bb` CLI. It provides tools for initializing, developing, testing, and deploying TypeScript-based browser automation scripts to the cloud.",[197,198,199,200,201],"Deploy serverless browser automation functions","Utilize Browserbase cloud infrastructure","Develop functions with TypeScript and Playwright","Local development server with auto-reloading","Publish functions for scheduled or webhook invocation",[203,204,205],"Running browser automation locally without deployment","Directly managing Browserbase infrastructure beyond function deployment","Generic browser automation without serverless deployment","3.0.0","4.4.0","To deploy and manage serverless browser automation as cloud functions using Browserbase, enabling scheduled tasks, webhook endpoints, and cloud-based execution.","The single warning regarding secret management and the warning on slow issue closure place this skill in the 'evaluated' tier. The remaining checks are largely passing, indicating good overall quality.",79,"A high-quality skill for deploying serverless browser automation functions, with excellent documentation and clear use cases.",[213,214,215,216,217,218],"browser-automation","cloud-functions","serverless","cli","typescript","playwright","global","community",[222,223,224,225],"Deploying browser automation to run on a schedule or cron","Creating webhook endpoints for browser automation tasks","Running browser automation in the cloud instead of locally","Asking about Browserbase Functions for deployment",{"codeQuality":227,"collectedAt":229,"documentation":230,"maintenance":233,"popularity":239,"security":240,"testCoverage":241},{"hasLockfile":228},true,1778683789756,{"descriptionLength":231,"readmeSize":232},287,4101,{"closedIssues90d":8,"forks":234,"hasChangelog":235,"openIssues90d":236,"pushedAt":237,"stars":238},214,false,2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":228,"smitheryVerified":235},{"hasCi":235,"hasTests":235},{"updatedAt":243},1778683808928,{"basePath":245,"githubOwner":246,"githubRepo":247,"locale":18,"slug":13,"type":248},"skills/functions","browserbase","skills","skill",{"_creationTime":250,"_id":251,"community":252,"display":253,"identity":257,"parentExtension":260,"providers":290,"relations":301,"tags":302,"workflow":303},1778683460321.38,"k17bx77jb71yrwatep2nb43r0d86m6cb",{"reviewCount":8},{"description":254,"installMethods":255,"name":256,"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":247},"browse",{"basePath":258,"githubOwner":246,"githubRepo":247,"locale":18,"slug":247,"type":259},"","plugin",{"_creationTime":261,"_id":262,"community":263,"display":264,"identity":267,"providers":269,"relations":284,"tags":286,"workflow":287},1778683460321.3796,"k17aawpn1wczwwhv1snb1x3q2h86m1hy",{"reviewCount":8},{"description":265,"installMethods":266,"name":246,"sourceUrl":14},"Browser automation and Browserbase CLI skills",{"claudeCode":12},{"basePath":258,"githubOwner":246,"githubRepo":247,"locale":18,"slug":247,"type":268},"marketplace",{"evaluate":270,"extract":278},{"promptVersionExtension":271,"promptVersionScoring":207,"score":272,"tags":273,"targetMarket":219,"tier":277},"3.1.0",95,[213,216,274,275,276],"web-scraping","developer-tools","testing","verified",{"commitSha":279,"marketplace":280,"plugin":282},"HEAD",{"name":246,"pluginCount":281},1,{"mcpCount":8,"provider":283,"skillCount":8},"classify",{"repoId":285},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[213,216,275,276,274],{"evaluatedAt":288,"extractAt":289,"updatedAt":288},1778683478405,1778683460321,{"evaluate":291,"extract":298},{"promptVersionExtension":206,"promptVersionScoring":207,"score":292,"tags":293,"targetMarket":219,"tier":277},98,[294,295,296,218,297],"browser","agent","cdp","automation",{"commitSha":279,"plugin":299},{"mcpCount":8,"provider":283,"skillCount":300},12,{"parentExtensionId":262,"repoId":285},[295,297,294,296,218],{"evaluatedAt":304,"extractAt":289,"updatedAt":304},1778683581384,{"evaluate":306,"extract":308},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":307,"targetMarket":219,"tier":220},[213,214,215,216,217,218],{"commitSha":279},{"parentExtensionId":251,"repoId":285},{"_creationTime":311,"_id":285,"identity":312,"providers":313,"workflow":570},1778683454816.9644,{"githubOwner":246,"githubRepo":247,"sourceUrl":14},{"classify":314,"discover":561,"extract":564,"github":565,"npm":569},{"commitSha":279,"extensions":315},[316,326,331,336,342,348,354,379,389,415,424,448,461,484,495,502,516,527,553],{"basePath":258,"description":265,"displayName":246,"installMethods":317,"rationale":318,"selectedPaths":319,"source":325,"sourceLanguage":18,"type":268},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[320,323],{"path":321,"priority":322},".claude-plugin/marketplace.json","mandatory",{"path":324,"priority":322},"README.md","rule",{"basePath":258,"description":254,"displayName":256,"installMethods":327,"rationale":328,"selectedPaths":329,"source":325,"sourceLanguage":18,"type":259},{"claudeCode":247},"inline plugin source from marketplace.json at /",[330],{"path":324,"priority":322},{"basePath":258,"description":332,"displayName":13,"installMethods":333,"rationale":328,"selectedPaths":334,"source":325,"sourceLanguage":18,"type":259},"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.",{"claudeCode":247},[335],{"path":324,"priority":322},{"basePath":258,"description":337,"displayName":338,"installMethods":339,"rationale":328,"selectedPaths":340,"source":325,"sourceLanguage":18,"type":259},"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":247},[341],{"path":324,"priority":322},{"basePath":258,"description":343,"displayName":344,"installMethods":345,"rationale":328,"selectedPaths":346,"source":325,"sourceLanguage":18,"type":259},"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":247},[347],{"path":324,"priority":322},{"basePath":258,"description":349,"displayName":350,"installMethods":351,"rationale":328,"selectedPaths":352,"source":325,"sourceLanguage":18,"type":259},"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":247},[353],{"path":324,"priority":322},{"basePath":355,"description":356,"displayName":357,"installMethods":358,"rationale":359,"selectedPaths":360,"source":325,"sourceLanguage":18,"type":248},"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",[361,363,365,367,370,372,374,376],{"path":362,"priority":322},"SKILL.md",{"path":324,"priority":364},"high",{"path":366,"priority":364},"LICENSE.txt",{"path":368,"priority":369},"EXAMPLES.md","medium",{"path":371,"priority":369},"REFERENCE.md",{"path":373,"priority":369},"references/example-skill.md",{"path":375,"priority":369},"references/example-task.md",{"path":377,"priority":378},"scripts/evaluate.mjs","low",{"basePath":380,"description":381,"displayName":294,"installMethods":382,"rationale":383,"selectedPaths":384,"source":325,"sourceLanguage":18,"type":248},"skills/browser","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},"SKILL.md frontmatter at skills/browser/SKILL.md",[385,386,387,388],{"path":362,"priority":322},{"path":366,"priority":364},{"path":368,"priority":369},{"path":371,"priority":369},{"basePath":390,"description":391,"displayName":344,"installMethods":392,"rationale":393,"selectedPaths":394,"source":325,"sourceLanguage":18,"type":248},"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",[395,396,397,398,399,401,403,405,407,409,411,413],{"path":362,"priority":322},{"path":366,"priority":364},{"path":368,"priority":369},{"path":371,"priority":369},{"path":400,"priority":378},"scripts/bb-capture.mjs",{"path":402,"priority":378},"scripts/bb-finalize.mjs",{"path":404,"priority":378},"scripts/bisect-cdp.mjs",{"path":406,"priority":378},"scripts/lib.mjs",{"path":408,"priority":378},"scripts/query.mjs",{"path":410,"priority":378},"scripts/snapshot-loop.mjs",{"path":412,"priority":378},"scripts/start-capture.mjs",{"path":414,"priority":378},"scripts/stop-capture.mjs",{"basePath":416,"description":417,"displayName":338,"installMethods":418,"rationale":419,"selectedPaths":420,"source":325,"sourceLanguage":18,"type":248},"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",[421,422,423],{"path":362,"priority":322},{"path":366,"priority":364},{"path":371,"priority":369},{"basePath":425,"description":426,"displayName":427,"installMethods":428,"rationale":429,"selectedPaths":430,"source":325,"sourceLanguage":18,"type":248},"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",[431,432,434,436,438,440,442,444,446],{"path":362,"priority":322},{"path":433,"priority":369},"references/example-research.md",{"path":435,"priority":369},"references/report-template.html",{"path":437,"priority":369},"references/research-patterns.md",{"path":439,"priority":369},"references/workflow.md",{"path":441,"priority":378},"scripts/compile_report.mjs",{"path":443,"priority":378},"scripts/extract_page.mjs",{"path":445,"priority":378},"scripts/list_urls.mjs",{"path":447,"priority":378},"scripts/package.json",{"basePath":449,"description":450,"displayName":451,"installMethods":452,"rationale":453,"selectedPaths":454,"source":325,"sourceLanguage":18,"type":248},"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",[455,456,457,458,459],{"path":362,"priority":322},{"path":366,"priority":364},{"path":368,"priority":369},{"path":371,"priority":369},{"path":460,"priority":378},"scripts/cookie-sync.mjs",{"basePath":462,"description":463,"displayName":464,"installMethods":465,"rationale":466,"selectedPaths":467,"source":325,"sourceLanguage":18,"type":248},"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",[468,469,471,472,473,474,475,477,478,480,481,482],{"path":362,"priority":322},{"path":470,"priority":369},"references/event-platforms.md",{"path":433,"priority":369},{"path":435,"priority":369},{"path":437,"priority":369},{"path":439,"priority":369},{"path":476,"priority":378},"scripts/__fixtures__/stripe-snapshot.json",{"path":441,"priority":378},{"path":479,"priority":378},"scripts/extract_event.mjs",{"path":443,"priority":378},{"path":447,"priority":378},{"path":483,"priority":378},"scripts/recon.mjs",{"basePath":485,"description":486,"displayName":487,"installMethods":488,"rationale":489,"selectedPaths":490,"source":325,"sourceLanguage":18,"type":248},"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",[491,492,493,494],{"path":362,"priority":322},{"path":366,"priority":364},{"path":368,"priority":369},{"path":371,"priority":369},{"basePath":245,"description":10,"displayName":13,"installMethods":496,"rationale":497,"selectedPaths":498,"source":325,"sourceLanguage":18,"type":248},{"claudeCode":12},"SKILL.md frontmatter at skills/functions/SKILL.md",[499,500,501],{"path":362,"priority":322},{"path":366,"priority":364},{"path":371,"priority":369},{"basePath":503,"description":504,"displayName":350,"installMethods":505,"rationale":506,"selectedPaths":507,"source":325,"sourceLanguage":18,"type":248},"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",[508,509,510,512,514],{"path":362,"priority":322},{"path":366,"priority":364},{"path":511,"priority":378},"templates/claude-agent-sdk/.gitignore",{"path":513,"priority":378},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":515,"priority":378},"templates/claude-agent-sdk/package.json",{"basePath":517,"description":518,"displayName":519,"installMethods":520,"rationale":521,"selectedPaths":522,"source":325,"sourceLanguage":18,"type":248},"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",[523,524,525,526],{"path":362,"priority":322},{"path":366,"priority":364},{"path":368,"priority":369},{"path":371,"priority":369},{"basePath":528,"description":529,"displayName":530,"installMethods":531,"rationale":532,"selectedPaths":533,"source":325,"sourceLanguage":18,"type":248},"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",[534,535,536,537,538,540,542,544,546,548,550,551],{"path":362,"priority":322},{"path":324,"priority":364},{"path":366,"priority":364},{"path":368,"priority":369},{"path":539,"priority":369},"references/adversarial-patterns.md",{"path":541,"priority":369},"references/browser-recipes.md",{"path":543,"priority":369},"references/design-consistency.md",{"path":545,"priority":369},"references/design-system.example.md",{"path":547,"priority":369},"references/exploratory-testing.md",{"path":549,"priority":369},"references/parallel-testing.md",{"path":435,"priority":369},{"path":552,"priority":369},"references/ux-heuristics.md",{"basePath":258,"displayName":554,"installMethods":555,"rationale":556,"selectedPaths":557,"source":325,"sourceLanguage":18,"type":216},"browserbase-skills",{"npm":554},"cli ecosystem detected at /",[558,560],{"path":559,"priority":322},"package.json",{"path":324,"priority":322},{"sources":562},[563],"manual",{"npmPackage":554},{"closedIssues90d":8,"description":566,"forks":234,"homepage":567,"openIssues90d":236,"pushedAt":237,"readmeSize":232,"stars":238,"topics":568},"Browserbase's official collection of agent skills to access the web.","https://www.browserbase.com/SKILL.md",[],{"downloads":8},{"classifiedAt":571,"discoverAt":572,"extractAt":573,"githubAt":573,"npmAt":574,"updatedAt":571},1778683460101,1778683454817,1778683457134,1778683458753,[213,216,214,218,215,217],{"evaluatedAt":243,"extractAt":289,"updatedAt":243},[],[579,607,638,666,694,721],{"_creationTime":580,"_id":581,"community":582,"display":583,"identity":589,"providers":594,"relations":599,"tags":602,"workflow":603},1778697373439.756,"k1735p8vnc44y3ntfepns5m0nx86npbs",{"reviewCount":8},{"description":584,"installMethods":585,"name":587,"sourceUrl":588},"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":586},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":590,"githubOwner":591,"githubRepo":592,"locale":593,"slug":587,"type":248},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice","de",{"evaluate":595,"extract":598},{"promptVersionExtension":206,"promptVersionScoring":207,"score":596,"tags":597,"targetMarket":219,"tier":277},100,[213,274,276,216,297],{"commitSha":279},{"repoId":600,"translatedFrom":601},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[297,213,216,276,274],{"evaluatedAt":604,"extractAt":605,"updatedAt":606},1778697222051,1778697205743,1778697373439,{"_creationTime":608,"_id":609,"community":610,"display":611,"identity":617,"providers":622,"relations":631,"tags":634,"workflow":635},1778696691708.3274,"k170az7r02e9e2v47mpy80kx6n86nff3",{"reviewCount":8},{"description":612,"installMethods":613,"name":615,"sourceUrl":616},"Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy",{"claudeCode":614},"ruvnet/ruflo","Trader Regime","https://github.com/ruvnet/ruflo",{"basePath":618,"githubOwner":619,"githubRepo":620,"locale":18,"slug":621,"type":248},"plugins/ruflo-neural-trader/skills/trader-regime","ruvnet","ruflo","trader-regime",{"evaluate":623,"extract":629},{"promptVersionExtension":206,"promptVersionScoring":207,"score":596,"tags":624,"targetMarket":219,"tier":277},[625,626,627,628,217,216],"finance","trading","market-analysis","ai",{"commitSha":279,"license":630},"MIT",{"parentExtensionId":632,"repoId":633},"k17drge8h1fgzchr0p4jaeg33n86mwmy","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[628,216,625,627,626,217],{"evaluatedAt":636,"extractAt":637,"updatedAt":636},1778701108877,1778696691708,{"_creationTime":639,"_id":640,"community":641,"display":642,"identity":648,"providers":651,"relations":658,"tags":661,"workflow":662},1778685790658.4368,"k17d6zvh5hjzrcw35cvd9k8dgh86med7",{"reviewCount":8},{"description":643,"installMethods":644,"name":646,"sourceUrl":647},"Verwenden Sie dies beim Schreiben von Playwright-Tests, Beheben von flackernden Tests, Debuggen von Fehlern, Implementieren des Page Object Model, Konfigurieren von CI/CD, Optimieren der Leistung, Mocken von APIs, Verwalten von Authentifizierung oder OAuth, Testen der Barrierefreiheit (axe-core), Hoch- und Herunterladen von Dateien, Mocken von Datums-/Uhrzeitangaben, WebSockets, Geolokalisierung, Berechtigungen, Multi-Tab-/Popup-Flows, mobilen/responsiven Layouts, Touch-Gesten, GraphQL, Fehlerbehandlung, Offline-Modus, Multi-User-Kollaboration, Drittanbieterdiensten (Zahlungen, E-Mail-Verifizierung), Überwachung von Konsolenfehlern, globalem Setup/Teardown, Testannotationen (skip, fixme, slow), Test-Tags (@smoke, @fast, @critical, Filterung mit --grep), Projekt­abhängigkeiten, Sicherheitstests (XSS, CSRF, Auth), Leistungsbudgets (Web Vitals, Lighthouse), iFrames, Komponententests, Canvas/WebGL, Service Workers/PWA, Testabdeckung, i18n/Lokalisierung, Electron-Apps oder Tests für Browser­erweiterungen. Deckt E2E-, Komponenten-, API-, visuelle, Barrierefreiheits-, Sicherheits-, Electron- und Erweiterungstests ab.",{"claudeCode":645},"currents-dev/playwright-best-practices-skill","playwright-best-practices","https://github.com/currents-dev/playwright-best-practices-skill",{"basePath":258,"githubOwner":649,"githubRepo":650,"locale":593,"slug":650,"type":248},"currents-dev","playwright-best-practices-skill",{"evaluate":652,"extract":657},{"promptVersionExtension":206,"promptVersionScoring":207,"score":596,"tags":653,"targetMarket":219,"tier":277},[218,276,217,654,297,655,656],"e2e","debugging","ci-cd",{"commitSha":279},{"repoId":659,"translatedFrom":660},"kd77ayvtb7bpbf2cjy3n64zekd86ndw6","k17axqfsk2shpatbgra08fjtgh86neqd",[297,656,655,654,218,276,217],{"evaluatedAt":663,"extractAt":664,"updatedAt":665},1778685761971,1778685735333,1778685790658,{"_creationTime":667,"_id":668,"community":669,"display":670,"identity":676,"providers":680,"relations":686,"tags":689,"workflow":690},1778698144390.3809,"k170vj7ejwkdfswk5f34zn1da586m0xw",{"reviewCount":8},{"description":671,"installMethods":672,"name":674,"sourceUrl":675},"Automatisiert Browser-Interaktionen zum Testen und Validieren Ihrer eigenen Webanwendungen mit playwright-cli. Verwenden Sie es, wenn Sie terminalbasierte Browsersteuerung für Navigation, Formularfüllung, Screenshots, Tracing, gebundene Browser-Sitzungen, Debugging oder die Generierung von Playwright-Testcode benötigen. Verwenden Sie es nur gegen Anwendungen, die Ihnen gehören oder für deren Testung Sie ausdrücklich autorisiert sind.",{"claudeCode":673},"testdino-hq/playwright-skill","Playwright CLI","https://github.com/testdino-hq/playwright-skill",{"basePath":677,"githubOwner":678,"githubRepo":679,"locale":593,"slug":677,"type":248},"playwright-cli","testdino-hq","playwright-skill",{"evaluate":681,"extract":685},{"promptVersionExtension":206,"promptVersionScoring":207,"score":682,"tags":683,"targetMarket":219,"tier":277},99,[218,276,213,216,684],"web-development",{"commitSha":279,"license":630},{"repoId":687,"translatedFrom":688},"kd74g5bbsqgts7834bk4gzkz4n86nnsm","k1762mzcgb766pzt6dd4a01ynh86m120",[213,216,218,276,684],{"evaluatedAt":691,"extractAt":692,"updatedAt":693},1778698091403,1778698023772,1778698144390,{"_creationTime":695,"_id":696,"community":697,"display":698,"identity":704,"providers":707,"relations":712,"tags":716,"workflow":717},1778696989496.538,"k1776jcwjkmjfcm2gv94xeezz586m1tg",{"reviewCount":8},{"description":699,"installMethods":700,"name":702,"sourceUrl":703},"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":701},"SawyerHood/dev-browser","dev-browser","https://github.com/SawyerHood/dev-browser",{"basePath":705,"githubOwner":706,"githubRepo":702,"locale":593,"slug":702,"type":248},"skills/dev-browser","SawyerHood",{"evaluate":708,"extract":711},{"promptVersionExtension":206,"promptVersionScoring":207,"score":682,"tags":709,"targetMarket":219,"tier":277},[213,218,710,276,274],"javascript",{"commitSha":279},{"parentExtensionId":713,"repoId":714,"translatedFrom":715},"k172vf4sjqdwht2n7b64bmf7wn86mzzp","kd778ksdnkgy1969578mg8f30986nddw","k17535f2wgbtzrzc5n55ps9f3586mr7p",[213,710,218,276,274],{"evaluatedAt":718,"extractAt":719,"updatedAt":720},1778696938150,1778696896101,1778696989496,{"_creationTime":722,"_id":723,"community":724,"display":725,"identity":731,"providers":735,"relations":742,"tags":745,"workflow":746},1778686592196.8232,"k176r260vrpe9m02nnmzmbf2vd86n3gh",{"reviewCount":8},{"description":726,"installMethods":727,"name":729,"sourceUrl":730},"Zeichnen Sie Browser-Interaktionen als Video mit Playwright auf. Verwenden Sie dies zum Erfassen von Demovideos, App-Walkthroughs und UI-Flows für Remotion-Videos. Auslöser sind die Aufzeichnung einer Demo, die Erfassung eines Browser-Videos, die Bildschirmaufnahme einer Website oder die Erstellung von Walkthrough-Aufnahmen.",{"claudeCode":728},"digitalsamba/claude-code-video-toolkit","playwright-recording","https://github.com/digitalsamba/claude-code-video-toolkit",{"basePath":732,"githubOwner":733,"githubRepo":734,"locale":593,"slug":729,"type":248},".claude/skills/playwright-recording","digitalsamba","claude-code-video-toolkit",{"evaluate":736,"extract":741},{"promptVersionExtension":206,"promptVersionScoring":207,"score":682,"tags":737,"targetMarket":219,"tier":277},[218,738,213,276,739,740],"recording","documentation","video",{"commitSha":279},{"repoId":743,"translatedFrom":744},"kd70r97eght58pp9f1x8scdagd86n32q","k17dr9txwv0jrjjyxkm9fdf9md86m9sf",[213,739,218,738,276,740],{"evaluatedAt":747,"extractAt":748,"updatedAt":749},1778686416894,1778686219732,1778686592196]