[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-browserbase-company-research-zh-CN":3,"guides-for-browserbase-company-research":595,"similar-k173t0vany5k5ve3tam3nyk8c186nq41-zh-CN":596},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":262,"isFallback":245,"parentExtension":267,"providers":322,"relations":327,"repo":328,"tags":593,"workflow":594},1778683460321.382,"k173t0vany5k5ve3tam3nyk8c186nq41",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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",{"claudeCode":12},"browserbase/skills","Company Research","https://github.com/browserbase/skills",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":243,"workflow":260},1778683708926.9146,"kn78a0t21fv9dnyaw3tpm4vj6h86n7tp","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":210,"promptVersionExtension":214,"promptVersionScoring":215,"purpose":216,"rationale":217,"score":218,"summary":219,"tags":220,"targetMarket":226,"tier":227,"useCases":228,"workflow":234},[21,26,29,32,36,39,43,47,51,54,58,62,65,69,72,75,78,81,84,87,90,94,99,103,107,110,113,116,120,123,126,129,132,135,138,142,146,150,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the user problem of company discovery and research, and identifies the target user (sales/market research) and the artifacts involved (companies, ICP, research reports).",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill leverages Browserbase Search API and a Plan→Research→Synthesize pattern, going beyond basic LLM capabilities for company research and ICP fit scoring.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill appears to cover the complete lifecycle from user input to a scored research report and CSV, with clear setup instructions and documented workflow.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill has a single, coherent domain: company discovery and deep research, with a well-defined process.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's capabilities, purpose, and usage triggers, and is concise and readable.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The skill restricts tool usage to specific commands like `bb search`, `bb fetch`, `node scripts/extract_page.mjs`, and `node scripts/compile_report.mjs` via Bash, adhering to strict tool rules.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","The SKILL.md details required environment variables (`BROWSERBASE_API_KEY`), command-line tool setup (`bb` CLI), and path rules, with clear instructions for first-run setup and permission approval.",{"category":33,"check":48,"severity":49,"summary":50},"Tool naming","not_applicable","The skill primarily uses the Bash tool to execute specific commands (bb, node scripts), rather than exposing distinct user-facing tools with unique names.",{"category":33,"check":52,"severity":24,"summary":53},"Minimal I/O surface","The skill's Bash tool usage is constrained to specific commands with defined outputs, and its sub-agents write to a designated output directory, avoiding unnecessary data exposure.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The license is MIT, a permissive open-source license, as declared in the SKILL.md frontmatter.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The repository was last pushed to on 2026-05-13, indicating recent maintenance.",{"category":59,"check":63,"severity":24,"summary":64},"Dependency Management","Dependencies like `bb` CLI and Node.js scripts are managed within the repository context; standard Node.js package management is assumed for script execution.",{"category":66,"check":67,"severity":24,"summary":68},"Security","Secret Management","The skill requires a `BROWSERBASE_API_KEY` as an environment variable, which is a standard and appropriate method for handling secrets. No secrets are hardcoded or leaked.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill explicitly states that user-provided data (like URLs) should be treated as data and not instructions, and all operations are performed through controlled `bb` commands and Node.js scripts, with strict rules against arbitrary command execution.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill restricts execution to committed scripts and `bb` CLI commands. It explicitly prohibits runtime downloads of code or data, and uses `extract_page.mjs` which handles fetching via `bb fetch` and `bb browse`.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill mandates the use of full literal paths and restricts operations to specific commands and a designated output directory on the user's Desktop, preventing writes outside its intended scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The skill's workflow and tool restrictions, particularly the prohibition of `~` and `$HOME` in paths and the reliance on specific `bb` commands executed within Bash, prevent detached process spawns and deny-retry loops.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill only uses the `BROWSERBASE_API_KEY` and outputs research data to the user's Desktop. It does not have any documented outbound calls for telemetry or data submission.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled markdown and scripts appear to be free of hidden-steering tricks, control characters, or malicious Unicode sequences. Prose adheres to standard formatting.",{"category":66,"check":88,"severity":24,"summary":89},"Opaque code execution","The skill's scripts are available as readable `.mjs` files and rely on standard `bb` CLI commands; there is no evidence of obfuscated code, base64 payloads, or runtime script fetching.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The skill explicitly states path rules, requiring full literal paths and resolving the home directory once, thus avoiding assumptions about user-specific project organization or OS-specific path syntaxes like `~` or `$HOME`.",{"category":95,"check":96,"severity":97,"summary":98},"Trust","Issues Attention","info","There are 2 open issues and 0 closed issues in the last 90 days, indicating low recent activity but not necessarily slow response for the few issues present.",{"category":100,"check":101,"severity":24,"summary":102},"Versioning","Release Management","The skill declares a version ('1.1.0') in its SKILL.md frontmatter, providing a clear version signal.",{"category":104,"check":105,"severity":24,"summary":106},"Code Execution","Validation","The skill relies on controlled `bb` commands and its own `extract_page.mjs` script for processing external content, implying built-in validation and sanitization for its inputs and outputs.",{"category":66,"check":108,"severity":24,"summary":109},"Unguarded Destructive Operations","The skill's primary destructive operation is writing to the user's Desktop directory, which is a standard location for output and is implicitly confirmed by the user when they initiate the skill. No other destructive operations are evident.",{"category":104,"check":111,"severity":24,"summary":112},"Error Handling","The skill's scripts and workflow description emphasize handling errors from `bb fetch` and `extract_page.mjs`, and the `compile_report.mjs` script includes error handling for file operations and parsing.",{"category":104,"check":114,"severity":49,"summary":115},"Logging","The skill does not appear to implement a custom local audit log file, but its workflow commands (like `bb search` and `bb fetch`) may have their own logging, and the final report provides a summary of outcomes.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The skill operates on company websites and outputs research data, but does not appear to collect or process personal data beyond what is publicly available on company sites, and outputs are directed to the user's local machine.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The skill focuses on company research and web scraping, with no explicit regional limitations; the `targetMarket` is global.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The skill relies on the `bb` CLI and Node.js, which are standard environments. Path rules ensure portability by avoiding OS-specific pathing.",{"category":44,"check":127,"severity":24,"summary":128},"README","A README.md file is present and provides a good overview of the Browserbase skills, including installation and usage instructions.",{"category":33,"check":130,"severity":49,"summary":131},"Tool surface size","The skill primarily uses the Bash tool to orchestrate a series of `bb` commands and Node.js scripts, rather than exposing numerous distinct tools.",{"category":40,"check":133,"severity":49,"summary":134},"Overlapping near-synonym tools","The skill primarily uses Bash to execute specific, non-overlapping commands like `bb search`, `bb fetch`, `extract_page.mjs`, and `compile_report.mjs`.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All features advertised in the README and SKILL.md, such as company discovery, research patterns, and report generation, have corresponding implementations in the provided scripts and workflow.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README and SKILL.md provide clear installation instructions via `npx skills add browserbase/skills` and manual steps for Claude Code, including setting up the `BROWSERBASE_API_KEY`.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The skill's documentation and script logic imply that errors from `bb` commands and Node.js scripts will be reported, with guidance on handling API keys and permissions.",{"category":147,"check":148,"severity":24,"summary":149},"Execution","Pinned dependencies","The skill's scripts are written in JavaScript/Node.js, and the `package.json` is present. The `bb` CLI dependency is assumed to be installed by the user.",{"category":33,"check":151,"severity":49,"summary":152},"Dry-run preview","The skill's primary output is a research report saved locally to the user's Desktop, which is not a destructive operation requiring a dry-run mode.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The skill uses external `bb` commands and Node.js scripts; timeouts are managed by `bb` and Node.js execution, and operations like file writes are inherently idempotent per run.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","The skill does not emit telemetry. Its operations are focused on local file output and interaction with the Browserbase API, with no mention of opt-in or opt-out telemetry.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined, detailing what it does (company discovery/research), how it does it (Browserbase API, Plan→Research→Synthesize), and when to use it with clear triggers and boundaries.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise and self-contained, clearly stating the skill's name, purpose, triggers, and essential setup requirements.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is well-structured and avoids excessive length, delegating detailed workflow and research patterns to separate reference files.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","Detailed workflow steps, research patterns, and example research files are provided in separate reference markdown files, linked from the main SKILL.md.",{"category":170,"check":174,"severity":49,"summary":175},"Forked exploration","This skill does not involve deep code review or extensive exploration that would require `context: fork`. Its workflow is linear and focused on data collection and synthesis.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md includes detailed examples of Bash commands for setup and research execution, and the `compile_report.mjs` script generates a user-facing HTML report and CSV, demonstrating the end-to-end process.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The skill addresses potential issues like inaccessible homepages (`Unknown — homepage content not accessible` and score capping), permission prompts, and the need for `BROWSERBASE_API_KEY`, providing recovery steps or clear instructions.",{"category":104,"check":183,"severity":49,"summary":184},"Tool Fallback","The skill explicitly requires the `bb` CLI and `BROWSERBASE_API_KEY`, and does not list optional tools or built-in fallbacks.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The skill outlines strict rules for path usage, tool execution, and data handling, which implicitly halts the workflow if unexpected states or disallowed operations occur. Permission prompts also act as a gate.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The skill is self-contained and does not appear to rely on other skills being loaded. Its dependencies are external tools (`bb` CLI) and Node.js scripts.",1778683708595,"This skill automates company discovery and deep research using the Browserbase Search API. It follows a Plan→Research→Synthesize pattern, scores ICP fit, and compiles findings into a research report and CSV. It supports configurable depth modes for balancing scale and intelligence.",[195,196,197,198,199],"Discover target companies using Browserbase Search API","Research companies using Plan→Research→Synthesize pattern","Score ICP fit with evidence-based reasoning","Generate scored research reports and CSV files","Support depth modes (quick/deep/deeper) for flexibility",[201,202,203,204],"Performing sales outreach or sending emails","Researching companies outside the explicitly defined ICP","Replacing manual sales prospecting entirely","Providing real-time company financial data beyond publicly available funding rounds",[206,207,208,209],"Plan→Research→Synthesize","ICP Alignment","Data Synthesis","Automated Reporting",[211,212,213],"Browserbase Search API access","BROWSERBASE_API_KEY environment variable","bb CLI installed (@browserbasehq/cli)","3.0.0","4.4.0","To automate the discovery and deep research of target companies for sales and marketing, enabling users to build targeted company lists and understand prospect ICP fit.","The skill has a clear purpose, robust documentation, and adheres to security best practices, with no critical or warning findings.",98,"A high-quality skill for in-depth company research and lead generation, well-documented and secure.",[221,222,223,224,225],"company-research","lead-generation","sales-intelligence","web-scraping","browser-automation","global","verified",[229,230,231,232,233],"Find companies to sell to","Research potential customers","Discover companies matching a specific ICP","Build a target company list","Conduct market research on prospects",[235,236,237,238,239,240,241,242],"Setup output directory on Desktop","Deeply research user's company to define ICP","Select depth mode (quick/deep/deeper)","Discover target companies via multiple search queries","Filter discovery results to company homepages","Deeply research each target company (plan, search, extract, synthesize, score)","Compile findings into an HTML report and CSV","Present summary and top companies in chat",{"codeQuality":244,"collectedAt":246,"documentation":247,"maintenance":250,"popularity":257,"security":258,"testCoverage":259},{"hasLockfile":245},true,1778683681984,{"descriptionLength":248,"readmeSize":249},757,4101,{"closedIssues90d":8,"forks":251,"hasChangelog":252,"manifestVersion":253,"openIssues90d":254,"pushedAt":255,"stars":256},214,false,"1.1.0",2,1778633729000,3179,{"npmDownloads":8},{"hasNpmPackage":245,"smitheryVerified":252},{"hasCi":252,"hasTests":252},{"updatedAt":261},1778683708926,{"basePath":263,"githubOwner":264,"githubRepo":265,"locale":18,"slug":221,"type":266},"skills/company-research","browserbase","skills","skill",{"_creationTime":268,"_id":269,"community":270,"display":271,"identity":275,"parentExtension":278,"providers":307,"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":265},"browse",{"basePath":276,"githubOwner":264,"githubRepo":265,"locale":18,"slug":265,"type":277},"","plugin",{"_creationTime":279,"_id":280,"community":281,"display":282,"identity":285,"providers":287,"relations":301,"tags":303,"workflow":304},1778683460321.3796,"k17aawpn1wczwwhv1snb1x3q2h86m1hy",{"reviewCount":8},{"description":283,"installMethods":284,"name":264,"sourceUrl":14},"Browser automation and Browserbase CLI skills",{"claudeCode":12},{"basePath":276,"githubOwner":264,"githubRepo":265,"locale":18,"slug":265,"type":286},"marketplace",{"evaluate":288,"extract":295},{"promptVersionExtension":289,"promptVersionScoring":215,"score":290,"tags":291,"targetMarket":226,"tier":227},"3.1.0",95,[225,292,224,293,294],"cli","developer-tools","testing",{"commitSha":296,"marketplace":297,"plugin":299},"HEAD",{"name":264,"pluginCount":298},1,{"mcpCount":8,"provider":300,"skillCount":8},"classify",{"repoId":302},"kd77wvcdm5fq9xp8hk6ppm832s86myxr",[225,292,293,294,224],{"evaluatedAt":305,"extractAt":306,"updatedAt":305},1778683478405,1778683460321,{"evaluate":308,"extract":315},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":309,"targetMarket":226,"tier":227},[310,311,312,313,314],"browser","agent","cdp","playwright","automation",{"commitSha":296,"plugin":316},{"mcpCount":8,"provider":300,"skillCount":317},12,{"parentExtensionId":280,"repoId":302},[311,314,310,312,313],{"evaluatedAt":321,"extractAt":306,"updatedAt":321},1778683581384,{"evaluate":323,"extract":325},{"promptVersionExtension":214,"promptVersionScoring":215,"score":218,"tags":324,"targetMarket":226,"tier":227},[221,222,223,224,225],{"commitSha":296,"license":326},"MIT",{"parentExtensionId":269,"repoId":302},{"_creationTime":329,"_id":302,"identity":330,"providers":331,"workflow":588},1778683454816.9644,{"githubOwner":264,"githubRepo":265,"sourceUrl":14},{"classify":332,"discover":579,"extract":582,"github":583,"npm":587},{"commitSha":296,"extensions":333},[334,344,349,355,361,367,373,398,408,434,443,464,477,500,511,520,534,545,571],{"basePath":276,"description":283,"displayName":264,"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":265},"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":265},[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":265},[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":265},[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":265},[372],{"path":342,"priority":340},{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":343,"sourceLanguage":18,"type":266},"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",[380,382,384,386,389,391,393,395],{"path":381,"priority":340},"SKILL.md",{"path":342,"priority":383},"high",{"path":385,"priority":383},"LICENSE.txt",{"path":387,"priority":388},"EXAMPLES.md","medium",{"path":390,"priority":388},"REFERENCE.md",{"path":392,"priority":388},"references/example-skill.md",{"path":394,"priority":388},"references/example-task.md",{"path":396,"priority":397},"scripts/evaluate.mjs","low",{"basePath":399,"description":400,"displayName":310,"installMethods":401,"rationale":402,"selectedPaths":403,"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",[404,405,406,407],{"path":381,"priority":340},{"path":385,"priority":383},{"path":387,"priority":388},{"path":390,"priority":388},{"basePath":409,"description":410,"displayName":363,"installMethods":411,"rationale":412,"selectedPaths":413,"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",[414,415,416,417,418,420,422,424,426,428,430,432],{"path":381,"priority":340},{"path":385,"priority":383},{"path":387,"priority":388},{"path":390,"priority":388},{"path":419,"priority":397},"scripts/bb-capture.mjs",{"path":421,"priority":397},"scripts/bb-finalize.mjs",{"path":423,"priority":397},"scripts/bisect-cdp.mjs",{"path":425,"priority":397},"scripts/lib.mjs",{"path":427,"priority":397},"scripts/query.mjs",{"path":429,"priority":397},"scripts/snapshot-loop.mjs",{"path":431,"priority":397},"scripts/start-capture.mjs",{"path":433,"priority":397},"scripts/stop-capture.mjs",{"basePath":435,"description":436,"displayName":357,"installMethods":437,"rationale":438,"selectedPaths":439,"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",[440,441,442],{"path":381,"priority":340},{"path":385,"priority":383},{"path":390,"priority":388},{"basePath":263,"description":10,"displayName":221,"installMethods":444,"rationale":445,"selectedPaths":446,"source":343,"sourceLanguage":18,"type":266},{"claudeCode":12},"SKILL.md frontmatter at skills/company-research/SKILL.md",[447,448,450,452,454,456,458,460,462],{"path":381,"priority":340},{"path":449,"priority":388},"references/example-research.md",{"path":451,"priority":388},"references/report-template.html",{"path":453,"priority":388},"references/research-patterns.md",{"path":455,"priority":388},"references/workflow.md",{"path":457,"priority":397},"scripts/compile_report.mjs",{"path":459,"priority":397},"scripts/extract_page.mjs",{"path":461,"priority":397},"scripts/list_urls.mjs",{"path":463,"priority":397},"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":381,"priority":340},{"path":385,"priority":383},{"path":387,"priority":388},{"path":390,"priority":388},{"path":476,"priority":397},"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":381,"priority":340},{"path":486,"priority":388},"references/event-platforms.md",{"path":449,"priority":388},{"path":451,"priority":388},{"path":453,"priority":388},{"path":455,"priority":388},{"path":492,"priority":397},"scripts/__fixtures__/stripe-snapshot.json",{"path":457,"priority":397},{"path":495,"priority":397},"scripts/extract_event.mjs",{"path":459,"priority":397},{"path":463,"priority":397},{"path":499,"priority":397},"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":381,"priority":340},{"path":385,"priority":383},{"path":387,"priority":388},{"path":390,"priority":388},{"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":381,"priority":340},{"path":385,"priority":383},{"path":390,"priority":388},{"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":381,"priority":340},{"path":385,"priority":383},{"path":529,"priority":397},"templates/claude-agent-sdk/.gitignore",{"path":531,"priority":397},"templates/claude-agent-sdk/hn-scraper-demo.mjs",{"path":533,"priority":397},"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":381,"priority":340},{"path":385,"priority":383},{"path":387,"priority":388},{"path":390,"priority":388},{"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":381,"priority":340},{"path":342,"priority":383},{"path":385,"priority":383},{"path":387,"priority":388},{"path":557,"priority":388},"references/adversarial-patterns.md",{"path":559,"priority":388},"references/browser-recipes.md",{"path":561,"priority":388},"references/design-consistency.md",{"path":563,"priority":388},"references/design-system.example.md",{"path":565,"priority":388},"references/exploratory-testing.md",{"path":567,"priority":388},"references/parallel-testing.md",{"path":451,"priority":388},{"path":570,"priority":388},"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":254,"pushedAt":255,"readmeSize":249,"stars":256,"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,[225,221,222,223,224],{"evaluatedAt":261,"extractAt":306,"updatedAt":261},[],[597,625,652,670,698,724],{"_creationTime":598,"_id":599,"community":600,"display":601,"identity":607,"providers":612,"relations":617,"tags":620,"workflow":621},1778697369634.8499,"k17333g8dacqsmw8kk79h77vmx86n0d1",{"reviewCount":8},{"description":602,"installMethods":603,"name":605,"sourceUrl":606},"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":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","zh-CN",{"evaluate":613,"extract":616},{"promptVersionExtension":214,"promptVersionScoring":215,"score":614,"tags":615,"targetMarket":226,"tier":227},100,[225,224,294,292,314],{"commitSha":296},{"repoId":618,"translatedFrom":619},"kd74710g49kxgwbfjxeb7s132d86myxr","k17ej9360g7468qswf3svnrx9186m1ng",[314,225,292,294,224],{"evaluatedAt":622,"extractAt":623,"updatedAt":624},1778697222051,1778697205743,1778697369634,{"_creationTime":626,"_id":627,"community":628,"display":629,"identity":635,"providers":639,"relations":646,"tags":648,"workflow":649},1778696993586.7058,"k174ty9vbfgj7cv3v2szdwjgh986mrsf",{"reviewCount":8},{"description":630,"installMethods":631,"name":633,"sourceUrl":634},"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":632},"SeifBenayed/claude-code-sdk","chatgpt-search","https://github.com/SeifBenayed/claude-code-sdk",{"basePath":636,"githubOwner":637,"githubRepo":638,"locale":18,"slug":633,"type":266},".claude/skills/chatgpt-search","SeifBenayed","claude-code-sdk",{"evaluate":640,"extract":645},{"promptVersionExtension":214,"promptVersionScoring":215,"score":614,"tags":641,"targetMarket":226,"tier":227},[642,643,225,644,224],"chatgpt","scraping","data-extraction",{"commitSha":296},{"repoId":647},"kd78s53c1852h5p7c3qem663xs86njab",[225,642,644,643,224],{"evaluatedAt":650,"extractAt":651,"updatedAt":650},1778697026743,1778696993586,{"_creationTime":653,"_id":654,"community":655,"display":656,"identity":659,"providers":660,"relations":666,"tags":667,"workflow":668},1778683460321.381,"k1707rtzme0qezretvp3gmtfvn86n1k1",{"reviewCount":8},{"description":375,"installMethods":657,"name":658,"sourceUrl":14},{"claudeCode":12},"AutoBrowse",{"basePath":374,"githubOwner":264,"githubRepo":265,"locale":18,"slug":376,"type":266},{"evaluate":661,"extract":665},{"promptVersionExtension":214,"promptVersionScoring":215,"score":614,"tags":662,"targetMarket":226,"tier":227},[225,224,663,294,664],"llm-agent","node-js",{"commitSha":296,"license":326},{"parentExtensionId":269,"repoId":302},[225,663,664,294,224],{"evaluatedAt":669,"extractAt":306,"updatedAt":669},1778683610531,{"_creationTime":671,"_id":672,"community":673,"display":674,"identity":680,"providers":684,"relations":691,"tags":694,"workflow":695},1778696691708.3125,"k1704t5mbdhdjkqqyvh15rz98986n4b0",{"reviewCount":8},{"description":675,"installMethods":676,"name":678,"sourceUrl":679},"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":677},"ruvnet/ruflo","browser-extract","https://github.com/ruvnet/ruflo",{"basePath":681,"githubOwner":682,"githubRepo":683,"locale":18,"slug":678,"type":266},"plugins/ruflo-browser/skills/browser-extract","ruvnet","ruflo",{"evaluate":685,"extract":690},{"promptVersionExtension":214,"promptVersionScoring":215,"score":686,"tags":687,"targetMarket":226,"tier":227},99,[224,644,225,688,689],"security","pii-detection",{"commitSha":296},{"parentExtensionId":692,"repoId":693},"k171keecmm9hg25jek1v0vqawd86ntq2","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[225,644,689,688,224],{"evaluatedAt":696,"extractAt":697,"updatedAt":696},1778699898275,1778696691708,{"_creationTime":699,"_id":700,"community":701,"display":702,"identity":707,"providers":711,"relations":716,"tags":719,"workflow":720},1778698650056.7576,"k1723ahhrd1f8ax5s297rmdp9s86n40f",{"reviewCount":8},{"description":703,"installMethods":704,"name":605,"sourceUrl":706},"通过浏览器自动化与 Slack 工作区进行交互。适用于用户需要检查未读频道、导航 Slack、发送消息、提取数据、查找信息、搜索对话或自动化任何 Slack 任务的场景。触发词包括“检查我的 Slack”、“有哪些未读频道”、“发送消息给”、“搜索 Slack”、“从 Slack 提取”、“查找谁说了”或任何需要程序化 Slack 交互的任务。",{"claudeCode":705},"vercel-labs/agent-browser","https://github.com/vercel-labs/agent-browser",{"basePath":708,"githubOwner":709,"githubRepo":605,"locale":611,"slug":710,"type":266},"skill-data/slack","vercel-labs","slack",{"evaluate":712,"extract":714},{"promptVersionExtension":214,"promptVersionScoring":215,"score":686,"tags":713,"targetMarket":226,"tier":227},[225,710,292,314,224],{"commitSha":296,"license":715},"Apache-2.0",{"repoId":717,"translatedFrom":718},"kd74a6sfc26xa0ec2tpntj8r2986mn0a","k175jjsqj2p1he1cnp97qv600x86m87w",[314,225,292,710,224],{"evaluatedAt":721,"extractAt":722,"updatedAt":723},1778698509141,1778698388091,1778698650056,{"_creationTime":725,"_id":726,"community":727,"display":728,"identity":734,"providers":737,"relations":742,"tags":746,"workflow":747},1778696994282.5017,"k17497mez0dgwcmcmmh6dvw05s86ne9k",{"reviewCount":8},{"description":729,"installMethods":730,"name":732,"sourceUrl":733},"使用持久化页面状态进行浏览器自动化。当用户要求导航网站、填写表单、截屏、提取网页数据、测试 Web 应用或自动化浏览器工作流时使用。触发短语包括“转到 [url]”、“点击”、“填写表单”、“截屏”、“抓取”、“自动化”、“测试网站”、“登录”或任何浏览器交互请求。",{"claudeCode":731},"SawyerHood/dev-browser","dev-browser","https://github.com/SawyerHood/dev-browser",{"basePath":735,"githubOwner":736,"githubRepo":732,"locale":611,"slug":732,"type":266},"skills/dev-browser","SawyerHood",{"evaluate":738,"extract":741},{"promptVersionExtension":214,"promptVersionScoring":215,"score":686,"tags":739,"targetMarket":226,"tier":227},[225,313,740,294,224],"javascript",{"commitSha":296},{"parentExtensionId":743,"repoId":744,"translatedFrom":745},"k172vf4sjqdwht2n7b64bmf7wn86mzzp","kd778ksdnkgy1969578mg8f30986nddw","k17535f2wgbtzrzc5n55ps9f3586mr7p",[225,740,313,294,224],{"evaluatedAt":748,"extractAt":749,"updatedAt":750},1778696938150,1778696896101,1778696994282]