[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-ui-test-zh-CN":3,"guides-for-browserbase-ui-test":577,"similar-k17dn7zcf77stm2nh1701tbywh86nc09-zh-CN":578},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":227,"parentExtension":249,"providers":305,"relations":309,"repo":310,"tags":575,"workflow":576},1778683460321.3838,"k17dn7zcf77stm2nh1701tbywh86nc09",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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).",{"claudeCode":12},"browserbase/skills","ui-test","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":242},1778683891525.7566,"kn77vsqy44xjw841c63p1xtwzd86nhyh","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":202,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,43,48,52,55,59,63,66,70,73,76,79,82,85,88,92,96,100,104,108,111,115,118,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly states the problem of 'adversarial UI testing' and specifies use cases like testing UI changes, QAing pull requests, and auditing accessibility.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value beyond default LLM behavior by implementing a structured, adversarial testing methodology and integrating with a browser CLI for real browser interaction and assertion, which is not a thin wrapper.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill provides a complete lifecycle for UI testing, from diff analysis to execution and reporting, with clear instructions and necessary tools.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses solely on UI testing using the browse CLI, with clear workflows for diff-driven, exploratory, and parallel testing, without extending into unrelated domains.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The provided description accurately and concisely reflects the skill's capabilities, use cases, and supported modes of operation.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill primarily uses the `browse` CLI, which acts as a tool with specific commands, adhering to a verb-noun structure for its operations.",{"category":44,"check":45,"severity":46,"summary":47},"Documentation","Configuration & parameter reference","info","The SKILL.md mentions `BROWSERBASE_API_KEY` for remote testing but does not explicitly detail its scope or how to verify its validity, and other configuration parameters like ports are implied rather than documented.",{"category":33,"check":49,"severity":50,"summary":51},"Tool naming","not_applicable","This skill primarily uses an external CLI tool (`browse`) rather than exposing its own distinct tools with custom names.",{"category":33,"check":53,"severity":24,"summary":54},"Minimal I/O surface","The `browse` CLI commands are specific, and the skill's usage of them focuses on necessary parameters for testing actions and assertions.",{"category":56,"check":57,"severity":24,"summary":58},"License","License usability","The MIT license is clearly provided in a dedicated LICENSE.txt file, which is a permissive open-source license.",{"category":60,"check":61,"severity":24,"summary":62},"Maintenance","Commit recency","The repository shows recent commits, indicating active maintenance.",{"category":60,"check":64,"severity":24,"summary":65},"Dependency Management","The `package.json` likely has dependencies managed, and the installation instructions suggest using `npm` or `npx`, implying standard package management practices.",{"category":67,"check":68,"severity":24,"summary":69},"Security","Secret Management","The skill does not appear to handle or expose secrets directly; it relies on an external API key for Browserbase which is managed via environment variables and is not echoed in output.",{"category":67,"check":71,"severity":24,"summary":72},"Injection","The skill uses the `browse` CLI with specific commands and parameters, and the SKILL.md emphasizes treating content as data, with clear instructions on assertion protocols.",{"category":67,"check":74,"severity":24,"summary":75},"Transitive Supply-Chain Grenades","The skill relies on the `browse` CLI and loads external scripts like axe-core via CDN, but these are standard, well-vetted libraries and the SKILL.md indicates how to manage them, not executing arbitrary remote code.",{"category":67,"check":77,"severity":24,"summary":78},"Sandbox Isolation","The skill operates within the `browse` CLI's sandbox environment and does not attempt to write files outside of designated context directories.",{"category":67,"check":80,"severity":24,"summary":81},"Sandbox escape primitives","No detached-process spawns or deny-retry loops were observed in the provided documentation or SKILL.md.",{"category":67,"check":83,"severity":24,"summary":84},"Data Exfiltration","The skill's primary function is UI testing and reporting; it does not instruct the agent to read or submit confidential data to third parties.",{"category":67,"check":86,"severity":24,"summary":87},"Hidden Text Tricks","The bundled files and documentation appear to be free of hidden steering tricks, control characters, or obfuscated content.",{"category":89,"check":90,"severity":24,"summary":91},"Hooks","Opaque code execution","The skill uses plain JavaScript and shell commands, with no evidence of obfuscation, base64 payloads, or runtime script fetching.",{"category":93,"check":94,"severity":24,"summary":95},"Portability","Structural Assumption","The skill makes minimal assumptions about project structure, primarily relying on the `browse` CLI and standard Git commands, and clearly states prerequisites.",{"category":97,"check":98,"severity":24,"summary":99},"Trust","Issues Attention","With 2 open and 0 closed issues in the last 90 days, the closure rate is technically undefined but the low volume of open issues suggests active or manageable attention.",{"category":101,"check":102,"severity":24,"summary":103},"Version","Release Management","The SKILL.md frontmatter declares a meaningful semver version ('0.4.0').",{"category":105,"check":106,"severity":24,"summary":107},"Execution","Validation","The skill relies on the `browse` CLI's inherent validation, and the SKILL.md emphasizes structured assertion protocols, implying validated inputs and outputs.",{"category":67,"check":109,"severity":24,"summary":110},"Unguarded Destructive Operations","The skill is focused on testing and reporting; it does not perform destructive operations like file deletion or system configuration changes.",{"category":112,"check":113,"severity":24,"summary":114},"Code Execution","Error Handling","The skill's documentation outlines clear reporting for test failures (`STEP_FAIL`) and provides guidance on handling browser command errors, promoting structured error reporting.",{"category":112,"check":116,"severity":50,"summary":117},"Logging","The skill's primary output is structured test results and an HTML report; it does not require or implement a separate local audit log for destructive actions.",{"category":119,"check":120,"severity":24,"summary":121},"Compliance","GDPR","The skill is focused on UI testing and does not operate on personal data; it relies on the user providing application URLs and potentially cookies for authenticated sessions.",{"category":119,"check":123,"severity":24,"summary":124},"Target market","The extension is designed for testing web applications and has no regional or jurisdictional limitations, making it globally applicable.",{"category":93,"check":126,"severity":24,"summary":127},"Runtime stability","The skill depends on the `browse` CLI and standard Node.js/npm for installation, which are broadly compatible across POSIX-like environments.",{"category":44,"check":129,"severity":24,"summary":130},"README","The README file is present and clearly states the extension's purpose, installation, and usage.",{"category":33,"check":132,"severity":50,"summary":133},"Tool surface size","This skill primarily interfaces with the `browse` CLI and does not expose multiple distinct tools or commands of its own.",{"category":40,"check":135,"severity":50,"summary":136},"Overlapping near-synonym tools","The skill primarily utilizes the `browse` CLI commands and does not expose multiple overlapping commands.",{"category":44,"check":138,"severity":24,"summary":139},"Phantom features","All advertised features, such as diff-driven testing, exploratory testing, and HTML report generation, are supported by clear documentation and examples.",{"category":141,"check":142,"severity":24,"summary":143},"Install","Installation instruction","The README provides clear installation instructions (`npx skills add`) and usage examples for all main workflows.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The documentation clearly describes failure reporting (`STEP_FAIL` markers) and troubleshooting for common issues with the `browse` CLI.",{"category":105,"check":149,"severity":24,"summary":150},"Pinned dependencies","The extension is installed via `npm`/`npx` which typically handles dependency pinning, and the `browse` CLI itself manages its dependencies.",{"category":33,"check":152,"severity":24,"summary":153},"Dry-run preview","The core functionality involves interacting with a browser and observing results; there are no inherently destructive operations that would require a dry-run mode.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","The skill leverages the `browse` CLI, which handles browser interactions and timeouts, and the testing methodology emphasizes clear assertions rather than retries of mutating operations.",{"category":119,"check":159,"severity":24,"summary":160},"Telemetry opt-in","The skill does not appear to emit any telemetry by default; it focuses on test execution and reporting.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly states the skill is for 'AI-powered adversarial UI testing' and outlines specific use cases like testing UI changes, QAing pull requests, and exploratory testing, with clear boundaries.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The SKILL.md frontmatter is concise and effectively summarizes the skill's purpose and triggers.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md is well-structured, providing detailed workflows and protocols, and delegates deeper material to reference files.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md clearly outlines core workflows and delegates detailed patterns and recipes to separate markdown files in the `references/` directory.",{"category":171,"check":175,"severity":50,"summary":176},"Forked exploration","The skill is designed for structured testing and exploration rather than deep code analysis that would require a forked context.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The EXAMPLES.md file provides numerous detailed, end-to-end examples covering various workflows and scenarios with exact commands and expected outputs.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The documentation and examples address numerous edge cases and adversarial patterns for forms, modals, navigation, and browser behavior.",{"category":112,"check":184,"severity":50,"summary":185},"Tool Fallback","The skill primarily uses the `browse` CLI and does not rely on optional external MCP servers or tools with fallbacks.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill emphasizes clear assertion protocols and reporting of `STEP_FAIL` for unexpected states, and the documentation instructs agents to stop on errors.",{"category":93,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill is self-contained, focusing on UI testing via the `browse` CLI, and does not implicitly rely on other skills.",1778683891420,"This skill enables AI-powered adversarial UI testing via the browse CLI. It supports analyzing git diffs to test only changed code, exploring the full application to find bugs, and running tests in parallel. It covers functional correctness, accessibility, responsive layout, and UX heuristics, supporting both local browser testing and remote Browserbase testing.",[196,197,198,199,200,201],"Diff-driven UI testing","Exploratory UI testing","Parallel testing with Browserbase","Accessibility audits (axe-core, keyboard nav)","Responsive and visual quality checks","Generates shareable HTML reports with embedded screenshots",[203,204,205],"Automated unit or integration testing of backend logic.","Performance load testing.","End-to-end test suite generation (focuses on exploratory/adversarial).","3.0.0","4.4.0","To help developers and QA teams find bugs and ensure UI quality by automating adversarial testing in real browsers.","The skill is exceptionally well-documented with clear examples and uses best practices for browser automation and adversarial testing. Minor info on configuration documentation and no explicit logging mechanism were noted.",97,"A comprehensive and well-executed skill for adversarial UI testing using a real browser.",[213,214,215,216,217],"ui-testing","browser-automation","qa","accessibility","testing","global","verified",[221,222,223,224],"Test UI changes in a pull request.","Audit website accessibility and compliance.","Perform exploratory testing to find unexpected bugs.","Verify functional correctness and UX heuristics.",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"popularity":239,"security":240,"testCoverage":241},{"hasLockfile":227},true,1778683866334,{"descriptionLength":230,"readmeSize":231},408,4101,{"closedIssues90d":8,"forks":233,"hasChangelog":234,"manifestVersion":235,"openIssues90d":236,"pushedAt":237,"stars":238},214,false,"0.4.0",2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":227,"smitheryVerified":234},{"hasCi":234,"hasTests":234},{"updatedAt":243},1778683891525,{"basePath":245,"githubOwner":246,"githubRepo":247,"locale":18,"slug":13,"type":248},"skills/ui-test","browserbase","skills","skill",{"_creationTime":250,"_id":251,"community":252,"display":253,"identity":257,"parentExtension":260,"providers":289,"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":283,"tags":285,"workflow":286},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":277},{"promptVersionExtension":271,"promptVersionScoring":207,"score":272,"tags":273,"targetMarket":218,"tier":219},"3.1.0",95,[214,274,275,276,217],"cli","web-scraping","developer-tools",{"commitSha":278,"marketplace":279,"plugin":281},"HEAD",{"name":246,"pluginCount":280},1,{"mcpCount":8,"provider":282,"skillCount":8},"classify",{"repoId":284},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[214,274,276,217,275],{"evaluatedAt":287,"extractAt":288,"updatedAt":287},1778683478405,1778683460321,{"evaluate":290,"extract":298},{"promptVersionExtension":206,"promptVersionScoring":207,"score":291,"tags":292,"targetMarket":218,"tier":219},98,[293,294,295,296,297],"browser","agent","cdp","playwright","automation",{"commitSha":278,"plugin":299},{"mcpCount":8,"provider":282,"skillCount":300},12,{"parentExtensionId":262,"repoId":284},[294,297,293,295,296],{"evaluatedAt":304,"extractAt":288,"updatedAt":304},1778683581384,{"evaluate":306,"extract":308},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":307,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":278},{"parentExtensionId":251,"repoId":284},{"_creationTime":311,"_id":284,"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":278,"extensions":315},[316,326,331,337,343,349,355,380,390,416,425,449,462,485,496,505,519,530,553],{"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":333,"installMethods":334,"rationale":328,"selectedPaths":335,"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.","functions",{"claudeCode":247},[336],{"path":324,"priority":322},{"basePath":258,"description":338,"displayName":339,"installMethods":340,"rationale":328,"selectedPaths":341,"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},[342],{"path":324,"priority":322},{"basePath":258,"description":344,"displayName":345,"installMethods":346,"rationale":328,"selectedPaths":347,"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},[348],{"path":324,"priority":322},{"basePath":258,"description":350,"displayName":351,"installMethods":352,"rationale":328,"selectedPaths":353,"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},[354],{"path":324,"priority":322},{"basePath":356,"description":357,"displayName":358,"installMethods":359,"rationale":360,"selectedPaths":361,"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",[362,364,366,368,371,373,375,377],{"path":363,"priority":322},"SKILL.md",{"path":324,"priority":365},"high",{"path":367,"priority":365},"LICENSE.txt",{"path":369,"priority":370},"EXAMPLES.md","medium",{"path":372,"priority":370},"REFERENCE.md",{"path":374,"priority":370},"references/example-skill.md",{"path":376,"priority":370},"references/example-task.md",{"path":378,"priority":379},"scripts/evaluate.mjs","low",{"basePath":381,"description":382,"displayName":293,"installMethods":383,"rationale":384,"selectedPaths":385,"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",[386,387,388,389],{"path":363,"priority":322},{"path":367,"priority":365},{"path":369,"priority":370},{"path":372,"priority":370},{"basePath":391,"description":392,"displayName":345,"installMethods":393,"rationale":394,"selectedPaths":395,"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",[396,397,398,399,400,402,404,406,408,410,412,414],{"path":363,"priority":322},{"path":367,"priority":365},{"path":369,"priority":370},{"path":372,"priority":370},{"path":401,"priority":379},"scripts/bb-capture.mjs",{"path":403,"priority":379},"scripts/bb-finalize.mjs",{"path":405,"priority":379},"scripts/bisect-cdp.mjs",{"path":407,"priority":379},"scripts/lib.mjs",{"path":409,"priority":379},"scripts/query.mjs",{"path":411,"priority":379},"scripts/snapshot-loop.mjs",{"path":413,"priority":379},"scripts/start-capture.mjs",{"path":415,"priority":379},"scripts/stop-capture.mjs",{"basePath":417,"description":418,"displayName":339,"installMethods":419,"rationale":420,"selectedPaths":421,"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",[422,423,424],{"path":363,"priority":322},{"path":367,"priority":365},{"path":372,"priority":370},{"basePath":426,"description":427,"displayName":428,"installMethods":429,"rationale":430,"selectedPaths":431,"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",[432,433,435,437,439,441,443,445,447],{"path":363,"priority":322},{"path":434,"priority":370},"references/example-research.md",{"path":436,"priority":370},"references/report-template.html",{"path":438,"priority":370},"references/research-patterns.md",{"path":440,"priority":370},"references/workflow.md",{"path":442,"priority":379},"scripts/compile_report.mjs",{"path":444,"priority":379},"scripts/extract_page.mjs",{"path":446,"priority":379},"scripts/list_urls.mjs",{"path":448,"priority":379},"scripts/package.json",{"basePath":450,"description":451,"displayName":452,"installMethods":453,"rationale":454,"selectedPaths":455,"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",[456,457,458,459,460],{"path":363,"priority":322},{"path":367,"priority":365},{"path":369,"priority":370},{"path":372,"priority":370},{"path":461,"priority":379},"scripts/cookie-sync.mjs",{"basePath":463,"description":464,"displayName":465,"installMethods":466,"rationale":467,"selectedPaths":468,"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",[469,470,472,473,474,475,476,478,479,481,482,483],{"path":363,"priority":322},{"path":471,"priority":370},"references/event-platforms.md",{"path":434,"priority":370},{"path":436,"priority":370},{"path":438,"priority":370},{"path":440,"priority":370},{"path":477,"priority":379},"scripts/__fixtures__/stripe-snapshot.json",{"path":442,"priority":379},{"path":480,"priority":379},"scripts/extract_event.mjs",{"path":444,"priority":379},{"path":448,"priority":379},{"path":484,"priority":379},"scripts/recon.mjs",{"basePath":486,"description":487,"displayName":488,"installMethods":489,"rationale":490,"selectedPaths":491,"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",[492,493,494,495],{"path":363,"priority":322},{"path":367,"priority":365},{"path":369,"priority":370},{"path":372,"priority":370},{"basePath":497,"description":498,"displayName":333,"installMethods":499,"rationale":500,"selectedPaths":501,"source":325,"sourceLanguage":18,"type":248},"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",[502,503,504],{"path":363,"priority":322},{"path":367,"priority":365},{"path":372,"priority":370},{"basePath":506,"description":507,"displayName":351,"installMethods":508,"rationale":509,"selectedPaths":510,"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",[511,512,513,515,517],{"path":363,"priority":322},{"path":367,"priority":365},{"path":514,"priority":379},"templates/claude-agent-sdk/.gitignore",{"path":516,"priority":379},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":518,"priority":379},"templates/claude-agent-sdk/package.json",{"basePath":520,"description":521,"displayName":522,"installMethods":523,"rationale":524,"selectedPaths":525,"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",[526,527,528,529],{"path":363,"priority":322},{"path":367,"priority":365},{"path":369,"priority":370},{"path":372,"priority":370},{"basePath":245,"description":10,"displayName":13,"installMethods":531,"rationale":532,"selectedPaths":533,"source":325,"sourceLanguage":18,"type":248},{"claudeCode":12},"SKILL.md frontmatter at skills/ui-test/SKILL.md",[534,535,536,537,538,540,542,544,546,548,550,551],{"path":363,"priority":322},{"path":324,"priority":365},{"path":367,"priority":365},{"path":369,"priority":370},{"path":539,"priority":370},"references/adversarial-patterns.md",{"path":541,"priority":370},"references/browser-recipes.md",{"path":543,"priority":370},"references/design-consistency.md",{"path":545,"priority":370},"references/design-system.example.md",{"path":547,"priority":370},"references/exploratory-testing.md",{"path":549,"priority":370},"references/parallel-testing.md",{"path":436,"priority":370},{"path":552,"priority":370},"references/ux-heuristics.md",{"basePath":258,"displayName":554,"installMethods":555,"rationale":556,"selectedPaths":557,"source":325,"sourceLanguage":18,"type":274},"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":233,"homepage":567,"openIssues90d":236,"pushedAt":237,"readmeSize":231,"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,[216,214,215,217,213],{"evaluatedAt":243,"extractAt":288,"updatedAt":243},[],[579,607,626,651,682,709],{"_creationTime":580,"_id":581,"community":582,"display":583,"identity":589,"providers":594,"relations":599,"tags":602,"workflow":603},1778697369634.8499,"k17333g8dacqsmw8kk79h77vmx86n0d1",{"reviewCount":8},{"description":584,"installMethods":585,"name":587,"sourceUrl":588},"AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用，包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。",{"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","zh-CN",{"evaluate":595,"extract":598},{"promptVersionExtension":206,"promptVersionScoring":207,"score":596,"tags":597,"targetMarket":218,"tier":219},100,[214,275,217,274,297],{"commitSha":278},{"repoId":600,"translatedFrom":601},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[297,214,274,217,275],{"evaluatedAt":604,"extractAt":605,"updatedAt":606},1778697222051,1778697205743,1778697369634,{"_creationTime":608,"_id":609,"community":610,"display":611,"identity":614,"providers":615,"relations":622,"tags":623,"workflow":624},1778683460321.381,"k1707rtzme0qezretvp3gmtfvn86n1k1",{"reviewCount":8},{"description":357,"installMethods":612,"name":613,"sourceUrl":14},{"claudeCode":12},"AutoBrowse",{"basePath":356,"githubOwner":246,"githubRepo":247,"locale":18,"slug":358,"type":248},{"evaluate":616,"extract":620},{"promptVersionExtension":206,"promptVersionScoring":207,"score":596,"tags":617,"targetMarket":218,"tier":219},[214,275,618,217,619],"llm-agent","node-js",{"commitSha":278,"license":621},"MIT",{"parentExtensionId":251,"repoId":284},[214,618,619,217,275],{"evaluatedAt":625,"extractAt":288,"updatedAt":625},1778683610531,{"_creationTime":627,"_id":628,"community":629,"display":630,"identity":636,"providers":640,"relations":645,"tags":647,"workflow":648},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":631,"installMethods":632,"name":634,"sourceUrl":635},"Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.",{"claudeCode":633},"steipete/clawdis","telegram-crabbox-e2e-proof","https://github.com/steipete/clawdis",{"basePath":637,"githubOwner":638,"githubRepo":639,"locale":18,"slug":634,"type":248},".agents/skills/telegram-crabbox-e2e-proof","steipete","clawdis",{"evaluate":641,"extract":644},{"promptVersionExtension":206,"promptVersionScoring":207,"score":596,"tags":642,"targetMarket":218,"tier":219},[217,643,297,215,274],"telegram",{"commitSha":278},{"repoId":646},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[297,274,215,643,217],{"evaluatedAt":649,"extractAt":650,"updatedAt":649},1778698038113,1778697652123,{"_creationTime":652,"_id":653,"community":654,"display":655,"identity":661,"providers":664,"relations":674,"tags":677,"workflow":678},1778695613089.784,"k17346gw32t4gahnqgf0q1stgd86n92z",{"reviewCount":8},{"description":656,"installMethods":657,"name":659,"sourceUrl":660},"使用此技能直接从 Claude Code 查询您的 Google NotebookLM 笔记本，以获取来自 Gemini 的、有来源依据且附带引用的答案。浏览器自动化、库管理、持久化身份验证。通过仅文档响应，极大地减少了幻觉。",{"claudeCode":658},"PleasePrompto/notebooklm-skill","NotebookLM 技能","https://github.com/PleasePrompto/notebooklm-skill",{"basePath":258,"githubOwner":662,"githubRepo":663,"locale":593,"slug":663,"type":248},"PleasePrompto","notebooklm-skill",{"evaluate":665,"extract":673},{"promptVersionExtension":206,"promptVersionScoring":207,"score":666,"tags":667,"targetMarket":218,"tier":219},99,[668,669,670,671,215,214,672],"notebooklm","google","documentation","research","python",{"commitSha":278,"license":621},{"repoId":675,"translatedFrom":676},"kd77gpjgrb75m8vdz999898gfx86nmyk","k17a2m4gyjvxe0gagyj92v85b986mdw8",[214,670,669,668,672,215,671],{"evaluatedAt":679,"extractAt":680,"updatedAt":681},1778695578542,1778695552536,1778695613089,{"_creationTime":683,"_id":684,"community":685,"display":686,"identity":692,"providers":697,"relations":702,"tags":705,"workflow":706},1778686640222.7986,"k173npg49t3qa1x72jhc9vqadn86mvsq",{"reviewCount":8},{"description":687,"installMethods":688,"name":690,"sourceUrl":691},"Run browser tests on pages affected by current PR or branch",{"claudeCode":689},"EveryInc/compound-engineering-plugin","Compound Engineering Browser Test","https://github.com/EveryInc/compound-engineering-plugin",{"basePath":693,"githubOwner":694,"githubRepo":695,"locale":18,"slug":696,"type":248},"plugins/compound-engineering/skills/ce-test-browser","EveryInc","compound-engineering-plugin","ce-test-browser",{"evaluate":698,"extract":701},{"promptVersionExtension":206,"promptVersionScoring":207,"score":666,"tags":699,"targetMarket":218,"tier":219},[217,214,274,215,700],"ci",{"commitSha":278,"license":621},{"parentExtensionId":703,"repoId":704},"k17d893df4em0e3pn8f55h1dxn86n09e","kd7e40my1b5g70tg0f60qg85ch86nn08",[214,700,274,215,217],{"evaluatedAt":707,"extractAt":708,"updatedAt":707},1778687496344,1778686640222,{"_creationTime":710,"_id":711,"community":712,"display":713,"identity":719,"providers":723,"relations":730,"tags":733,"workflow":734},1778699018122.7856,"k170rwpkqsz8b50gnytayw5zj986maex",{"reviewCount":8},{"description":714,"installMethods":715,"name":717,"sourceUrl":718},"Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.",{"claudeCode":716},"wshobson/agents","screen-reader-testing","https://github.com/wshobson/agents",{"basePath":720,"githubOwner":721,"githubRepo":722,"locale":18,"slug":717,"type":248},"plugins/accessibility-compliance/skills/screen-reader-testing","wshobson","agents",{"evaluate":724,"extract":729},{"promptVersionExtension":206,"promptVersionScoring":207,"score":291,"tags":725,"targetMarket":218,"tier":219},[216,726,727,728,215],"web-testing","screen-reader","a11y",{"commitSha":278},{"parentExtensionId":731,"repoId":732},"k172w4j8rxzh1f0hc5qhwye5xx86msks","kd74de64zj0axtg5b8t7eqqe2x86nske",[728,216,215,727,726],{"evaluatedAt":735,"extractAt":736,"updatedAt":735},1778700360545,1778699018122]