[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-browser-trace-de":3,"guides-for-browserbase-browser-trace":576,"similar-k17fd1dhmc76frn5d1xjjc23bx86mjba-de":577},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":242,"isFallback":226,"parentExtension":248,"providers":303,"relations":308,"repo":309,"tags":574,"workflow":575},1778683460321.3816,"k17fd1dhmc76frn5d1xjjc23bx86mjba",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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},"browserbase/skills","Browser Trace","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":224,"workflow":240},1778683657573.1108,"kn7dfjf9kdcd6y5fhybk2s543h86n5nn","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"promptVersionExtension":204,"promptVersionScoring":205,"purpose":206,"rationale":207,"score":208,"summary":209,"tags":210,"targetMarket":217,"tier":218,"useCases":219},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","Description clearly names the problem of debugging browser automation failures and auditing activity.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers a specialized approach to capturing and bisecting CDP traces, going beyond basic browser automation tools.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for capturing, bisecting, and analyzing browser traces, suitable for production workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses specifically on capturing and processing browser traces, not unrelated domains like general browser automation or deployment.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The description accurately reflects the skill's capabilities and provides clear use cases and non-goals.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This is a skill, not a toolset; direct invocation is not applicable.",{"category":45,"check":46,"severity":24,"summary":47},"Documentation","Configuration & parameter reference","The SKILL.md details dependencies, environment variables, and command-line arguments with clear explanations.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","This is a skill, not a toolset; tool naming is not applicable.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","This is a skill, not a toolset; tool I/O surface is not applicable.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The MIT license is clearly defined in LICENSE.txt and is a permissive open-source license.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","Dependencies are managed via lockfiles and declared clearly, with no indications of vulnerabilities or outdated mechanisms.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill does not appear to handle or expose secrets; it operates on browser traces and metadata.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill focuses on data processing and doesn't appear to load or execute untrusted external code.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill bundles its dependencies and does not fetch external code or data at runtime.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill operates within its defined output directory and does not modify files outside of its scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","No evidence of detached processes or deny-retry loops that could indicate sandbox escape attempts.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill's purpose is trace analysis, and there are no indications of it reading or submitting confidential data.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","Bundled files do not contain hidden steering tricks or suspicious Unicode characters.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","Scripts are provided in clear, readable JavaScript (Node.js ESM) without obfuscation or runtime downloads.",{"category":92,"check":93,"severity":24,"summary":94},"Portability","Structural Assumption","The skill uses relative paths and clearly documented output directories, avoiding assumptions about user project structure.",{"category":96,"check":97,"severity":24,"summary":98},"Trust","Issues Attention","With 2 open and 0 closed issues in the last 90 days, engagement is likely high or issues are resolved quickly.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The SKILL.md frontmatter declares a license, and the repository has recent commits, implying a stable versioning approach.",{"category":104,"check":105,"severity":42,"summary":106},"Code Execution","Validation","The skill primarily orchestrates CLI tools and processes JSONL files; explicit schema validation within the skill itself is not a primary concern for its function.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill is primarily read-only for trace analysis and does not perform destructive operations.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The scripts appear to handle errors gracefully, with clear logging and fallbacks.",{"category":104,"check":114,"severity":24,"summary":115},"Logging","The skill logs actions and errors to files within the run directory, providing an audit trail.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill analyzes browser traces and does not inherently operate on personal data without sanitization.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill is a technical tool for browser tracing and has no regional or jurisdictional limitations, making it global.",{"category":92,"check":124,"severity":24,"summary":125},"Runtime stability","The skill relies on Node.js 18+ and standard command-line tools, with clear instructions for setup, ensuring cross-platform compatibility.",{"category":45,"check":127,"severity":24,"summary":128},"README","The README provides a comprehensive overview of the skills, installation, and usage, effectively stating the extension's purpose.",{"category":33,"check":130,"severity":42,"summary":131},"Tool surface size","This is a skill, not a toolset; tool surface size is not applicable.",{"category":40,"check":133,"severity":42,"summary":134},"Overlapping near-synonym tools","This is a skill, not a toolset; overlapping tool names are not applicable.",{"category":45,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features and capabilities are implemented and documented in the SKILL.md and supporting files.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","Clear installation instructions are provided in both README.md and SKILL.md, including copy-paste examples and setup checks.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","Error messages are generally clear, and troubleshooting sections provide remediation steps.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","Dependencies are managed via lockfiles and interpreter versions are declared, ensuring consistent execution.",{"category":33,"check":151,"severity":42,"summary":152},"Dry-run preview","The skill is primarily for data capture and analysis, not state-changing operations, so a dry-run feature is not applicable.",{"category":154,"check":155,"severity":42,"summary":156},"Protocol","Idempotent retry & timeouts","The skill itself doesn't make external calls that require idempotency; it orchestrates local processes.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill does not appear to emit telemetry; all data collection is local to the run directory.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The description clearly states what the skill does (capture and bisect CDP traces) and when to use it (debugging, auditing).",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The frontmatter in SKILL.md is concise and effectively summarizes the core capability and triggers.",{"category":45,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md is well-structured with detailed explanations and delegates extensive material to REFERENCE.md and EXAMPLES.md.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Detailed technical reference and examples are provided in separate files, adhering to progressive disclosure.",{"category":170,"check":174,"severity":42,"summary":175},"Forked exploration","The skill captures data and performs analysis, but does not engage in deep code review or multi-file exploration that would necessitate forked context.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The EXAMPLES.md file provides several detailed, end-to-end scenarios with setup, invocation, and analysis queries.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The troubleshooting sections and script logic address potential issues like unreachable targets, session endings, and incomplete captures.",{"category":104,"check":183,"severity":42,"summary":184},"Tool Fallback","The skill relies on the 'browse' CLI and Node.js, which are clearly specified prerequisites and not optional tools with fallbacks.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The scripts include checks for prerequisites and immediate failures are reported, halting the process.",{"category":92,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill operates independently and does not implicitly rely on other skills; its documentation cross-references other Browserbase skills when relevant.",1778683657469,"This skill captures a full DevTools Protocol (CDP) trace of browser automation sessions, including network requests, console logs, DOM dumps, and screenshots. It then bisects this data into per-page searchable buckets and provides tools for analysis. It is designed to attach to existing browser automation processes rather than drive them itself.",[195,196,197,198,199],"Capture full CDP firehose to NDJSON","Record parallel screenshots and DOM dumps","Bisect traces into per-page searchable buckets","Support for local Chrome and Browserbase remote sessions","Provide analysis scripts and query tools",[201,202,203],"Driving browser pages; this skill only listens","Replacing existing browser automation frameworks","Providing a graphical UI for trace analysis","3.0.0","4.4.0","To provide developers with a comprehensive tool for debugging and auditing browser automation runs by capturing detailed traces and making them easily searchable.","The skill is exceptionally well-documented and robust, with clear instructions, extensive examples, and strong adherence to security and best practices. No significant issues were found.",99,"A high-quality skill for capturing, bisecting, and analyzing browser traces.",[211,212,213,214,215,216],"browser-automation","debugging","tracing","cdp","developer-tools","network-analysis","global","verified",[220,221,222,223],"Debugging failed browser automation runs","Auditing network, console, and DOM activity","Attaching a trace to an in-progress browser session","Feeding structured per-page summaries into agent loops for learning",{"codeQuality":225,"collectedAt":227,"documentation":228,"maintenance":231,"popularity":237,"security":238,"testCoverage":239},{"hasLockfile":226},true,1778683633539,{"descriptionLength":229,"readmeSize":230},401,4101,{"closedIssues90d":8,"forks":232,"hasChangelog":233,"openIssues90d":234,"pushedAt":235,"stars":236},214,false,2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":226,"smitheryVerified":233},{"hasCi":233,"hasTests":233},{"updatedAt":241},1778683657573,{"basePath":243,"githubOwner":244,"githubRepo":245,"locale":18,"slug":246,"type":247},"skills/browser-trace","browserbase","skills","browser-trace","skill",{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":256,"parentExtension":259,"providers":288,"relations":299,"tags":300,"workflow":301},1778683460321.38,"k17bx77jb71yrwatep2nb43r0d86m6cb",{"reviewCount":8},{"description":253,"installMethods":254,"name":255,"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":245},"browse",{"basePath":257,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":258},"","plugin",{"_creationTime":260,"_id":261,"community":262,"display":263,"identity":266,"providers":268,"relations":282,"tags":284,"workflow":285},1778683460321.3796,"k17aawpn1wczwwhv1snb1x3q2h86m1hy",{"reviewCount":8},{"description":264,"installMethods":265,"name":244,"sourceUrl":14},"Browser automation and Browserbase CLI skills",{"claudeCode":12},{"basePath":257,"githubOwner":244,"githubRepo":245,"locale":18,"slug":245,"type":267},"marketplace",{"evaluate":269,"extract":276},{"promptVersionExtension":270,"promptVersionScoring":205,"score":271,"tags":272,"targetMarket":217,"tier":218},"3.1.0",95,[211,273,274,215,275],"cli","web-scraping","testing",{"commitSha":277,"marketplace":278,"plugin":280},"HEAD",{"name":244,"pluginCount":279},1,{"mcpCount":8,"provider":281,"skillCount":8},"classify",{"repoId":283},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[211,273,215,275,274],{"evaluatedAt":286,"extractAt":287,"updatedAt":286},1778683478405,1778683460321,{"evaluate":289,"extract":296},{"promptVersionExtension":204,"promptVersionScoring":205,"score":290,"tags":291,"targetMarket":217,"tier":218},98,[292,293,214,294,295],"browser","agent","playwright","automation",{"commitSha":277,"plugin":297},{"mcpCount":8,"provider":281,"skillCount":298},12,{"parentExtensionId":261,"repoId":283},[293,295,292,214,294],{"evaluatedAt":302,"extractAt":287,"updatedAt":302},1778683581384,{"evaluate":304,"extract":306},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":305,"targetMarket":217,"tier":218},[211,212,213,214,215,216],{"commitSha":277,"license":307},"MIT",{"parentExtensionId":250,"repoId":283},{"_creationTime":310,"_id":283,"identity":311,"providers":312,"workflow":569},1778683454816.9644,{"githubOwner":244,"githubRepo":245,"sourceUrl":14},{"classify":313,"discover":560,"extract":563,"github":564,"npm":568},{"commitSha":277,"extensions":314},[315,325,330,336,342,347,353,378,388,412,421,445,458,481,492,501,515,526,552],{"basePath":257,"description":264,"displayName":244,"installMethods":316,"rationale":317,"selectedPaths":318,"source":324,"sourceLanguage":18,"type":267},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[319,322],{"path":320,"priority":321},".claude-plugin/marketplace.json","mandatory",{"path":323,"priority":321},"README.md","rule",{"basePath":257,"description":253,"displayName":255,"installMethods":326,"rationale":327,"selectedPaths":328,"source":324,"sourceLanguage":18,"type":258},{"claudeCode":245},"inline plugin source from marketplace.json at /",[329],{"path":323,"priority":321},{"basePath":257,"description":331,"displayName":332,"installMethods":333,"rationale":327,"selectedPaths":334,"source":324,"sourceLanguage":18,"type":258},"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":245},[335],{"path":323,"priority":321},{"basePath":257,"description":337,"displayName":338,"installMethods":339,"rationale":327,"selectedPaths":340,"source":324,"sourceLanguage":18,"type":258},"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":245},[341],{"path":323,"priority":321},{"basePath":257,"description":343,"displayName":246,"installMethods":344,"rationale":327,"selectedPaths":345,"source":324,"sourceLanguage":18,"type":258},"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.",{"claudeCode":245},[346],{"path":323,"priority":321},{"basePath":257,"description":348,"displayName":349,"installMethods":350,"rationale":327,"selectedPaths":351,"source":324,"sourceLanguage":18,"type":258},"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":245},[352],{"path":323,"priority":321},{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":324,"sourceLanguage":18,"type":247},"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",[360,362,364,366,369,371,373,375],{"path":361,"priority":321},"SKILL.md",{"path":323,"priority":363},"high",{"path":365,"priority":363},"LICENSE.txt",{"path":367,"priority":368},"EXAMPLES.md","medium",{"path":370,"priority":368},"REFERENCE.md",{"path":372,"priority":368},"references/example-skill.md",{"path":374,"priority":368},"references/example-task.md",{"path":376,"priority":377},"scripts/evaluate.mjs","low",{"basePath":379,"description":380,"displayName":292,"installMethods":381,"rationale":382,"selectedPaths":383,"source":324,"sourceLanguage":18,"type":247},"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",[384,385,386,387],{"path":361,"priority":321},{"path":365,"priority":363},{"path":367,"priority":368},{"path":370,"priority":368},{"basePath":243,"description":10,"displayName":246,"installMethods":389,"rationale":390,"selectedPaths":391,"source":324,"sourceLanguage":18,"type":247},{"claudeCode":12},"SKILL.md frontmatter at skills/browser-trace/SKILL.md",[392,393,394,395,396,398,400,402,404,406,408,410],{"path":361,"priority":321},{"path":365,"priority":363},{"path":367,"priority":368},{"path":370,"priority":368},{"path":397,"priority":377},"scripts/bb-capture.mjs",{"path":399,"priority":377},"scripts/bb-finalize.mjs",{"path":401,"priority":377},"scripts/bisect-cdp.mjs",{"path":403,"priority":377},"scripts/lib.mjs",{"path":405,"priority":377},"scripts/query.mjs",{"path":407,"priority":377},"scripts/snapshot-loop.mjs",{"path":409,"priority":377},"scripts/start-capture.mjs",{"path":411,"priority":377},"scripts/stop-capture.mjs",{"basePath":413,"description":414,"displayName":338,"installMethods":415,"rationale":416,"selectedPaths":417,"source":324,"sourceLanguage":18,"type":247},"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",[418,419,420],{"path":361,"priority":321},{"path":365,"priority":363},{"path":370,"priority":368},{"basePath":422,"description":423,"displayName":424,"installMethods":425,"rationale":426,"selectedPaths":427,"source":324,"sourceLanguage":18,"type":247},"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",[428,429,431,433,435,437,439,441,443],{"path":361,"priority":321},{"path":430,"priority":368},"references/example-research.md",{"path":432,"priority":368},"references/report-template.html",{"path":434,"priority":368},"references/research-patterns.md",{"path":436,"priority":368},"references/workflow.md",{"path":438,"priority":377},"scripts/compile_report.mjs",{"path":440,"priority":377},"scripts/extract_page.mjs",{"path":442,"priority":377},"scripts/list_urls.mjs",{"path":444,"priority":377},"scripts/package.json",{"basePath":446,"description":447,"displayName":448,"installMethods":449,"rationale":450,"selectedPaths":451,"source":324,"sourceLanguage":18,"type":247},"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",[452,453,454,455,456],{"path":361,"priority":321},{"path":365,"priority":363},{"path":367,"priority":368},{"path":370,"priority":368},{"path":457,"priority":377},"scripts/cookie-sync.mjs",{"basePath":459,"description":460,"displayName":461,"installMethods":462,"rationale":463,"selectedPaths":464,"source":324,"sourceLanguage":18,"type":247},"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",[465,466,468,469,470,471,472,474,475,477,478,479],{"path":361,"priority":321},{"path":467,"priority":368},"references/event-platforms.md",{"path":430,"priority":368},{"path":432,"priority":368},{"path":434,"priority":368},{"path":436,"priority":368},{"path":473,"priority":377},"scripts/__fixtures__/stripe-snapshot.json",{"path":438,"priority":377},{"path":476,"priority":377},"scripts/extract_event.mjs",{"path":440,"priority":377},{"path":444,"priority":377},{"path":480,"priority":377},"scripts/recon.mjs",{"basePath":482,"description":483,"displayName":484,"installMethods":485,"rationale":486,"selectedPaths":487,"source":324,"sourceLanguage":18,"type":247},"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",[488,489,490,491],{"path":361,"priority":321},{"path":365,"priority":363},{"path":367,"priority":368},{"path":370,"priority":368},{"basePath":493,"description":494,"displayName":332,"installMethods":495,"rationale":496,"selectedPaths":497,"source":324,"sourceLanguage":18,"type":247},"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",[498,499,500],{"path":361,"priority":321},{"path":365,"priority":363},{"path":370,"priority":368},{"basePath":502,"description":503,"displayName":349,"installMethods":504,"rationale":505,"selectedPaths":506,"source":324,"sourceLanguage":18,"type":247},"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",[507,508,509,511,513],{"path":361,"priority":321},{"path":365,"priority":363},{"path":510,"priority":377},"templates/claude-agent-sdk/.gitignore",{"path":512,"priority":377},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":514,"priority":377},"templates/claude-agent-sdk/package.json",{"basePath":516,"description":517,"displayName":518,"installMethods":519,"rationale":520,"selectedPaths":521,"source":324,"sourceLanguage":18,"type":247},"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",[522,523,524,525],{"path":361,"priority":321},{"path":365,"priority":363},{"path":367,"priority":368},{"path":370,"priority":368},{"basePath":527,"description":528,"displayName":529,"installMethods":530,"rationale":531,"selectedPaths":532,"source":324,"sourceLanguage":18,"type":247},"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",[533,534,535,536,537,539,541,543,545,547,549,550],{"path":361,"priority":321},{"path":323,"priority":363},{"path":365,"priority":363},{"path":367,"priority":368},{"path":538,"priority":368},"references/adversarial-patterns.md",{"path":540,"priority":368},"references/browser-recipes.md",{"path":542,"priority":368},"references/design-consistency.md",{"path":544,"priority":368},"references/design-system.example.md",{"path":546,"priority":368},"references/exploratory-testing.md",{"path":548,"priority":368},"references/parallel-testing.md",{"path":432,"priority":368},{"path":551,"priority":368},"references/ux-heuristics.md",{"basePath":257,"displayName":553,"installMethods":554,"rationale":555,"selectedPaths":556,"source":324,"sourceLanguage":18,"type":273},"browserbase-skills",{"npm":553},"cli ecosystem detected at /",[557,559],{"path":558,"priority":321},"package.json",{"path":323,"priority":321},{"sources":561},[562],"manual",{"npmPackage":553},{"closedIssues90d":8,"description":565,"forks":232,"homepage":566,"openIssues90d":234,"pushedAt":235,"readmeSize":230,"stars":236,"topics":567},"Browserbase's official collection of agent skills to access the web.","https://www.browserbase.com/SKILL.md",[],{"downloads":8},{"classifiedAt":570,"discoverAt":571,"extractAt":572,"githubAt":572,"npmAt":573,"updatedAt":570},1778683460101,1778683454817,1778683457134,1778683458753,[211,214,212,215,216,213],{"evaluatedAt":241,"extractAt":287,"updatedAt":241},[],[578,607,637,667,693,720],{"_creationTime":579,"_id":580,"community":581,"display":582,"identity":588,"providers":593,"relations":599,"tags":602,"workflow":603},1778699368519.5344,"k17ab0jk30pqm4zejpk383w4dn86mj8t",{"reviewCount":8},{"description":583,"installMethods":584,"name":586,"sourceUrl":587},"Verwenden Sie dies, wenn die Arbeit von den Live-Browsersitzungs- oder gerenderten Zustand des Benutzers abhängt und nicht von statischen Abrufen, insbesondere für Browser-Debugging-Kontexte oder von DevTools ausgewählte Elemente oder Anfragen, angemeldeten Dashboards oder CMS-Flows, localhost-Apps, Formularen, Uploads, Downloads, Medieninspektion, DOM- oder iframe-Inspektion, Shadow DOM oder Browserfehlern, die wie Soft-404s, Authentifizierungswände, Anti-Bot-Prüfungen oder Ratenbegrenzungen aussehen.",{"claudeCode":585},"xixu-me/skills","Use My Browser","https://github.com/xixu-me/skills",{"basePath":589,"githubOwner":590,"githubRepo":245,"locale":591,"slug":592,"type":247},"skills/use-my-browser","xixu-me","de","use-my-browser",{"evaluate":594,"extract":598},{"promptVersionExtension":204,"promptVersionScoring":205,"score":595,"tags":596,"targetMarket":217,"tier":218},100,[292,212,295,597,215],"ux",{"commitSha":277,"license":307},{"repoId":600,"translatedFrom":601},"kd77r2vb42jmgam0qbr9f2c6kn86mebv","k179cgk616p3xva37r5jqsfwvh86mcp2",[295,292,212,215,597],{"evaluatedAt":604,"extractAt":605,"updatedAt":606},1778699261239,1778699106670,1778699368519,{"_creationTime":608,"_id":609,"community":610,"display":611,"identity":617,"providers":621,"relations":628,"tags":632,"workflow":633},1778693776323.6208,"k17d4tp9kh6k4rf7s1rzzw5b6s86m492",{"reviewCount":8},{"description":612,"installMethods":613,"name":615,"sourceUrl":616},"Führt Diagnosen für den Kontextmodus aus. Überprüft Laufzeiten, Hooks, FTS5,\nPlugin-Registrierung sowie npm- und Marktplatzversionen.\nAuslöser: /context-mode:ctx-doctor\n",{"claudeCode":614},"mksglu/context-mode","ctx-doctor","https://github.com/mksglu/context-mode",{"basePath":618,"githubOwner":619,"githubRepo":620,"locale":591,"slug":615,"type":247},"skills/ctx-doctor","mksglu","context-mode",{"evaluate":622,"extract":627},{"promptVersionExtension":204,"promptVersionScoring":205,"score":595,"tags":623,"targetMarket":217,"tier":218},[624,215,625,212,626],"context-management","productivity","diagnostics",{"commitSha":277},{"parentExtensionId":629,"repoId":630,"translatedFrom":631},"k17ezy748es7sfnbnp9phht43h86m53y","kd764b2fctbqg4b8j8y6xvmkvs86m29m","k17dre81ghdhwnja4h61m340qd86m942",[624,212,215,626,625],{"evaluatedAt":634,"extractAt":635,"updatedAt":636},1778693603549,1778693511416,1778693776323,{"_creationTime":638,"_id":639,"community":640,"display":641,"identity":647,"providers":652,"relations":660,"tags":663,"workflow":664},1778695116697.1929,"k176f565j7tyetjxk9sgbjcqp186ndk5",{"reviewCount":8},{"description":642,"installMethods":643,"name":645,"sourceUrl":646},"LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.",{"claudeCode":644},"Orchestra-Research/AI-Research-SKILLs","LangSmith Observability","https://github.com/Orchestra-Research/AI-Research-SKILLs",{"basePath":648,"githubOwner":649,"githubRepo":650,"locale":18,"slug":651,"type":247},"17-observability/langsmith","Orchestra-Research","AI-Research-SKILLs","langsmith",{"evaluate":653,"extract":659},{"promptVersionExtension":204,"promptVersionScoring":205,"score":208,"tags":654,"targetMarket":217,"tier":218},[655,651,213,656,657,658,212,275],"observability","evaluation","monitoring","llmops",{"commitSha":277,"license":307},{"parentExtensionId":661,"repoId":662},"k17155ws9qc0hw7a568bg79sfd86max8","kd70hj1y80mhra5xm5g188j5n586mg18",[212,656,651,658,657,655,275,213],{"evaluatedAt":665,"extractAt":666,"updatedAt":665},1778697046926,1778695116697,{"_creationTime":668,"_id":669,"community":670,"display":671,"identity":677,"providers":681,"relations":685,"tags":688,"workflow":689},1778697373439.756,"k1735p8vnc44y3ntfepns5m0nx86npbs",{"reviewCount":8},{"description":672,"installMethods":673,"name":675,"sourceUrl":676},"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":674},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":678,"githubOwner":679,"githubRepo":680,"locale":591,"slug":675,"type":247},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":682,"extract":684},{"promptVersionExtension":204,"promptVersionScoring":205,"score":595,"tags":683,"targetMarket":217,"tier":218},[211,274,275,273,295],{"commitSha":277},{"repoId":686,"translatedFrom":687},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[295,211,273,275,274],{"evaluatedAt":690,"extractAt":691,"updatedAt":692},1778697222051,1778697205743,1778697373439,{"_creationTime":694,"_id":695,"community":696,"display":697,"identity":703,"providers":707,"relations":714,"tags":716,"workflow":717},1778696993586.7058,"k174ty9vbfgj7cv3v2szdwjgh986mrsf",{"reviewCount":8},{"description":698,"installMethods":699,"name":701,"sourceUrl":702},"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":700},"SeifBenayed/claude-code-sdk","chatgpt-search","https://github.com/SeifBenayed/claude-code-sdk",{"basePath":704,"githubOwner":705,"githubRepo":706,"locale":18,"slug":701,"type":247},".claude/skills/chatgpt-search","SeifBenayed","claude-code-sdk",{"evaluate":708,"extract":713},{"promptVersionExtension":204,"promptVersionScoring":205,"score":595,"tags":709,"targetMarket":217,"tier":218},[710,711,211,712,274],"chatgpt","scraping","data-extraction",{"commitSha":277},{"repoId":715},"kd78s53c1852h5p7c3qem663xs86njab",[211,710,712,711,274],{"evaluatedAt":718,"extractAt":719,"updatedAt":718},1778697026743,1778696993586,{"_creationTime":721,"_id":722,"community":723,"display":724,"identity":730,"providers":734,"relations":741,"tags":743,"workflow":744},1778688417731.9568,"k174wzq7pzgctyr9y4yakmzsjn86mwk9",{"reviewCount":8},{"description":725,"installMethods":726,"name":728,"sourceUrl":729},"Safari browser automation CLI on macOS via safari-mcp. Controls real Safari (native, keeps logins) by wrapping the safari-mcp MCP server. Every one of the 84 MCP tools is exposed 1:1 with schema-accurate arguments — guaranteed parity, no manual drift.",{"claudeCode":727},"hkuds/cli-anything","cli-anything-safari","https://github.com/hkuds/cli-anything",{"basePath":731,"githubOwner":732,"githubRepo":733,"locale":18,"slug":728,"type":247},"skills/cli-anything-safari","hkuds","cli-anything",{"evaluate":735,"extract":740},{"promptVersionExtension":204,"promptVersionScoring":205,"score":595,"tags":736,"targetMarket":217,"tier":218},[737,738,211,273,739],"safari","macos","mcp",{"commitSha":277},{"repoId":742},"kd7e2bra4ymb6r521a25r6yges86n35p",[211,273,738,739,737],{"evaluatedAt":745,"extractAt":746,"updatedAt":745},1778689594971,1778688417732]