[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-autobrowse-de":3,"guides-for-browserbase-autobrowse":595,"similar-k1707rtzme0qezretvp3gmtfvn86n1k1-de":596},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":261,"isFallback":245,"parentExtension":267,"providers":322,"relations":327,"repo":328,"tags":593,"workflow":594},1778683460321.381,"k1707rtzme0qezretvp3gmtfvn86n1k1",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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.",{"claudeCode":12},"browserbase/skills","AutoBrowse","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":243,"workflow":259},1778683610531.5461,"kn7908h5ms5d1h1hbvc9fpjkkh86nht1","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"practices":206,"prerequisites":210,"promptVersionExtension":215,"promptVersionScoring":216,"purpose":217,"rationale":218,"score":219,"summary":220,"tags":221,"targetMarket":227,"tier":228,"useCases":229,"workflow":234},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,99,103,107,110,114,117,122,125,128,131,134,137,140,144,148,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly identifies the problem of building reliable browser automation skills and specifies the target user intent: improving navigation skills for specific website tasks.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The auto-research loop, iterative improvement of strategy.md, and support for parallel runs with sub-agents offer significant value beyond a simple prompt, indicating a unique capability.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension appears production-ready, covering the complete lifecycle from task definition to graduated skill, with clear instructions and environment modes.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses on iterative browser automation and skill improvement, with a clear domain and no unrelated capabilities.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The provided description accurately reflects the extension's self-improving browser automation capabilities and use cases.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The `execute` tool takes a specific `command` string, which is then parsed and executed safely, preventing arbitrary command execution.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The `evaluate.mjs` script and SKILL.md clearly document all relevant flags, environment variables, and command usage.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The primary tool (`execute`) and its associated commands (`browse ...`) are descriptive and follow a consistent pattern.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The `execute` tool's input schema is a single command string, and the output is text, adhering to a minimal I/O surface.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is licensed under the MIT License, as indicated by the LICENSE.txt file.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The repository shows recent commits as of May 13, 2026, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and has a `package-lock.json` (implied by `npm install` and `hasLockfile: true`), indicating managed dependencies.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","Secrets are expected to be managed via environment variables (ANTHROPIC_API_KEY, BROWSERBASE_API_KEY) and are not hardcoded or exposed in logs.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The `executeCommand` function strictly limits execution to the `browse` command and parses arguments directly, preventing shell injection.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension executes local commands via `execFileSync` and does not fetch remote code or data at runtime.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The `executeCommand` function limits execution to the `browse` CLI, which operates within its own sandboxed environment, and all paths are relative.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","The code uses `execFileSync` and does not appear to spawn detached processes or employ retry loops around denied tool calls.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension's primary function is browser automation, and it does not appear to have logic for exfiltrating confidential data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The bundled code and documentation do not contain hidden text tricks, invisible characters, or malicious HTML comments.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The `evaluate.mjs` script is plain JavaScript and does not use obfuscation, base64 payloads, or runtime code fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill manages its workspace relative to the current directory and uses relative paths for artifacts, avoiding assumptions about fixed project structures.",{"category":95,"check":96,"severity":97,"summary":98},"Trust","Issues Attention","info","With 2 issues opened and 0 closed in the last 90 days, maintainer responsiveness on issues is currently not demonstrable.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The repository includes versioning information and a recent commit date, with no obvious versioning issues.",{"category":104,"check":105,"severity":24,"summary":106},"Execution","Validation","The `parseCommand` function performs basic validation on the command string, ensuring it starts with `browse` and handling quoting/escaping.",{"category":65,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The extension's core function is browser automation, not destructive operations like file deletion or infra changes, and it operates within the `browse` CLI's sandbox.",{"category":111,"check":112,"severity":24,"summary":113},"Code Execution","Error Handling","The `evaluateCommand` function includes try-catch blocks for `execFileSync` and reports errors clearly, exiting non-zero on critical failures.",{"category":111,"check":115,"severity":24,"summary":116},"Logging","The script logs execution details to stderr and writes a detailed trace to disk, allowing users to review actions.",{"category":118,"check":119,"severity":120,"summary":121},"Compliance","GDPR","not_applicable","The extension is a browser automation tool and does not appear to operate on personal data directly.",{"category":118,"check":123,"severity":24,"summary":124},"Target market","The extension is a general-purpose browser automation tool with no specific regional or jurisdictional limitations, thus `targetMarket` is global.",{"category":91,"check":126,"severity":24,"summary":127},"Runtime stability","The script declares Node.js 18+ in SKILL.md and uses standard Node.js APIs, ensuring multi-platform compatibility.",{"category":44,"check":129,"severity":24,"summary":130},"README","The README provides a clear overview of the extension's purpose, how it works, requirements, setup, and usage.",{"category":33,"check":132,"severity":24,"summary":133},"Tool surface size","The skill primarily exposes the `execute` tool, which then interfaces with the `browse` CLI commands, keeping the primary tool surface small.",{"category":40,"check":135,"severity":24,"summary":136},"Overlapping near-synonym tools","The primary interface is the `execute` tool, which calls specific `browse` commands, avoiding near-synonym redundancy.",{"category":44,"check":138,"severity":24,"summary":139},"Phantom features","All advertised features, such as iterative improvement and parallel runs, are implemented and described in the documentation.",{"category":141,"check":142,"severity":24,"summary":143},"Install","Installation instruction","The README provides clear installation instructions for Node.js, npm, the browse CLI, and API key setup.",{"category":145,"check":146,"severity":24,"summary":147},"Errors","Actionable error messages","The script provides clear error messages for missing API keys, tasks, and command execution failures, with guidance on how to resolve them.",{"category":104,"check":149,"severity":24,"summary":150},"Pinned dependencies","The project uses npm and has a lockfile (`hasLockfile: true`), indicating pinned dependencies.",{"category":33,"check":152,"severity":120,"summary":153},"Dry-run preview","The extension is focused on browser automation and does not perform state-changing operations that would typically require a dry-run preview.",{"category":155,"check":156,"severity":24,"summary":157},"Protocol","Idempotent retry & timeouts","The `evaluateCommand` function enforces a hard timeout for `execFileSync` and returns structured errors, and the browse CLI commands are generally idempotent within a session.",{"category":118,"check":159,"severity":24,"summary":160},"Telemetry opt-in","The extension does not appear to emit telemetry by default; any data collection would be via the underlying Anthropic API usage.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The description clearly states the purpose of self-improving browser automation and its use case for building reliable navigation skills.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The SKILL.md frontmatter is concise and effectively summarizes the core capability and usage instructions.",{"category":44,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md content is well-structured, uses progressive disclosure, and delegates complex material to separate files.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md and README appropriately link to references and examples, avoiding inline bloat.",{"category":171,"check":175,"severity":120,"summary":176},"Forked exploration","This skill is designed for iterative improvement and does not involve deep code review or exploration that would require `context: fork`.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","The README and EXAMPLES.md provide clear, ready-to-use examples for various scenarios, including single tasks, parallel runs, and remote environments.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md and references document failure modes, recovery steps, and specific gotchas for different websites and scenarios.",{"category":111,"check":184,"severity":24,"summary":185},"Tool Fallback","The skill uses the `browse` CLI directly and does not depend on an external MCP server, making it self-contained.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The script handles errors by exiting non-zero and provides clear messages, effectively halting on unexpected states.",{"category":91,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill is designed to be self-contained and does not implicitly rely on other skills, clearly stating its own requirements.",1778683609428,"This skill iteratively improves browser automation tasks by running an inner agent, analyzing traces, and refining navigation strategies. It supports parallel runs and graduates tasks into self-contained skills.",[196,197,198,199,200],"Iterative skill improvement via auto-research loop","Parallel task execution using sub-agents","Support for local and remote browser environments","Generation of self-contained, graduated skills","Clear documentation and examples for usage and setup",[202,203,204,205],"Executing arbitrary shell commands","Replacing a full testing framework","Managing the user's local browser installation","Performing destructive operations outside the browser context",[207,208,209],"Iterative refinement","Browser automation","Agent development",[211,212,213,214],"Node.js 18+","browse CLI","ANTHROPIC_API_KEY","BROWSERBASE_API_KEY (for remote env)","3.0.0","4.4.0","To build and refine reliable, production-ready browser automation skills for any website through an iterative, agent-driven process, significantly reducing costs and improving deterministic outcomes.","All checks passed with high severity, indicating a well-documented, robust, and secure extension.",100,"A robust, self-improving browser automation skill with excellent documentation and security.",[222,223,224,225,226],"browser-automation","web-scraping","llm-agent","testing","node-js","global","verified",[230,231,232,233],"Building automated navigation for specific website tasks","Improving existing brittle browser automation scripts","Creating site-specific playbooks for agents","Reducing LLM exploration costs for repetitive web tasks",[235,236,237,238,239,240,241,242],"Parse arguments and orient task mode (single/multi-task, iterations, env).","Set up workspace (tasks/, traces/) and scaffold task.md/strategy.md if needed.","Run the inner agent via `evaluate.mjs` for the specified task and environment.","Read the trace (summary.md) to identify failures or areas for improvement.","Formulate a single hypothesis and update strategy.md.","Repeat the loop until the task passes consistently or max iterations are reached.","If ready, graduate the task by writing a self-contained SKILL.md to ~/.claude/skills/.","Generate a final report for multi-task sessions.",{"codeQuality":244,"collectedAt":246,"documentation":247,"maintenance":250,"popularity":256,"security":257,"testCoverage":258},{"hasLockfile":245},true,1778683581735,{"descriptionLength":248,"readmeSize":249},341,4101,{"closedIssues90d":8,"forks":251,"hasChangelog":252,"openIssues90d":253,"pushedAt":254,"stars":255},214,false,2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":245,"smitheryVerified":252},{"hasCi":252,"hasTests":252},{"updatedAt":260},1778683610531,{"basePath":262,"githubOwner":263,"githubRepo":264,"locale":18,"slug":265,"type":266},"skills/autobrowse","browserbase","skills","autobrowse","skill",{"_creationTime":268,"_id":269,"community":270,"display":271,"identity":275,"parentExtension":278,"providers":306,"relations":318,"tags":319,"workflow":320},1778683460321.38,"k17bx77jb71yrwatep2nb43r0d86m6cb",{"reviewCount":8},{"description":272,"installMethods":273,"name":274,"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":264},"browse",{"basePath":276,"githubOwner":263,"githubRepo":264,"locale":18,"slug":264,"type":277},"","plugin",{"_creationTime":279,"_id":280,"community":281,"display":282,"identity":285,"providers":287,"relations":300,"tags":302,"workflow":303},1778683460321.3796,"k17aawpn1wczwwhv1snb1x3q2h86m1hy",{"reviewCount":8},{"description":283,"installMethods":284,"name":263,"sourceUrl":14},"Browser automation and Browserbase CLI skills",{"claudeCode":12},{"basePath":276,"githubOwner":263,"githubRepo":264,"locale":18,"slug":264,"type":286},"marketplace",{"evaluate":288,"extract":294},{"promptVersionExtension":289,"promptVersionScoring":216,"score":290,"tags":291,"targetMarket":227,"tier":228},"3.1.0",95,[222,292,223,293,225],"cli","developer-tools",{"commitSha":295,"marketplace":296,"plugin":298},"HEAD",{"name":263,"pluginCount":297},1,{"mcpCount":8,"provider":299,"skillCount":8},"classify",{"repoId":301},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[222,292,293,225,223],{"evaluatedAt":304,"extractAt":305,"updatedAt":304},1778683478405,1778683460321,{"evaluate":307,"extract":315},{"promptVersionExtension":215,"promptVersionScoring":216,"score":308,"tags":309,"targetMarket":227,"tier":228},98,[310,311,312,313,314],"browser","agent","cdp","playwright","automation",{"commitSha":295,"plugin":316},{"mcpCount":8,"provider":299,"skillCount":317},12,{"parentExtensionId":280,"repoId":301},[311,314,310,312,313],{"evaluatedAt":321,"extractAt":305,"updatedAt":321},1778683581384,{"evaluate":323,"extract":325},{"promptVersionExtension":215,"promptVersionScoring":216,"score":219,"tags":324,"targetMarket":227,"tier":228},[222,223,224,225,226],{"commitSha":295,"license":326},"MIT",{"parentExtensionId":269,"repoId":301},{"_creationTime":329,"_id":301,"identity":330,"providers":331,"workflow":588},1778683454816.9644,{"githubOwner":263,"githubRepo":264,"sourceUrl":14},{"classify":332,"discover":579,"extract":582,"github":583,"npm":587},{"commitSha":295,"extensions":333},[334,344,349,355,361,367,373,395,405,431,440,464,477,500,511,520,534,545,571],{"basePath":276,"description":283,"displayName":263,"installMethods":335,"rationale":336,"selectedPaths":337,"source":343,"sourceLanguage":18,"type":286},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[338,341],{"path":339,"priority":340},".claude-plugin/marketplace.json","mandatory",{"path":342,"priority":340},"README.md","rule",{"basePath":276,"description":272,"displayName":274,"installMethods":345,"rationale":346,"selectedPaths":347,"source":343,"sourceLanguage":18,"type":277},{"claudeCode":264},"inline plugin source from marketplace.json at /",[348],{"path":342,"priority":340},{"basePath":276,"description":350,"displayName":351,"installMethods":352,"rationale":346,"selectedPaths":353,"source":343,"sourceLanguage":18,"type":277},"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":264},[354],{"path":342,"priority":340},{"basePath":276,"description":356,"displayName":357,"installMethods":358,"rationale":346,"selectedPaths":359,"source":343,"sourceLanguage":18,"type":277},"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":264},[360],{"path":342,"priority":340},{"basePath":276,"description":362,"displayName":363,"installMethods":364,"rationale":346,"selectedPaths":365,"source":343,"sourceLanguage":18,"type":277},"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":264},[366],{"path":342,"priority":340},{"basePath":276,"description":368,"displayName":369,"installMethods":370,"rationale":346,"selectedPaths":371,"source":343,"sourceLanguage":18,"type":277},"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":264},[372],{"path":342,"priority":340},{"basePath":262,"description":10,"displayName":265,"installMethods":374,"rationale":375,"selectedPaths":376,"source":343,"sourceLanguage":18,"type":266},{"claudeCode":12},"SKILL.md frontmatter at skills/autobrowse/SKILL.md",[377,379,381,383,386,388,390,392],{"path":378,"priority":340},"SKILL.md",{"path":342,"priority":380},"high",{"path":382,"priority":380},"LICENSE.txt",{"path":384,"priority":385},"EXAMPLES.md","medium",{"path":387,"priority":385},"REFERENCE.md",{"path":389,"priority":385},"references/example-skill.md",{"path":391,"priority":385},"references/example-task.md",{"path":393,"priority":394},"scripts/evaluate.mjs","low",{"basePath":396,"description":397,"displayName":310,"installMethods":398,"rationale":399,"selectedPaths":400,"source":343,"sourceLanguage":18,"type":266},"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",[401,402,403,404],{"path":378,"priority":340},{"path":382,"priority":380},{"path":384,"priority":385},{"path":387,"priority":385},{"basePath":406,"description":407,"displayName":363,"installMethods":408,"rationale":409,"selectedPaths":410,"source":343,"sourceLanguage":18,"type":266},"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",[411,412,413,414,415,417,419,421,423,425,427,429],{"path":378,"priority":340},{"path":382,"priority":380},{"path":384,"priority":385},{"path":387,"priority":385},{"path":416,"priority":394},"scripts/bb-capture.mjs",{"path":418,"priority":394},"scripts/bb-finalize.mjs",{"path":420,"priority":394},"scripts/bisect-cdp.mjs",{"path":422,"priority":394},"scripts/lib.mjs",{"path":424,"priority":394},"scripts/query.mjs",{"path":426,"priority":394},"scripts/snapshot-loop.mjs",{"path":428,"priority":394},"scripts/start-capture.mjs",{"path":430,"priority":394},"scripts/stop-capture.mjs",{"basePath":432,"description":433,"displayName":357,"installMethods":434,"rationale":435,"selectedPaths":436,"source":343,"sourceLanguage":18,"type":266},"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",[437,438,439],{"path":378,"priority":340},{"path":382,"priority":380},{"path":387,"priority":385},{"basePath":441,"description":442,"displayName":443,"installMethods":444,"rationale":445,"selectedPaths":446,"source":343,"sourceLanguage":18,"type":266},"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",[447,448,450,452,454,456,458,460,462],{"path":378,"priority":340},{"path":449,"priority":385},"references/example-research.md",{"path":451,"priority":385},"references/report-template.html",{"path":453,"priority":385},"references/research-patterns.md",{"path":455,"priority":385},"references/workflow.md",{"path":457,"priority":394},"scripts/compile_report.mjs",{"path":459,"priority":394},"scripts/extract_page.mjs",{"path":461,"priority":394},"scripts/list_urls.mjs",{"path":463,"priority":394},"scripts/package.json",{"basePath":465,"description":466,"displayName":467,"installMethods":468,"rationale":469,"selectedPaths":470,"source":343,"sourceLanguage":18,"type":266},"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",[471,472,473,474,475],{"path":378,"priority":340},{"path":382,"priority":380},{"path":384,"priority":385},{"path":387,"priority":385},{"path":476,"priority":394},"scripts/cookie-sync.mjs",{"basePath":478,"description":479,"displayName":480,"installMethods":481,"rationale":482,"selectedPaths":483,"source":343,"sourceLanguage":18,"type":266},"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",[484,485,487,488,489,490,491,493,494,496,497,498],{"path":378,"priority":340},{"path":486,"priority":385},"references/event-platforms.md",{"path":449,"priority":385},{"path":451,"priority":385},{"path":453,"priority":385},{"path":455,"priority":385},{"path":492,"priority":394},"scripts/__fixtures__/stripe-snapshot.json",{"path":457,"priority":394},{"path":495,"priority":394},"scripts/extract_event.mjs",{"path":459,"priority":394},{"path":463,"priority":394},{"path":499,"priority":394},"scripts/recon.mjs",{"basePath":501,"description":502,"displayName":503,"installMethods":504,"rationale":505,"selectedPaths":506,"source":343,"sourceLanguage":18,"type":266},"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",[507,508,509,510],{"path":378,"priority":340},{"path":382,"priority":380},{"path":384,"priority":385},{"path":387,"priority":385},{"basePath":512,"description":513,"displayName":351,"installMethods":514,"rationale":515,"selectedPaths":516,"source":343,"sourceLanguage":18,"type":266},"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",[517,518,519],{"path":378,"priority":340},{"path":382,"priority":380},{"path":387,"priority":385},{"basePath":521,"description":522,"displayName":369,"installMethods":523,"rationale":524,"selectedPaths":525,"source":343,"sourceLanguage":18,"type":266},"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",[526,527,528,530,532],{"path":378,"priority":340},{"path":382,"priority":380},{"path":529,"priority":394},"templates/claude-agent-sdk/.gitignore",{"path":531,"priority":394},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":533,"priority":394},"templates/claude-agent-sdk/package.json",{"basePath":535,"description":536,"displayName":537,"installMethods":538,"rationale":539,"selectedPaths":540,"source":343,"sourceLanguage":18,"type":266},"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",[541,542,543,544],{"path":378,"priority":340},{"path":382,"priority":380},{"path":384,"priority":385},{"path":387,"priority":385},{"basePath":546,"description":547,"displayName":548,"installMethods":549,"rationale":550,"selectedPaths":551,"source":343,"sourceLanguage":18,"type":266},"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",[552,553,554,555,556,558,560,562,564,566,568,569],{"path":378,"priority":340},{"path":342,"priority":380},{"path":382,"priority":380},{"path":384,"priority":385},{"path":557,"priority":385},"references/adversarial-patterns.md",{"path":559,"priority":385},"references/browser-recipes.md",{"path":561,"priority":385},"references/design-consistency.md",{"path":563,"priority":385},"references/design-system.example.md",{"path":565,"priority":385},"references/exploratory-testing.md",{"path":567,"priority":385},"references/parallel-testing.md",{"path":451,"priority":385},{"path":570,"priority":385},"references/ux-heuristics.md",{"basePath":276,"displayName":572,"installMethods":573,"rationale":574,"selectedPaths":575,"source":343,"sourceLanguage":18,"type":292},"browserbase-skills",{"npm":572},"cli ecosystem detected at /",[576,578],{"path":577,"priority":340},"package.json",{"path":342,"priority":340},{"sources":580},[581],"manual",{"npmPackage":572},{"closedIssues90d":8,"description":584,"forks":251,"homepage":585,"openIssues90d":253,"pushedAt":254,"readmeSize":249,"stars":255,"topics":586},"Browserbase's official collection of agent skills to access the web.","https://www.browserbase.com/SKILL.md",[],{"downloads":8},{"classifiedAt":589,"discoverAt":590,"extractAt":591,"githubAt":591,"npmAt":592,"updatedAt":589},1778683460101,1778683454817,1778683457134,1778683458753,[222,224,226,225,223],{"evaluatedAt":260,"extractAt":305,"updatedAt":260},[],[597,624,651,686,713,739],{"_creationTime":598,"_id":599,"community":600,"display":601,"identity":607,"providers":612,"relations":616,"tags":619,"workflow":620},1778697373439.756,"k1735p8vnc44y3ntfepns5m0nx86npbs",{"reviewCount":8},{"description":602,"installMethods":603,"name":605,"sourceUrl":606},"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":604},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":608,"githubOwner":609,"githubRepo":610,"locale":611,"slug":605,"type":266},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice","de",{"evaluate":613,"extract":615},{"promptVersionExtension":215,"promptVersionScoring":216,"score":219,"tags":614,"targetMarket":227,"tier":228},[222,223,225,292,314],{"commitSha":295},{"repoId":617,"translatedFrom":618},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[314,222,292,225,223],{"evaluatedAt":621,"extractAt":622,"updatedAt":623},1778697222051,1778697205743,1778697373439,{"_creationTime":625,"_id":626,"community":627,"display":628,"identity":634,"providers":638,"relations":645,"tags":647,"workflow":648},1778696993586.7058,"k174ty9vbfgj7cv3v2szdwjgh986mrsf",{"reviewCount":8},{"description":629,"installMethods":630,"name":632,"sourceUrl":633},"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":631},"SeifBenayed/claude-code-sdk","chatgpt-search","https://github.com/SeifBenayed/claude-code-sdk",{"basePath":635,"githubOwner":636,"githubRepo":637,"locale":18,"slug":632,"type":266},".claude/skills/chatgpt-search","SeifBenayed","claude-code-sdk",{"evaluate":639,"extract":644},{"promptVersionExtension":215,"promptVersionScoring":216,"score":219,"tags":640,"targetMarket":227,"tier":228},[641,642,222,643,223],"chatgpt","scraping","data-extraction",{"commitSha":295},{"repoId":646},"kd78s53c1852h5p7c3qem663xs86njab",[222,641,643,642,223],{"evaluatedAt":649,"extractAt":650,"updatedAt":649},1778697026743,1778696993586,{"_creationTime":652,"_id":653,"community":654,"display":655,"identity":661,"providers":666,"relations":679,"tags":682,"workflow":683},1778675056600.249,"k176bgqbfa54d9kxrf8abw5j9s86mhr5",{"reviewCount":8},{"description":656,"installMethods":657,"name":659,"sourceUrl":660},"Designs and implements backend systems including REST APIs, microservices, database architectures, authentication flows, and security hardening. Use when the user asks to \"design REST APIs\", \"optimize database queries\", \"implement authentication\", \"build microservices\", \"review backend code\", \"set up GraphQL\", \"handle database migrations\", or \"load test APIs\". Covers Node.js/Express/Fastify development, PostgreSQL optimization, API security, and backend architecture patterns.",{"claudeCode":658},"alirezarezvani/claude-skills","Senior Backend Engineer","https://github.com/alirezarezvani/claude-skills",{"basePath":662,"githubOwner":663,"githubRepo":664,"locale":18,"slug":665,"type":266},"engineering-team/skills/senior-backend","alirezarezvani","claude-skills","senior-backend",{"evaluate":667,"extract":678},{"promptVersionExtension":215,"promptVersionScoring":216,"score":219,"tags":668,"targetMarket":227,"tier":228},[669,670,671,672,673,674,675,226,676,677,225],"backend","api","rest","microservices","database","postgresql","typescript","express","security",{"commitSha":295,"license":326},{"parentExtensionId":680,"repoId":681},"k179s2ynpr6g927zdzf23zrhad86net8","kd7ff9s1w43mfyy1n7hf87816186m6px",[670,669,673,676,672,226,674,671,677,225,675],{"evaluatedAt":684,"extractAt":685,"updatedAt":684},1778683394838,1778675056600,{"_creationTime":687,"_id":688,"community":689,"display":690,"identity":696,"providers":700,"relations":706,"tags":709,"workflow":710},1778696691708.3125,"k1704t5mbdhdjkqqyvh15rz98986n4b0",{"reviewCount":8},{"description":691,"installMethods":692,"name":694,"sourceUrl":695},"Extract structured data via stored browser-templates or one-shot DOM queries, with mandatory AIDefence PII + prompt-injection gates before content reaches the model",{"claudeCode":693},"ruvnet/ruflo","browser-extract","https://github.com/ruvnet/ruflo",{"basePath":697,"githubOwner":698,"githubRepo":699,"locale":18,"slug":694,"type":266},"plugins/ruflo-browser/skills/browser-extract","ruvnet","ruflo",{"evaluate":701,"extract":705},{"promptVersionExtension":215,"promptVersionScoring":216,"score":702,"tags":703,"targetMarket":227,"tier":228},99,[223,643,222,677,704],"pii-detection",{"commitSha":295},{"parentExtensionId":707,"repoId":708},"k171keecmm9hg25jek1v0vqawd86ntq2","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[222,643,704,677,223],{"evaluatedAt":711,"extractAt":712,"updatedAt":711},1778699898275,1778696691708,{"_creationTime":714,"_id":715,"community":716,"display":717,"identity":722,"providers":726,"relations":731,"tags":734,"workflow":735},1778698644808.435,"k179zdfeah0b0cr5pvznget1cx86mkmf",{"reviewCount":8},{"description":718,"installMethods":719,"name":605,"sourceUrl":721},"Interagieren Sie mit Slack-Arbeitsbereichen mithilfe von Browser-Automatisierung. Verwenden Sie dies, wenn der Benutzer ungelesene Kanäle überprüfen, Slack navigieren, Nachrichten senden, Daten extrahieren, Informationen finden, Konversationen durchsuchen oder jede Slack-Aufgabe automatisieren muss. Trigger sind \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\" oder jede Aufgabe, die programmatische Slack-Interaktion erfordert.",{"claudeCode":720},"vercel-labs/agent-browser","https://github.com/vercel-labs/agent-browser",{"basePath":723,"githubOwner":724,"githubRepo":605,"locale":611,"slug":725,"type":266},"skill-data/slack","vercel-labs","slack",{"evaluate":727,"extract":729},{"promptVersionExtension":215,"promptVersionScoring":216,"score":702,"tags":728,"targetMarket":227,"tier":228},[222,725,292,314,223],{"commitSha":295,"license":730},"Apache-2.0",{"repoId":732,"translatedFrom":733},"kd74a6sfc26xa0ec2tpntj8r2986mn0a","k175jjsqj2p1he1cnp97qv600x86m87w",[314,222,292,725,223],{"evaluatedAt":736,"extractAt":737,"updatedAt":738},1778698509141,1778698388091,1778698644808,{"_creationTime":740,"_id":741,"community":742,"display":743,"identity":749,"providers":752,"relations":757,"tags":761,"workflow":762},1778696989496.538,"k1776jcwjkmjfcm2gv94xeezz586m1tg",{"reviewCount":8},{"description":744,"installMethods":745,"name":747,"sourceUrl":748},"Browserautomatisierung mit persistentem Seitenzustand. Verwenden Sie dies, wenn Benutzer aufgefordert werden, Websites zu navigieren, Formulare auszufüllen, Screenshots zu erstellen, Webdaten zu extrahieren, Webanwendungen zu testen oder Browser-Workflows zu automatisieren. Auslöser-Phrasen sind \"gehe zu [URL]\", \"klicke auf\", \"fülle das Formular aus\", \"mache einen Screenshot\", \"scrapen\", \"automatisieren\", \"teste die Website\", \"melde dich an\" oder jede Anfrage zur Browserinteraktion.",{"claudeCode":746},"SawyerHood/dev-browser","dev-browser","https://github.com/SawyerHood/dev-browser",{"basePath":750,"githubOwner":751,"githubRepo":747,"locale":611,"slug":747,"type":266},"skills/dev-browser","SawyerHood",{"evaluate":753,"extract":756},{"promptVersionExtension":215,"promptVersionScoring":216,"score":702,"tags":754,"targetMarket":227,"tier":228},[222,313,755,225,223],"javascript",{"commitSha":295},{"parentExtensionId":758,"repoId":759,"translatedFrom":760},"k172vf4sjqdwht2n7b64bmf7wn86mzzp","kd778ksdnkgy1969578mg8f30986nddw","k17535f2wgbtzrzc5n55ps9f3586mr7p",[222,755,313,225,223],{"evaluatedAt":763,"extractAt":764,"updatedAt":765},1778696938150,1778696896101,1778696989496]