[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-firecrawl-firecrawl-interact-en":3,"guides-for-firecrawl-firecrawl-interact":510,"similar-k171m557sa526rn734zqq7hpe586m3b8-en":511},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":260,"isFallback":250,"parentExtension":265,"providers":320,"relations":324,"repo":325,"tags":508,"workflow":509},1778686940775.5718,"k171m557sa526rn734zqq7hpe586m3b8",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Control and interact with a live browser session on any scraped page — click buttons, fill forms, navigate flows, and extract data using natural language prompts or code. Use when the user needs to interact with a webpage beyond simple scraping: logging into a site, submitting forms, clicking through pagination, handling infinite scroll, navigating multi-step checkout or wizard flows, or when a regular scrape failed because content is behind JavaScript interaction. Also useful for authenticated scraping via profiles. Triggers on \"interact\", \"click\", \"fill out the form\", \"log in to\", \"sign in\", \"submit\", \"paginated\", \"next page\", \"infinite scroll\", \"interact with the page\", \"navigate to\", \"open a session\", or \"scrape failed\".\n",{"claudeCode":12},"firecrawl/cli","Firecrawl Interact","https://github.com/firecrawl/cli",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":240,"workflow":258},1778687114384.0718,"kn78xapmstygw616wvh6gbfta586mc3c","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":200,"practices":205,"prerequisites":209,"promptVersionExtension":213,"promptVersionScoring":214,"purpose":215,"rationale":216,"score":217,"summary":218,"tags":219,"targetMarket":225,"tier":226,"useCases":227,"workflow":233},[21,26,29,32,36,39,43,47,50,53,57,61,64,68,71,74,77,80,83,86,90,94,98,102,106,109,113,116,120,123,126,129,132,135,138,142,146,149,153,157,160,163,166,169,173,176,179,182,185,189],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly articulates the user problem of needing to interact with web pages beyond simple scraping, specifying scenarios like logging in, filling forms, and navigating complex flows.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill offers significant value by enabling interactive browser automation through natural language or code, going beyond basic scraping and providing fine-grained control for complex web interactions.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The extension provides a complete lifecycle for interacting with web pages, from scraping to advanced navigation and data extraction, suitable for real-world workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses specifically on browser interaction and data extraction after an initial scrape, maintaining a clear and coherent scope.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the capabilities of the 'interact' command, detailing its use cases and triggers.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The 'interact' command uses scoped actions like 'click', 'fill', and 'extract', rather than a single generalist execution tool.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All options and parameters for the 'interact' command, including the use of profiles and timeouts, are clearly documented in the SKILL.md.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","The 'interact' command is descriptively named and its functionality is clear.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","The command's parameters are well-defined, requesting only necessary information like prompts or code snippets, and outputs are focused on the interaction results.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The extension is distributed under a permissive MIT license, clearly indicated and usable.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The latest commit was on May 12, 2026, indicating recent maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and has a lockfile, indicating proper dependency management.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The extension does not appear to handle or expose secrets, operating on publicly accessible web content.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The interaction commands are designed to execute specific browser actions rather than arbitrary code from untrusted sources.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The extension relies on the Firecrawl CLI, which is installed via npm, and does not appear to fetch or execute untrusted external content at runtime.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","The interaction commands operate within the browser sandbox managed by the Firecrawl CLI, and do not modify files outside the project folder.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No evidence of detached-process spawns or deny-retry loops that could facilitate sandbox escape.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The extension interacts with web pages and does not appear to exfiltrate confidential data to third parties.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","Bundled content and descriptions appear free of hidden steering tricks or malicious Unicode characters.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The code executed via the `--code` option is plain and readable, not obfuscated.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The extension operates on web page content and does not make structural assumptions about the user's local project organization.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","With 4 issues opened and 1 closed in the last 90 days, the closure rate is 25%, and the number of open issues is low, indicating good maintainer engagement.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The CLI version is available and the installation instructions point to a specific version, indicating good release management.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Input parameters like prompts and code snippets are handled, and the underlying CLI likely performs necessary validation for web interactions.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The 'interact' command is primarily for state-changing web operations (like form fills) but is controlled by user prompts or code, not silent destructive operations.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The Firecrawl CLI handles errors robustly, providing clear messages and output formats for issues encountered during scraping or interaction.",{"category":110,"check":114,"severity":24,"summary":115},"Logging","The Firecrawl CLI provides detailed output and the ability to save results to files, allowing for audit trails of actions taken.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The extension interacts with public web content and does not appear to process personal data without sanitization.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The extension's functionality is global and does not exhibit any regional or jurisdictional limitations.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The CLI is cross-platform (npm installation) and does not appear to make OS-specific assumptions beyond standard browser automation dependencies.",{"category":44,"check":127,"severity":24,"summary":128},"README","A comprehensive README exists and clearly outlines the extension's purpose, installation, and usage.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The 'interact' command is a single, well-defined tool within the broader Firecrawl CLI.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","The 'interact' command focuses on a single core capability, avoiding near-synonym tool names.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All advertised features for the 'interact' command are implemented and accessible via the CLI.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","Clear installation instructions using npm are provided in the README, along with copy-pasteable examples.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","The Firecrawl CLI provides actionable error messages for common issues, aiding in troubleshooting.",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","The project utilizes npm and a lockfile, indicating pinned dependencies for reproducible builds.",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","The 'interact' command's primary function is to perform actions within a live browser session, making a dry-run preview not directly applicable.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The CLI has configurable timeouts for interactions, and the underlying browser automation likely handles retries gracefully.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","Telemetry is opt-in via an environment variable and documented, following best practices.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The purpose is precisely defined: to control and interact with a live browser session for specific web automation tasks beyond basic scraping.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise, clearly stating the name, description, and allowed tools.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md body is well-structured with clear sections and examples, avoiding unnecessary verbosity.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md is concise and links to external documentation for deeper details, adhering to progressive disclosure.",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","This skill's purpose is direct interaction, not deep exploration or code review, so 'context: fork' is not applicable.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","The SKILL.md provides clear, end-to-end examples for natural language prompts, code execution, and profile usage.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation mentions limitations like timeouts and the need for prior scraping, providing context for failure modes.",{"category":110,"check":183,"severity":151,"summary":184},"Tool Fallback","This skill relies on the main Firecrawl CLI and its internal browser automation, not external MCPs that would require fallback.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The system's reliance on specific browser states and user prompts implies a halt on unexpected or invalid states before performing actions.",{"category":91,"check":190,"severity":24,"summary":191},"Cross-skill coupling","The 'interact' skill is self-contained and clearly delineates its scope from other Firecrawl commands.",1778687114268,"This extension allows users to control a live browser session to click buttons, fill forms, navigate complex web flows, and extract data using natural language or code, building upon previous scrape operations.",[195,196,197,198,199],"Control live browser sessions","Fill forms and click buttons via prompts/code","Navigate multi-step web flows","Extract data from interacted pages","Persist browser state with profiles",[201,202,203,204],"Performing general web searches (use 'search' command)","Crawling entire websites (use 'crawl' command)","Performing bulk site downloads (use 'experimental download')","Simple static content scraping (use 'scrape' command)",[206,207,208],"Browser automation","Web interaction","Data extraction",[210,211,212],"Node.js installed","Firecrawl CLI installed (`npm install -g firecrawl-cli`)","A previous 'firecrawl scrape' command must have been run","3.0.0","4.4.0","To enable users to perform complex interactions with web pages that go beyond simple scraping, by controlling a live browser session for tasks like logging in, form submission, and navigating dynamic content.","All checks passed, with no critical or warning findings. The extension is well-documented, secure, and production-ready.",98,"A robust CLI tool for interactive browser automation and data extraction.",[220,221,222,223,224],"browser-automation","web-scraping","javascript-interaction","cli","developer-tools","global","verified",[228,229,230,231,232],"Logging into websites and authenticated scraping","Submitting forms and completing wizard-like flows","Handling pagination and infinite scroll","Interacting with JavaScript-heavy content","Recovering when standard scraping fails",[234,235,236,237,238,239],"Scrape a target URL using `firecrawl scrape`.","Initiate interaction with the scraped page using `firecrawl interact`.","Provide natural language prompts or executable code to control browser actions.","Extract desired data from the interacted page.","Optionally use profiles to persist browser state across sessions.","Stop the interaction session using `firecrawl interact stop` when done.",{"codeQuality":241,"collectedAt":243,"documentation":244,"maintenance":247,"popularity":254,"security":256,"testCoverage":257},{"hasLockfile":242},true,1778687082565,{"descriptionLength":245,"readmeSize":246},735,25712,{"closedIssues90d":248,"forks":249,"hasChangelog":250,"openIssues90d":251,"pushedAt":252,"stars":253},1,49,false,4,1778599393000,383,{"npmDownloads":255},51144,{"hasNpmPackage":242,"smitheryVerified":250},{"hasCi":242,"hasTests":242},{"updatedAt":259},1778687114384,{"basePath":261,"githubOwner":262,"githubRepo":223,"locale":18,"slug":263,"type":264},"skills/firecrawl-interact","firecrawl","firecrawl-interact","skill",{"_creationTime":266,"_id":267,"community":268,"display":269,"identity":272,"parentExtension":275,"providers":307,"relations":316,"tags":317,"workflow":318},1778686940775.5706,"k17axfavjpz72cd3qqzn86shb186ncqt",{"reviewCount":8},{"description":270,"installMethods":271,"name":262,"sourceUrl":14},"Scrape, search, crawl, and map the web with a single command.",{"claudeCode":262},{"basePath":273,"githubOwner":262,"githubRepo":223,"locale":18,"slug":223,"type":274},"","plugin",{"_creationTime":276,"_id":277,"community":278,"display":279,"identity":283,"providers":285,"relations":301,"tags":303,"workflow":304},1778686940775.5703,"k17be4khad1zr773wdg2m4yjhn86mjpr",{"reviewCount":8},{"description":280,"installMethods":281,"name":282,"sourceUrl":14},"CLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agents",{"claudeCode":12},"Firecrawl CLI",{"basePath":273,"githubOwner":262,"githubRepo":223,"locale":18,"slug":223,"type":284},"marketplace",{"evaluate":286,"extract":295},{"promptVersionExtension":287,"promptVersionScoring":214,"score":288,"tags":289,"targetMarket":225,"tier":226},"3.1.0",97,[221,223,290,291,292,293,294],"ai-agents","data-extraction","search","crawl","automation",{"commitSha":296,"license":297,"marketplace":298,"plugin":299},"HEAD","MIT",{"name":262,"pluginCount":248},{"mcpCount":8,"provider":300,"skillCount":8},"classify",{"repoId":302},"kd7csd1wb06dg9c1jfy5063f2586ne60",[290,294,223,293,291,292,221],{"evaluatedAt":305,"extractAt":306,"updatedAt":305},1778686962954,1778686940775,{"evaluate":308,"extract":313},{"promptVersionExtension":213,"promptVersionScoring":214,"score":309,"tags":310,"targetMarket":225,"tier":312},78,[221,223,294,291,292,293,311],"agent","community",{"commitSha":296,"plugin":314},{"mcpCount":8,"provider":300,"skillCount":315},9,{"parentExtensionId":277,"repoId":302},[311,294,223,293,291,292,221],{"evaluatedAt":319,"extractAt":306,"updatedAt":319},1778686985594,{"evaluate":321,"extract":323},{"promptVersionExtension":213,"promptVersionScoring":214,"score":217,"tags":322,"targetMarket":225,"tier":226},[220,221,222,223,224],{"commitSha":296,"license":297},{"parentExtensionId":267,"repoId":302},{"_creationTime":326,"_id":302,"identity":327,"providers":328,"workflow":503},1778686934511.6108,{"githubOwner":262,"githubRepo":223,"sourceUrl":14},{"classify":329,"discover":495,"extract":498,"github":499,"npm":502},{"commitSha":296,"extensions":330},[331,341,367,376,383,391,399,404,412,420,428,436],{"basePath":273,"displayName":262,"installMethods":332,"rationale":333,"selectedPaths":334,"source":340,"sourceLanguage":18,"type":284},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[335,338],{"path":336,"priority":337},".claude-plugin/marketplace.json","mandatory",{"path":339,"priority":337},"README.md","rule",{"basePath":273,"description":270,"displayName":262,"installMethods":342,"rationale":343,"selectedPaths":344,"source":340,"sourceLanguage":18,"type":274},{"claudeCode":262},"plugin manifest at .claude-plugin/plugin.json",[345,347,348,351,353,355,357,359,361,363,365],{"path":346,"priority":337},".claude-plugin/plugin.json",{"path":339,"priority":337},{"path":349,"priority":350},"skills/firecrawl-agent/SKILL.md","medium",{"path":352,"priority":350},"skills/firecrawl-cli/SKILL.md",{"path":354,"priority":350},"skills/firecrawl-crawl/SKILL.md",{"path":356,"priority":350},"skills/firecrawl-download/SKILL.md",{"path":358,"priority":350},"skills/firecrawl-interact/SKILL.md",{"path":360,"priority":350},"skills/firecrawl-map/SKILL.md",{"path":362,"priority":350},"skills/firecrawl-parse/SKILL.md",{"path":364,"priority":350},"skills/firecrawl-scrape/SKILL.md",{"path":366,"priority":350},"skills/firecrawl-search/SKILL.md",{"basePath":368,"description":369,"displayName":370,"installMethods":371,"rationale":372,"selectedPaths":373,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-agent","AI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, product listings, directory entries, or any data as JSON with a schema. Triggers on \"extract structured data\", \"get all the products\", \"pull pricing info\", \"extract as JSON\", or when the user provides a JSON schema for website data. More powerful than simple scraping for multi-page structured extraction.\n","firecrawl-agent",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-agent/SKILL.md",[374],{"path":375,"priority":337},"SKILL.md",{"basePath":377,"description":378,"displayName":262,"installMethods":379,"rationale":380,"selectedPaths":381,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-cli","Search, scrape, and interact with the web via the Firecrawl CLI. Use this skill whenever the user wants to search the web, find articles, research a topic, look something up online, scrape a webpage, grab content from a URL, get data from a website, crawl documentation, download a site, or interact with pages that need clicks or logins. Also use when they say \"fetch this page\", \"pull the content from\", \"get the page at https://\", or reference external websites. This provides real-time web search with full page content and interact capabilities — beyond what Claude can do natively with built-in tools. Do NOT trigger for local file operations, git commands, deployments, or code editing tasks.\n",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-cli/SKILL.md",[382],{"path":375,"priority":337},{"basePath":384,"description":385,"displayName":386,"installMethods":387,"rationale":388,"selectedPaths":389,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-crawl","Bulk extract content from an entire website or site section. Use this skill when the user wants to crawl a site, extract all pages from a docs section, bulk-scrape multiple pages following links, or says \"crawl\", \"get all the pages\", \"extract everything under /docs\", \"bulk extract\", or needs content from many pages on the same site. Handles depth limits, path filtering, and concurrent extraction.\n","firecrawl-crawl",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-crawl/SKILL.md",[390],{"path":375,"priority":337},{"basePath":392,"description":393,"displayName":394,"installMethods":395,"rationale":396,"selectedPaths":397,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-download","Download an entire website as local files — markdown, screenshots, or multiple formats per page. Use this skill when the user wants to save a site locally, download documentation for offline use, bulk-save pages as files, or says \"download the site\", \"save as local files\", \"offline copy\", \"download all the docs\", or \"save for reference\". Combines site mapping and scraping into organized local directories.\n","firecrawl-download",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-download/SKILL.md",[398],{"path":375,"priority":337},{"basePath":261,"description":10,"displayName":263,"installMethods":400,"rationale":401,"selectedPaths":402,"source":340,"sourceLanguage":18,"type":264},{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-interact/SKILL.md",[403],{"path":375,"priority":337},{"basePath":405,"description":406,"displayName":407,"installMethods":408,"rationale":409,"selectedPaths":410,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-map","Discover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where something is on a domain, or says \"map the site\", \"find the URL for\", \"what pages are on\", or \"list all pages\". Essential when the user knows which site but not which exact page.\n","firecrawl-map",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-map/SKILL.md",[411],{"path":375,"priority":337},{"basePath":413,"description":414,"displayName":415,"installMethods":416,"rationale":417,"selectedPaths":418,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-parse","Efficiently extract and convert the contents of any local file—such as PDF, DOCX, DOC, ODT, RTF, XLSX, XLS, or HTML—into clean, well-formatted markdown saved to disk. Use this skill whenever the user requests to parse, read, or extract information from a file on their computer, including phrases like “parse this PDF”, “convert this document”, “read this file”, “extract text from”, or when a local file path (not a URL) is provided. This skill offers advanced options like generating AI-powered summaries and answering questions based on the file's content. Prefer this tool over `scrape` when handling local files to deliver precise, structured outputs for downstream tasks.\n","firecrawl-parse",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-parse/SKILL.md",[419],{"path":375,"priority":337},{"basePath":421,"description":422,"displayName":423,"installMethods":424,"rationale":425,"selectedPaths":426,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-scrape","Extract clean markdown from any URL, including JavaScript-rendered SPAs. Use this skill whenever the user provides a URL and wants its content, says \"scrape\", \"grab\", \"fetch\", \"pull\", \"get the page\", \"extract from this URL\", or \"read this webpage\". Handles JS-rendered pages, multiple concurrent URLs, and returns LLM-optimized markdown. Use this instead of WebFetch for any webpage content extraction.\n","firecrawl-scrape",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-scrape/SKILL.md",[427],{"path":375,"priority":337},{"basePath":429,"description":430,"displayName":431,"installMethods":432,"rationale":433,"selectedPaths":434,"source":340,"sourceLanguage":18,"type":264},"skills/firecrawl-search","Web search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says \"search for\", \"find me\", \"look up\", \"what are people saying about\", or \"find articles about\". Returns real search results with optional full-page markdown — not just snippets. Provides capabilities beyond Claude's built-in WebSearch.\n","firecrawl-search",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-search/SKILL.md",[435],{"path":375,"priority":337},{"basePath":273,"description":437,"displayName":438,"installMethods":439,"license":440,"rationale":441,"selectedPaths":442,"source":340,"sourceLanguage":18,"type":223},"Command-line interface for Firecrawl. Scrape, crawl, and extract data from any website directly from your terminal.","firecrawl-cli",{"npm":438},"ISC","cli ecosystem detected at /",[443,445,446,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483,485,487,489,491,493],{"path":444,"priority":337},"package.json",{"path":339,"priority":337},{"path":447,"priority":448},"src/index.ts","low",{"path":450,"priority":448},"src/commands/agent.ts",{"path":452,"priority":448},"src/commands/browser.ts",{"path":454,"priority":448},"src/commands/config.ts",{"path":456,"priority":448},"src/commands/crawl.ts",{"path":458,"priority":448},"src/commands/create.ts",{"path":460,"priority":448},"src/commands/credit-usage.ts",{"path":462,"priority":448},"src/commands/env.ts",{"path":464,"priority":448},"src/commands/experimental/backends.ts",{"path":466,"priority":448},"src/commands/experimental/index.ts",{"path":468,"priority":448},"src/commands/experimental/shared.ts",{"path":470,"priority":448},"src/commands/init.ts",{"path":472,"priority":448},"src/commands/interact.ts",{"path":474,"priority":448},"src/commands/login.ts",{"path":476,"priority":448},"src/commands/logout.ts",{"path":478,"priority":448},"src/commands/map.ts",{"path":480,"priority":448},"src/commands/parse.ts",{"path":482,"priority":448},"src/commands/scrape.ts",{"path":484,"priority":448},"src/commands/search.ts",{"path":486,"priority":448},"src/commands/setup.ts",{"path":488,"priority":448},"src/commands/skills-install.ts",{"path":490,"priority":448},"src/commands/skills-native.ts",{"path":492,"priority":448},"src/commands/status.ts",{"path":494,"priority":448},"src/commands/version.ts",{"sources":496},[497],"manual",{"npmPackage":438},{"closedIssues90d":248,"description":280,"forks":249,"homepage":500,"openIssues90d":251,"pushedAt":252,"readmeSize":246,"stars":253,"topics":501},"http://docs.firecrawl.dev/cli",[],{"downloads":255},{"classifiedAt":504,"discoverAt":505,"extractAt":506,"githubAt":506,"npmAt":507,"updatedAt":504},1778686940560,1778686934511,1778686936677,1778686938425,[220,223,224,222,221],{"evaluatedAt":259,"extractAt":306,"updatedAt":259},[],[512,539,565,593,618,643],{"_creationTime":513,"_id":514,"community":515,"display":516,"identity":522,"providers":526,"relations":532,"tags":534,"workflow":535},1778697205743.894,"k17ej9360g7468qswf3svnrx9186m1ng",{"reviewCount":8},{"description":517,"installMethods":518,"name":520,"sourceUrl":521},"Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.",{"claudeCode":519},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":523,"githubOwner":524,"githubRepo":525,"locale":18,"slug":520,"type":264},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":527,"extract":531},{"promptVersionExtension":213,"promptVersionScoring":214,"score":528,"tags":529,"targetMarket":225,"tier":226},100,[220,221,530,223,294],"testing",{"commitSha":296},{"repoId":533},"kd74710g49kxgwbfjxeb7s132d86myxr",[294,220,223,530,221],{"evaluatedAt":536,"extractAt":537,"updatedAt":538},1778697222051,1778697205743,1778697438718,{"_creationTime":540,"_id":541,"community":542,"display":543,"identity":549,"providers":553,"relations":559,"tags":561,"workflow":562},1778696993586.7058,"k174ty9vbfgj7cv3v2szdwjgh986mrsf",{"reviewCount":8},{"description":544,"installMethods":545,"name":547,"sourceUrl":548},"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":546},"SeifBenayed/claude-code-sdk","chatgpt-search","https://github.com/SeifBenayed/claude-code-sdk",{"basePath":550,"githubOwner":551,"githubRepo":552,"locale":18,"slug":547,"type":264},".claude/skills/chatgpt-search","SeifBenayed","claude-code-sdk",{"evaluate":554,"extract":558},{"promptVersionExtension":213,"promptVersionScoring":214,"score":528,"tags":555,"targetMarket":225,"tier":226},[556,557,220,291,221],"chatgpt","scraping",{"commitSha":296},{"repoId":560},"kd78s53c1852h5p7c3qem663xs86njab",[220,556,291,557,221],{"evaluatedAt":563,"extractAt":564,"updatedAt":563},1778697026743,1778696993586,{"_creationTime":566,"_id":567,"community":568,"display":569,"identity":575,"providers":580,"relations":586,"tags":589,"workflow":590},1778683460321.381,"k1707rtzme0qezretvp3gmtfvn86n1k1",{"reviewCount":8},{"description":570,"installMethods":571,"name":573,"sourceUrl":574},"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":572},"browserbase/skills","AutoBrowse","https://github.com/browserbase/skills",{"basePath":576,"githubOwner":577,"githubRepo":578,"locale":18,"slug":579,"type":264},"skills/autobrowse","browserbase","skills","autobrowse",{"evaluate":581,"extract":585},{"promptVersionExtension":213,"promptVersionScoring":214,"score":528,"tags":582,"targetMarket":225,"tier":226},[220,221,583,530,584],"llm-agent","node-js",{"commitSha":296,"license":297},{"parentExtensionId":587,"repoId":588},"k17bx77jb71yrwatep2nb43r0d86m6cb","kd77wvcdm5fq9xp8hk6ppm832s86myxr",[220,583,584,530,221],{"evaluatedAt":591,"extractAt":592,"updatedAt":591},1778683610531,1778683460321,{"_creationTime":594,"_id":595,"community":596,"display":597,"identity":603,"providers":607,"relations":612,"tags":614,"workflow":615},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":598,"installMethods":599,"name":601,"sourceUrl":602},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":600},"steipete/clawdis","github","https://github.com/steipete/clawdis",{"basePath":604,"githubOwner":605,"githubRepo":606,"locale":18,"slug":601,"type":264},"skills/github","steipete","clawdis",{"evaluate":608,"extract":611},{"promptVersionExtension":213,"promptVersionScoring":214,"score":528,"tags":609,"targetMarket":225,"tier":226},[601,223,610,224,294],"api",{"commitSha":296},{"repoId":613},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[610,294,223,224,601],{"evaluatedAt":616,"extractAt":617,"updatedAt":616},1778698569289,1778697652123,{"_creationTime":619,"_id":620,"community":621,"display":622,"identity":628,"providers":631,"relations":637,"tags":639,"workflow":640},1778695021936.555,"k1715rn9402s29yge55y9nt0x986n2tf",{"reviewCount":8},{"description":623,"installMethods":624,"name":626,"sourceUrl":627},"Build a composable CLI for Codex from API docs, an OpenAPI spec, existing curl examples, an SDK, a web app, an admin tool, or a local script. Use when the user wants Codex to create a command-line tool that can run from any repo, expose composable read/write commands, return stable JSON, manage auth, and pair with a companion skill.",{"claudeCode":625},"openai/skills","cli-creator","https://github.com/openai/skills",{"basePath":629,"githubOwner":630,"githubRepo":578,"locale":18,"slug":626,"type":264},"skills/.curated/cli-creator","openai",{"evaluate":632,"extract":636},{"promptVersionExtension":213,"promptVersionScoring":214,"score":528,"tags":633,"targetMarket":225,"tier":226},[223,634,224,635,294],"code-generation","codex",{"commitSha":296},{"repoId":638},"kd75n2zj3yh472p25zffgycved86mnpx",[294,223,634,635,224],{"evaluatedAt":641,"extractAt":642,"updatedAt":641},1778695068759,1778695021936,{"_creationTime":644,"_id":645,"community":646,"display":647,"identity":653,"providers":657,"relations":664,"tags":667,"workflow":668},1778696691708.3125,"k1704t5mbdhdjkqqyvh15rz98986n4b0",{"reviewCount":8},{"description":648,"installMethods":649,"name":651,"sourceUrl":652},"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":650},"ruvnet/ruflo","browser-extract","https://github.com/ruvnet/ruflo",{"basePath":654,"githubOwner":655,"githubRepo":656,"locale":18,"slug":651,"type":264},"plugins/ruflo-browser/skills/browser-extract","ruvnet","ruflo",{"evaluate":658,"extract":663},{"promptVersionExtension":213,"promptVersionScoring":214,"score":659,"tags":660,"targetMarket":225,"tier":226},99,[221,291,220,661,662],"security","pii-detection",{"commitSha":296},{"parentExtensionId":665,"repoId":666},"k171keecmm9hg25jek1v0vqawd86ntq2","kd7ed28gj8n0y3msk5dzrp05zs86nqtc",[220,291,662,661,221],{"evaluatedAt":669,"extractAt":670,"updatedAt":669},1778699898275,1778696691708]