[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-safe-browser-zh-CN":3,"guides-for-browserbase-safe-browser":584,"similar-k1778nak5hc8b0f1v34mcmqsxd86mh6n-zh-CN":585},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":251,"isFallback":235,"parentExtension":256,"providers":311,"relations":316,"repo":317,"tags":582,"workflow":583},1778683460321.3833,"k1778nak5hc8b0f1v34mcmqsxd86mh6n",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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},"browserbase/skills","safe-browser","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":233,"workflow":249},1778683843366.5845,"kn72vteqkax6qe6hz5xxgbb9gh86mg3d","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":204,"prerequisites":205,"promptVersionExtension":208,"promptVersionScoring":209,"purpose":210,"rationale":211,"score":212,"summary":213,"tags":214,"targetMarket":220,"tier":221,"useCases":222,"workflow":227},[21,26,29,33,37,41,45,48,52,56,60,63,66,69,73,76,79,82,85,88,92,96,99,103,106,109,112,115,118,121,125,128,132,136,140,143,147,150,154,157,160,163,166,169,172,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Invocation","Precise Purpose","pass","The skill's purpose is precisely defined, stating it builds local constrained-browser agents using a safe_browser tool with CDP, domain allowlisting, and an agent SDK. It clearly outlines when to use it for staying on approved domains or demonstrating containment, and implicitly avoids general browsing.",{"category":22,"check":27,"severity":24,"summary":28},"Concise Frontmatter","The frontmatter is concise and directly states the core capability: building local constrained-browser agents with a safe_browser tool, and provides clear use cases and boundaries.",{"category":30,"check":31,"severity":24,"summary":32},"Documentation","Concise Body","The SKILL.md body is concise and delegates the detailed template setup to separate files, adhering to progressive disclosure.",{"category":34,"check":35,"severity":24,"summary":36},"Context","Progressive Disclosure","The skill.md outlines the main flow and correctly references the template code in separate files, without embedding large amounts of material inline.",{"category":34,"check":38,"severity":39,"summary":40},"Forked exploration","not_applicable","This skill is a builder guide for a demo agent, not a deep exploration or code review tool, so forked exploration is not applicable.",{"category":42,"check":43,"severity":24,"summary":44},"Practical Utility","Usage examples","The README and SKILL.md provide a clear, end-to-end example script demonstrating the intended usage, including setup and verification steps.",{"category":42,"check":46,"severity":24,"summary":47},"Edge cases","The SKILL.md addresses edge cases and limitations, such as handling missing Chromium, demonstrating CDP block decisions, and specifying recovery steps for navigation failures.",{"category":49,"check":50,"severity":39,"summary":51},"Code Execution","Tool Fallback","The skill directly uses the Claude Agent SDK and Playwright, and does not rely on an external MCP server, making this check not applicable.",{"category":53,"check":54,"severity":24,"summary":55},"Safety","Halt on unexpected state","The example script includes assertions and error handling, ensuring that unexpected states (like failed navigations or missing extractions) halt the workflow with clear reporting.",{"category":57,"check":58,"severity":24,"summary":59},"Portability","Cross-skill coupling","The skill is self-contained and does not rely on other skills being loaded; its functionality is distinct and clearly defined.",{"category":42,"check":61,"severity":24,"summary":62},"Problem relevance","The description clearly states the problem of building constrained-browser agents that must stay on approved domains, addressing a specific user need for controlled web scraping and browsing.",{"category":42,"check":64,"severity":24,"summary":65},"Unique selling proposition","The skill uniquely offers a constrained browser agent builder with CDP Fetch interception for domain allowlisting, providing more control than a standard browser or web scraping tool.",{"category":42,"check":67,"severity":24,"summary":68},"Production readiness","The skill provides a complete lifecycle for building and demonstrating a constrained browser agent, including setup, execution, verification, and artifact generation.",{"category":70,"check":71,"severity":24,"summary":72},"Scope","Single responsibility principle","The skill focuses solely on building and demonstrating a constrained browser agent with specific browser capabilities, adhering to a single responsibility.",{"category":70,"check":74,"severity":24,"summary":75},"Description quality","The displayed description accurately reflects the skill's functionality: building local constrained-browser agents with domain allowlist enforcement via a safe_browser tool.",{"category":22,"check":77,"severity":24,"summary":78},"Scoped tools","The skill exposes narrow, verb-noun specific tools like `goto`, `extract_front_page`, and `audit_log`, avoiding a single generalist tool.",{"category":30,"check":80,"severity":24,"summary":81},"Configuration & parameter reference","Parameters like `SAFE_BROWSER_HEADLESS` and tool parameters like `url` and `limit` are documented within the SKILL.md and tool definitions, with default values implied or explicit.",{"category":70,"check":83,"severity":24,"summary":84},"Tool naming","All exposed tools (`goto`, `extract_front_page`, etc.) are descriptive, verb-noun pairs that clearly indicate their function within the domain.",{"category":70,"check":86,"severity":24,"summary":87},"Minimal I/O surface","Tool inputs (`url`, `limit`) are specific to the task, and outputs provide structured data relevant to the requested action, avoiding diagnostic dumps.",{"category":89,"check":90,"severity":24,"summary":91},"License","License usability","The extension is licensed under the MIT license, which is permissive and widely usable, as confirmed by the LICENSE.txt file.",{"category":93,"check":94,"severity":24,"summary":95},"Maintenance","Commit recency","The latest commit was on 2026-05-13, indicating recent maintenance.",{"category":93,"check":97,"severity":24,"summary":98},"Dependency Management","The `package.json` lists dependencies and Playwright includes Chromium, suggesting managed dependencies.",{"category":100,"check":101,"severity":24,"summary":102},"Security","Secret Management","The skill requires ANTHROPIC_API_KEY but uses environment variables for it, and the example script demonstrates loading it from a local .env file, which is appropriate.",{"category":100,"check":104,"severity":24,"summary":105},"Injection","The code treats fetched URLs and user inputs as data, and the `safe_browser` tool enforces domain restrictions, preventing script injection.",{"category":100,"check":107,"severity":24,"summary":108},"Transitive Supply-Chain Grenades","The skill uses vendored dependencies (Playwright, Agent SDK) and does not fetch remote code or markdown for execution.",{"category":100,"check":110,"severity":24,"summary":111},"Sandbox Isolation","The skill operates within the NodeJS environment and Playwright's sandboxing; it does not attempt to write outside its designated artifacts directory or project folder.",{"category":100,"check":113,"severity":24,"summary":114},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls are present in the provided scripts.",{"category":100,"check":116,"severity":24,"summary":117},"Data Exfiltration","The skill does not appear to exfiltrate confidential data; API keys are handled via environment variables, and outbound calls are restricted by the `safe_browser` tool.",{"category":100,"check":119,"severity":24,"summary":120},"Hidden Text Tricks","The bundled markdown and script files do not contain hidden steering tricks, invisible characters, or malformed HTML comments.",{"category":122,"check":123,"severity":24,"summary":124},"Hooks","Opaque code execution","The bundled scripts are plain Javascript and are not obfuscated, base64-encoded, or dynamically fetched for execution.",{"category":57,"check":126,"severity":24,"summary":127},"Structural Assumption","The example script uses relative paths for artifact generation and `.env` file loading, avoiding assumptions about user project structure.",{"category":129,"check":130,"severity":24,"summary":131},"Trust","Issues Attention","With 2 open and 0 closed issues in the last 90 days, the closure rate is indeterminate but the low number of open issues suggests good attention.",{"category":133,"check":134,"severity":24,"summary":135},"Versioning","Release Management","The skill has a `version` field in its `package.json` and SKILL.md frontmatter, and dependencies are managed, indicating clear versioning practices.",{"category":137,"check":138,"severity":24,"summary":139},"Execution","Validation","Input validation is present for tool parameters (e.g., URL format, limit range via Zod) and the example script uses assertions to validate outcomes.",{"category":100,"check":141,"severity":24,"summary":142},"Unguarded Destructive Operations","The skill primarily performs read-only operations related to browsing and extraction; destructive operations are not present.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Error Handling","The example script includes error handling for navigation, extraction, and assertions, with informative messages and non-zero exits on failure.",{"category":49,"check":148,"severity":24,"summary":149},"Logging","The example script writes detailed audit logs, tool logs, and CDP command logs to an artifacts directory, providing a clear record of actions.",{"category":151,"check":152,"severity":24,"summary":153},"Compliance","GDPR","The skill does not operate on personal data; it scrapes public web content, and any potential personal data encountered would be handled within the agent's context.",{"category":151,"check":155,"severity":24,"summary":156},"Target market","The extension is designed for general web browsing and scraping tasks and does not exhibit any regional or jurisdictional limitations.",{"category":57,"check":158,"severity":24,"summary":159},"Runtime stability","The skill uses standard Node.js and Playwright, which are cross-platform, and the setup instructions for Chromium installation are provided.",{"category":30,"check":161,"severity":24,"summary":162},"README","The README provides a comprehensive overview of the Browserbase skills, including installation, usage, and troubleshooting, clearly stating the purpose of each skill.",{"category":70,"check":164,"severity":24,"summary":165},"Tool surface size","The skill exposes 5 well-defined tools, which falls within the ideal range of 3-10 tools.",{"category":22,"check":167,"severity":24,"summary":168},"Overlapping near-synonym tools","The exposed tools (`goto`, `extract_front_page`, `extract_comments`, `current_url`, `audit_log`) are distinct and do not have overlapping, near-synonym names.",{"category":30,"check":170,"severity":24,"summary":171},"Phantom features","All advertised features, such as the safe_browser tool and its CDP capabilities, are implemented and demonstrated in the example script.",{"category":173,"check":174,"severity":24,"summary":175},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions for both npx and Claude Code, along with usage examples.",{"category":144,"check":177,"severity":24,"summary":178},"Actionable error messages","Error messages in the example script are specific, indicate the cause (e.g., missing URL, blocked request), and provide context for remediation.",{"category":137,"check":180,"severity":24,"summary":181},"Pinned dependencies","The `package.json` pins dependencies like `@anthropic-ai/claude-agent-sdk` and `playwright`, and Playwright manages its own browser binaries.",{"category":70,"check":183,"severity":39,"summary":184},"Dry-run preview","The skill's primary function is browsing and data extraction, which are not state-changing operations requiring a dry-run preview.",{"category":186,"check":187,"severity":24,"summary":188},"Protocol","Idempotent retry & timeouts","While not strictly state-changing operations, the navigation actions include timeouts, and the audit log allows for retry analysis if needed.",{"category":151,"check":190,"severity":24,"summary":191},"Telemetry opt-in","The skill does not appear to emit any telemetry; environment variables are used for configuration, and no opt-in/out mechanisms are present.",1778683843242,"This skill provides the tools and guidance to build local browser agents using the Claude Agent SDK. It leverages a `safe_browser` tool that controls CDP sessions, enforces domain allowlists, and restricts agent capabilities to prevent unauthorized browsing or data access.",[195,196,197,198,199],"Builds local constrained-browser agents","Enforces domain allowlist with CDP Fetch interception","Provides a `safe_browser` tool with restricted capabilities","Includes example for Hacker News scraping with security checks","Generates audit logs and artifacts for verification",[201,202,203],"Providing a general-purpose browser automation tool","Allowing agents raw browser, shell, or CDP access","Supporting off-domain navigation or arbitrary web requests",[],[206,207],"Node.js installed","Chromium browser installed (or will be installed via Playwright)","3.0.0","4.4.0","To enable users to build and demonstrate browser agents that operate within strict domain boundaries, ensuring safety and control during web browsing and scraping tasks.","The skill has a perfect score across all checks, demonstrating high quality in documentation, security, and practical utility.",99,"A high-quality skill for building constrained browser agents with robust security and clear documentation.",[215,216,217,218,219],"browser","agent-sdk","scraping","automation","cdp","global","verified",[223,224,225,226],"Browsing or scraping while staying on approved domains","Demonstrating prompt-injection or link-following containment","Building scrapers or browser workflows with domain policy","Generating a Claude Agent SDK example for browser tasks",[228,229,230,231,232],"Copy the local template and set up the environment.","Run the provided Node.js script (`hn-scraper-demo.mjs`).","Observe the agent interacting with the `safe_browser` tool.","Verify browser navigation stays within the allowlist.","Review generated artifacts (audit log, screenshots) for proof of concept.",{"codeQuality":234,"collectedAt":236,"documentation":237,"maintenance":240,"popularity":246,"security":247,"testCoverage":248},{"hasLockfile":235},true,1778683809281,{"descriptionLength":238,"readmeSize":239},399,4101,{"closedIssues90d":8,"forks":241,"hasChangelog":242,"openIssues90d":243,"pushedAt":244,"stars":245},214,false,2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":235,"smitheryVerified":242},{"hasCi":242,"hasTests":242},{"updatedAt":250},1778683843366,{"basePath":252,"githubOwner":253,"githubRepo":254,"locale":18,"slug":13,"type":255},"skills/safe-browser","browserbase","skills","skill",{"_creationTime":257,"_id":258,"community":259,"display":260,"identity":264,"parentExtension":267,"providers":298,"relations":307,"tags":308,"workflow":309},1778683460321.38,"k17bx77jb71yrwatep2nb43r0d86m6cb",{"reviewCount":8},{"description":261,"installMethods":262,"name":263,"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":254},"browse",{"basePath":265,"githubOwner":253,"githubRepo":254,"locale":18,"slug":254,"type":266},"","plugin",{"_creationTime":268,"_id":269,"community":270,"display":271,"identity":274,"providers":276,"relations":292,"tags":294,"workflow":295},1778683460321.3796,"k17aawpn1wczwwhv1snb1x3q2h86m1hy",{"reviewCount":8},{"description":272,"installMethods":273,"name":253,"sourceUrl":14},"Browser automation and Browserbase CLI skills",{"claudeCode":12},{"basePath":265,"githubOwner":253,"githubRepo":254,"locale":18,"slug":254,"type":275},"marketplace",{"evaluate":277,"extract":286},{"promptVersionExtension":278,"promptVersionScoring":209,"score":279,"tags":280,"targetMarket":220,"tier":221},"3.1.0",95,[281,282,283,284,285],"browser-automation","cli","web-scraping","developer-tools","testing",{"commitSha":287,"marketplace":288,"plugin":290},"HEAD",{"name":253,"pluginCount":289},1,{"mcpCount":8,"provider":291,"skillCount":8},"classify",{"repoId":293},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[281,282,284,285,283],{"evaluatedAt":296,"extractAt":297,"updatedAt":296},1778683478405,1778683460321,{"evaluate":299,"extract":304},{"promptVersionExtension":208,"promptVersionScoring":209,"score":300,"tags":301,"targetMarket":220,"tier":221},98,[215,302,219,303,218],"agent","playwright",{"commitSha":287,"plugin":305},{"mcpCount":8,"provider":291,"skillCount":306},12,{"parentExtensionId":269,"repoId":293},[302,218,215,219,303],{"evaluatedAt":310,"extractAt":297,"updatedAt":310},1778683581384,{"evaluate":312,"extract":314},{"promptVersionExtension":208,"promptVersionScoring":209,"score":212,"tags":313,"targetMarket":220,"tier":221},[215,216,217,218,219],{"commitSha":287,"license":315},"MIT",{"parentExtensionId":258,"repoId":293},{"_creationTime":318,"_id":293,"identity":319,"providers":320,"workflow":577},1778683454816.9644,{"githubOwner":253,"githubRepo":254,"sourceUrl":14},{"classify":321,"discover":568,"extract":571,"github":572,"npm":576},{"commitSha":287,"extensions":322},[323,333,338,344,350,356,361,386,396,422,431,455,468,491,502,511,523,534,560],{"basePath":265,"description":272,"displayName":253,"installMethods":324,"rationale":325,"selectedPaths":326,"source":332,"sourceLanguage":18,"type":275},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[327,330],{"path":328,"priority":329},".claude-plugin/marketplace.json","mandatory",{"path":331,"priority":329},"README.md","rule",{"basePath":265,"description":261,"displayName":263,"installMethods":334,"rationale":335,"selectedPaths":336,"source":332,"sourceLanguage":18,"type":266},{"claudeCode":254},"inline plugin source from marketplace.json at /",[337],{"path":331,"priority":329},{"basePath":265,"description":339,"displayName":340,"installMethods":341,"rationale":335,"selectedPaths":342,"source":332,"sourceLanguage":18,"type":266},"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":254},[343],{"path":331,"priority":329},{"basePath":265,"description":345,"displayName":346,"installMethods":347,"rationale":335,"selectedPaths":348,"source":332,"sourceLanguage":18,"type":266},"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":254},[349],{"path":331,"priority":329},{"basePath":265,"description":351,"displayName":352,"installMethods":353,"rationale":335,"selectedPaths":354,"source":332,"sourceLanguage":18,"type":266},"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":254},[355],{"path":331,"priority":329},{"basePath":265,"description":357,"displayName":13,"installMethods":358,"rationale":335,"selectedPaths":359,"source":332,"sourceLanguage":18,"type":266},"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.",{"claudeCode":254},[360],{"path":331,"priority":329},{"basePath":362,"description":363,"displayName":364,"installMethods":365,"rationale":366,"selectedPaths":367,"source":332,"sourceLanguage":18,"type":255},"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",[368,370,372,374,377,379,381,383],{"path":369,"priority":329},"SKILL.md",{"path":331,"priority":371},"high",{"path":373,"priority":371},"LICENSE.txt",{"path":375,"priority":376},"EXAMPLES.md","medium",{"path":378,"priority":376},"REFERENCE.md",{"path":380,"priority":376},"references/example-skill.md",{"path":382,"priority":376},"references/example-task.md",{"path":384,"priority":385},"scripts/evaluate.mjs","low",{"basePath":387,"description":388,"displayName":215,"installMethods":389,"rationale":390,"selectedPaths":391,"source":332,"sourceLanguage":18,"type":255},"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",[392,393,394,395],{"path":369,"priority":329},{"path":373,"priority":371},{"path":375,"priority":376},{"path":378,"priority":376},{"basePath":397,"description":398,"displayName":352,"installMethods":399,"rationale":400,"selectedPaths":401,"source":332,"sourceLanguage":18,"type":255},"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",[402,403,404,405,406,408,410,412,414,416,418,420],{"path":369,"priority":329},{"path":373,"priority":371},{"path":375,"priority":376},{"path":378,"priority":376},{"path":407,"priority":385},"scripts/bb-capture.mjs",{"path":409,"priority":385},"scripts/bb-finalize.mjs",{"path":411,"priority":385},"scripts/bisect-cdp.mjs",{"path":413,"priority":385},"scripts/lib.mjs",{"path":415,"priority":385},"scripts/query.mjs",{"path":417,"priority":385},"scripts/snapshot-loop.mjs",{"path":419,"priority":385},"scripts/start-capture.mjs",{"path":421,"priority":385},"scripts/stop-capture.mjs",{"basePath":423,"description":424,"displayName":346,"installMethods":425,"rationale":426,"selectedPaths":427,"source":332,"sourceLanguage":18,"type":255},"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",[428,429,430],{"path":369,"priority":329},{"path":373,"priority":371},{"path":378,"priority":376},{"basePath":432,"description":433,"displayName":434,"installMethods":435,"rationale":436,"selectedPaths":437,"source":332,"sourceLanguage":18,"type":255},"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",[438,439,441,443,445,447,449,451,453],{"path":369,"priority":329},{"path":440,"priority":376},"references/example-research.md",{"path":442,"priority":376},"references/report-template.html",{"path":444,"priority":376},"references/research-patterns.md",{"path":446,"priority":376},"references/workflow.md",{"path":448,"priority":385},"scripts/compile_report.mjs",{"path":450,"priority":385},"scripts/extract_page.mjs",{"path":452,"priority":385},"scripts/list_urls.mjs",{"path":454,"priority":385},"scripts/package.json",{"basePath":456,"description":457,"displayName":458,"installMethods":459,"rationale":460,"selectedPaths":461,"source":332,"sourceLanguage":18,"type":255},"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",[462,463,464,465,466],{"path":369,"priority":329},{"path":373,"priority":371},{"path":375,"priority":376},{"path":378,"priority":376},{"path":467,"priority":385},"scripts/cookie-sync.mjs",{"basePath":469,"description":470,"displayName":471,"installMethods":472,"rationale":473,"selectedPaths":474,"source":332,"sourceLanguage":18,"type":255},"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",[475,476,478,479,480,481,482,484,485,487,488,489],{"path":369,"priority":329},{"path":477,"priority":376},"references/event-platforms.md",{"path":440,"priority":376},{"path":442,"priority":376},{"path":444,"priority":376},{"path":446,"priority":376},{"path":483,"priority":385},"scripts/__fixtures__/stripe-snapshot.json",{"path":448,"priority":385},{"path":486,"priority":385},"scripts/extract_event.mjs",{"path":450,"priority":385},{"path":454,"priority":385},{"path":490,"priority":385},"scripts/recon.mjs",{"basePath":492,"description":493,"displayName":494,"installMethods":495,"rationale":496,"selectedPaths":497,"source":332,"sourceLanguage":18,"type":255},"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",[498,499,500,501],{"path":369,"priority":329},{"path":373,"priority":371},{"path":375,"priority":376},{"path":378,"priority":376},{"basePath":503,"description":504,"displayName":340,"installMethods":505,"rationale":506,"selectedPaths":507,"source":332,"sourceLanguage":18,"type":255},"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",[508,509,510],{"path":369,"priority":329},{"path":373,"priority":371},{"path":378,"priority":376},{"basePath":252,"description":10,"displayName":13,"installMethods":512,"rationale":513,"selectedPaths":514,"source":332,"sourceLanguage":18,"type":255},{"claudeCode":12},"SKILL.md frontmatter at skills/safe-browser/SKILL.md",[515,516,517,519,521],{"path":369,"priority":329},{"path":373,"priority":371},{"path":518,"priority":385},"templates/claude-agent-sdk/.gitignore",{"path":520,"priority":385},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":522,"priority":385},"templates/claude-agent-sdk/package.json",{"basePath":524,"description":525,"displayName":526,"installMethods":527,"rationale":528,"selectedPaths":529,"source":332,"sourceLanguage":18,"type":255},"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",[530,531,532,533],{"path":369,"priority":329},{"path":373,"priority":371},{"path":375,"priority":376},{"path":378,"priority":376},{"basePath":535,"description":536,"displayName":537,"installMethods":538,"rationale":539,"selectedPaths":540,"source":332,"sourceLanguage":18,"type":255},"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",[541,542,543,544,545,547,549,551,553,555,557,558],{"path":369,"priority":329},{"path":331,"priority":371},{"path":373,"priority":371},{"path":375,"priority":376},{"path":546,"priority":376},"references/adversarial-patterns.md",{"path":548,"priority":376},"references/browser-recipes.md",{"path":550,"priority":376},"references/design-consistency.md",{"path":552,"priority":376},"references/design-system.example.md",{"path":554,"priority":376},"references/exploratory-testing.md",{"path":556,"priority":376},"references/parallel-testing.md",{"path":442,"priority":376},{"path":559,"priority":376},"references/ux-heuristics.md",{"basePath":265,"displayName":561,"installMethods":562,"rationale":563,"selectedPaths":564,"source":332,"sourceLanguage":18,"type":282},"browserbase-skills",{"npm":561},"cli ecosystem detected at /",[565,567],{"path":566,"priority":329},"package.json",{"path":331,"priority":329},{"sources":569},[570],"manual",{"npmPackage":561},{"closedIssues90d":8,"description":573,"forks":241,"homepage":574,"openIssues90d":243,"pushedAt":244,"readmeSize":239,"stars":245,"topics":575},"Browserbase's official collection of agent skills to access the web.","https://www.browserbase.com/SKILL.md",[],{"downloads":8},{"classifiedAt":578,"discoverAt":579,"extractAt":580,"githubAt":580,"npmAt":581,"updatedAt":578},1778683460101,1778683454817,1778683457134,1778683458753,[216,218,215,219,217],{"evaluatedAt":250,"extractAt":297,"updatedAt":250},[],[586,616,641,672,700,722],{"_creationTime":587,"_id":588,"community":589,"display":590,"identity":596,"providers":601,"relations":608,"tags":611,"workflow":612},1778699366078.7817,"k173mj3k9wcdq512bp1532xkwx86nrh4",{"reviewCount":8},{"description":591,"installMethods":592,"name":594,"sourceUrl":595},"当工作依赖于用户实时浏览器会话或可见的渲染状态，而不是静态抓取时使用，尤其是在浏览器调试上下文或 DevTools 选择的元素或请求、登录仪表板或 CMS 流程、localhost 应用、上传、下载、媒体检查、DOM 或 iframe 检查、Shadow DOM，或看起来像软 404、身份验证墙、反机器人检查或速率限制的浏览器故障时。",{"claudeCode":593},"xixu-me/skills","使用我的浏览器","https://github.com/xixu-me/skills",{"basePath":597,"githubOwner":598,"githubRepo":254,"locale":599,"slug":600,"type":255},"skills/use-my-browser","xixu-me","zh-CN","use-my-browser",{"evaluate":602,"extract":607},{"promptVersionExtension":208,"promptVersionScoring":209,"score":603,"tags":604,"targetMarket":220,"tier":221},100,[215,605,218,606,284],"debugging","ux",{"commitSha":287,"license":315},{"repoId":609,"translatedFrom":610},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[218,215,605,284,606],{"evaluatedAt":613,"extractAt":614,"updatedAt":615},1778699261239,1778699106670,1778699366078,{"_creationTime":617,"_id":618,"community":619,"display":620,"identity":626,"providers":629,"relations":635,"tags":637,"workflow":638},1778687183932.1946,"k174dcbhpv61bq493drtep8shd86md4e",{"reviewCount":8},{"description":621,"installMethods":622,"name":624,"sourceUrl":625},"Codify the most recent successful /scrape flow into a permanent\nbrowser-skill on disk. Future /scrape calls with the same intent run\nthe codified script in ~200ms instead of re-driving the page. Walks\nback through the conversation, synthesizes script.ts + script.test.ts\n+ fixture, runs the test in a temp dir, and asks before committing.\nUse when asked to \"skillify\", \"codify\", \"save this scrape\", or\n\"make this permanent\". (gstack)\n",{"claudeCode":623},"garrytan/gstack","skillify","https://github.com/garrytan/gstack",{"basePath":624,"githubOwner":627,"githubRepo":628,"locale":18,"slug":624,"type":255},"garrytan","gstack",{"evaluate":630,"extract":634},{"promptVersionExtension":208,"promptVersionScoring":209,"score":631,"tags":632,"targetMarket":220,"tier":221},97,[218,215,217,633,285],"code-generation",{"commitSha":287},{"repoId":636},"kd73s35xh97m9mmc5nz3pb1f3n86m0an",[218,215,633,217,285],{"evaluatedAt":639,"extractAt":640,"updatedAt":639},1778688452847,1778687183932,{"_creationTime":642,"_id":643,"community":644,"display":645,"identity":651,"providers":656,"relations":665,"tags":668,"workflow":669},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":646,"installMethods":647,"name":649,"sourceUrl":650},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":648},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":652,"githubOwner":653,"githubRepo":654,"locale":18,"slug":655,"type":255},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":657,"extract":664},{"promptVersionExtension":208,"promptVersionScoring":209,"score":603,"tags":658,"targetMarket":220,"tier":221},[659,660,661,662,218,282,663],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":287,"license":315},{"parentExtensionId":666,"repoId":667},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[218,282,663,660,659,662,661],{"evaluatedAt":670,"extractAt":671,"updatedAt":670},1778699613343,1778699234184,{"_creationTime":673,"_id":674,"community":675,"display":676,"identity":682,"providers":684,"relations":692,"tags":695,"workflow":696},1778699505679.3464,"k1751nm85mw95gw3rsqgrdqspx86ncq2",{"reviewCount":8},{"description":677,"installMethods":678,"name":680,"sourceUrl":681},"无需 OAuth 即可创建公开的 Google Docs 或 Google Sheet 文件。使用此技能创建和编辑 Google Docs 和 Sheets，无需登录 Google。文档可通过共享链接查看。首次使用时自动注册。",{"claudeCode":679},"zagmoai/public-google-drive","public-google-drive","https://github.com/zagmoai/public-google-drive",{"basePath":265,"githubOwner":683,"githubRepo":680,"locale":599,"slug":680,"type":255},"zagmoai",{"evaluate":685,"extract":691},{"promptVersionExtension":208,"promptVersionScoring":209,"score":603,"tags":686,"targetMarket":220,"tier":221},[687,688,689,218,690],"google-docs","google-sheets","productivity","api-client",{"commitSha":287},{"repoId":693,"translatedFrom":694},"kd776ynh73t0d6samn4bnxdf3x86n8mj","k1707pszx7h026a651dp5tvaxd86m3ag",[690,218,687,688,689],{"evaluatedAt":697,"extractAt":698,"updatedAt":699},1778699485884,1778699468747,1778699505679,{"_creationTime":701,"_id":702,"community":703,"display":704,"identity":707,"providers":710,"relations":718,"tags":719,"workflow":720},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":705,"installMethods":706,"name":654,"sourceUrl":650},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":648},{"basePath":708,"githubOwner":653,"githubRepo":654,"locale":18,"slug":709,"type":255},"skills/ask","ask",{"evaluate":711,"extract":717},{"promptVersionExtension":208,"promptVersionScoring":209,"score":603,"tags":712,"targetMarket":220,"tier":221},[282,218,713,714,715,716],"llm","prompting","code-review","artifact-generation",{"commitSha":287,"license":315},{"parentExtensionId":666,"repoId":667},[716,218,282,715,713,714],{"evaluatedAt":721,"extractAt":671,"updatedAt":721},1778699303045,{"_creationTime":723,"_id":724,"community":725,"display":726,"identity":732,"providers":735,"relations":745,"tags":749,"workflow":750},1778699289329.1182,"k172jykxz0jywjekjxjt5thj5x86nm3n",{"reviewCount":8},{"description":727,"installMethods":728,"name":730,"sourceUrl":731},"当用户需要通过 Xquik 获取 X (Twitter) 数据或执行需要确认的 X 操作时使用：推文搜索、用户查找、关注者提取、媒体下载、监控、Webhook、MCP、SDK、发布、点赞、私信和个人资料更新。需要 Xquik API 密钥。切勿索要 X 登录凭据。",{"claudeCode":729},"Xquik-dev/x-twitter-scraper","x-twitter-scraper","https://github.com/Xquik-dev/x-twitter-scraper",{"basePath":733,"githubOwner":734,"githubRepo":730,"locale":599,"slug":730,"type":255},"skills/x-twitter-scraper","Xquik-dev",{"evaluate":736,"extract":744},{"promptVersionExtension":208,"promptVersionScoring":209,"score":603,"tags":737,"targetMarket":220,"tier":221},[738,739,740,741,218,742,743],"twitter","x","api","data-retrieval","mcp","sdk",{"commitSha":287},{"parentExtensionId":746,"repoId":747,"translatedFrom":748},"k17axvhmvwp90strpqcd5b0h7986m80d","kd783enpnwhry153ka0z65ear186mjbh","k172e8vt4zcz50bb0vfp6ptb1n86mf90",[740,218,741,742,743,738,739],{"evaluatedAt":751,"extractAt":752,"updatedAt":753},1778699230863,1778699170774,1778699289329]