[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-firecrawl-firecrawl-search-en":3,"guides-for-firecrawl-firecrawl-search":500,"similar-k1763fmwvnx4jva5z2b3mfb75n86mhqf-en":501},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":255,"isFallback":245,"parentExtension":260,"providers":310,"relations":314,"repo":315,"tags":498,"workflow":499},1778686940775.5728,"k1763fmwvnx4jva5z2b3mfb75n86mhqf",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"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",{"claudeCode":12},"firecrawl/cli","Firecrawl CLI","https://github.com/firecrawl/cli",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":235,"workflow":253},1778687239795.4355,"kn7cfrk4299y7ghr3pm93xqj6s86mt51","en",{"checks":20,"evaluatedAt":192,"extensionSummary":193,"features":194,"nonGoals":202,"practices":206,"prerequisites":207,"promptVersionExtension":208,"promptVersionScoring":209,"purpose":210,"rationale":211,"score":212,"summary":213,"tags":214,"targetMarket":222,"tier":223,"useCases":224,"workflow":229},[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 states the problem of needing web search with full page content extraction and names specific user intents and actions.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The extension offers capabilities beyond the built-in WebSearch by providing full page content extraction and advanced search options, differentiating it from a simple wrapper.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The CLI tool is fully implemented and appears ready for production use, covering search, scraping, and providing various output formats and options.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The extension focuses on web search and content extraction, with related subcommands like scraping, mapping, and crawling, all within the domain of web data retrieval.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the extension's capabilities, highlighting full page extraction and differentiating it from built-in search.",{"category":40,"check":41,"severity":24,"summary":42},"Invocation","Scoped tools","The CLI provides narrowly scoped commands like `search`, `scrape`, `map`, and `crawl`, making them easier for the agent to select.",{"category":44,"check":45,"severity":24,"summary":46},"Documentation","Configuration & parameter reference","All options and parameters for commands like `search` and `scrape` are well-documented in the README, including descriptions and defaults where applicable.",{"category":33,"check":48,"severity":24,"summary":49},"Tool naming","All exposed commands (`search`, `scrape`, `map`, `crawl`, `agent`, `interact`, `credit-usage`, `config`, `view-config`, `login`, `logout`) are descriptive and follow kebab-case convention.",{"category":33,"check":51,"severity":24,"summary":52},"Minimal I/O surface","Command options are specific and well-defined, requesting only necessary parameters, and outputs are structured (JSON, markdown) without excessive internal details.",{"category":54,"check":55,"severity":24,"summary":56},"License","License usability","The project is licensed under the MIT license, which is a permissive open-source license.",{"category":58,"check":59,"severity":24,"summary":60},"Maintenance","Commit recency","The last commit was on May 12, 2026, which is very recent, indicating active maintenance.",{"category":58,"check":62,"severity":24,"summary":63},"Dependency Management","The project uses npm and lists dependencies in `package.json`, with a lockfile present, suggesting good dependency management practices.",{"category":65,"check":66,"severity":24,"summary":67},"Security","Secret Management","The CLI handles API keys via environment variables or command-line arguments, and the `login` command manages credentials securely without echoing them to stdout.",{"category":65,"check":69,"severity":24,"summary":70},"Injection","The CLI treats user input for search queries and URLs as data, and scrape formats are specified, mitigating injection risks. No evidence of executing arbitrary code from external sources.",{"category":65,"check":72,"severity":24,"summary":73},"Transitive Supply-Chain Grenades","The CLI installs via npm and does not appear to fetch or execute remote code at runtime. Dependencies are bundled. WebFetch in the agent/skill context is handled by Firecrawl's backend, not the CLI itself.",{"category":65,"check":75,"severity":24,"summary":76},"Sandbox Isolation","As a CLI tool, it operates within the user's terminal environment. It does not attempt to modify files outside its own configuration directory or project scope without explicit user action.",{"category":65,"check":78,"severity":24,"summary":79},"Sandbox escape primitives","No evidence of detached processes or retry loops around denied tool calls in the CLI's operation.",{"category":65,"check":81,"severity":24,"summary":82},"Data Exfiltration","The tool collects anonymous telemetry opt-in and requires explicit API key input for authenticated requests. No sensitive data is exfiltrated without user action or consent.",{"category":65,"check":84,"severity":24,"summary":85},"Hidden Text Tricks","The README and SKILL.md files do not contain hidden text, invisible characters, or other tricks to manipulate the model.",{"category":87,"check":88,"severity":24,"summary":89},"Hooks","Opaque code execution","The CLI is distributed as an npm package and its scripts are standard JavaScript, not obfuscated or dynamically fetched and executed.",{"category":91,"check":92,"severity":24,"summary":93},"Portability","Structural Assumption","The CLI operates on URLs and file paths provided by the user. It defaults to saving output in `.firecrawl/` but allows specifying other paths, without making rigid assumptions about project structure.",{"category":95,"check":96,"severity":24,"summary":97},"Trust","Issues Attention","Open issues (4) vs closed issues (1) in the last 90 days indicate active maintenance, with a reasonable closure rate.",{"category":99,"check":100,"severity":24,"summary":101},"Versioning","Release Management","The CLI has a clear versioning scheme (e.g., v1.16.2) and is distributed via npm, allowing for version pinning.",{"category":103,"check":104,"severity":24,"summary":105},"Execution","Validation","Command-line arguments and output formats are validated. For instance, URL inputs are processed, and output formats are constrained.",{"category":65,"check":107,"severity":24,"summary":108},"Unguarded Destructive Operations","The CLI performs read operations (search, scrape) and data extraction. Operations like file writes are user-directed via `-o` and do not appear to be destructive without explicit user intent.",{"category":110,"check":111,"severity":24,"summary":112},"Code Execution","Error Handling","The CLI provides clear error messages for invalid commands, authentication failures, and rate limits, guiding the user towards remediation.",{"category":110,"check":114,"severity":24,"summary":115},"Logging","The tool logs its status (authentication, credits) via `--status` and provides output to stdout or files. It does not log commands or their results to a persistent audit file by default.",{"category":117,"check":118,"severity":24,"summary":119},"Compliance","GDPR","The tool collects opt-in anonymous telemetry. It does not operate on personal data unless provided by the user via URLs or prompts, and any data sent to Firecrawl's API is handled by their privacy policy.",{"category":117,"check":121,"severity":24,"summary":122},"Target market","The tool is a general-purpose web scraping and search utility with no apparent regional or jurisdictional limitations. `targetMarket` is global.",{"category":91,"check":124,"severity":24,"summary":125},"Runtime stability","The CLI is distributed as an npm package and should be compatible with any system that has Node.js installed, with no apparent OS-specific dependencies.",{"category":44,"check":127,"severity":24,"summary":128},"README","A comprehensive README file exists and clearly states the extension's purpose, installation, and usage instructions.",{"category":33,"check":130,"severity":24,"summary":131},"Tool surface size","The CLI exposes a reasonable number of distinct commands (10 main commands, plus experimental) suitable for its purpose.",{"category":40,"check":133,"severity":24,"summary":134},"Overlapping near-synonym tools","Command names like `search` and `scrape` are distinct, and other commands like `map` and `crawl` represent separate functionalities, avoiding near-synonyms.",{"category":44,"check":136,"severity":24,"summary":137},"Phantom features","All features advertised in the README and SKILL.md (search, scrape, crawl, agent, interact) have corresponding implemented commands.",{"category":139,"check":140,"severity":24,"summary":141},"Install","Installation instruction","The README provides clear npm installation instructions and multiple copy-pasteable invocation examples for various commands.",{"category":143,"check":144,"severity":24,"summary":145},"Errors","Actionable error messages","Errors provide specific details (e.g., invalid arguments, auth issues, rate limits) and suggest remediation steps like checking API keys or bandwidth.",{"category":103,"check":147,"severity":24,"summary":148},"Pinned dependencies","The project includes a `package-lock.json` file, indicating pinned dependencies for reproducible builds.",{"category":33,"check":150,"severity":151,"summary":152},"Dry-run preview","not_applicable","The tool's primary functions are data retrieval (search, scrape) and file output, not destructive operations, so a dry-run mode is not applicable.",{"category":154,"check":155,"severity":24,"summary":156},"Protocol","Idempotent retry & timeouts","The `search` and `agent` commands have options for timeouts (`--timeout`) and webhook notifications, implying some retry/completion handling, though explicit idempotency on mutations isn't applicable here.",{"category":117,"check":158,"severity":24,"summary":159},"Telemetry opt-in","Telemetry is explicitly opt-in via an environment variable (`FIRECRAWL_NO_TELEMETRY=1`) and is described as anonymous usage data, not command data or contents.",{"category":40,"check":161,"severity":24,"summary":162},"Precise Purpose","The skill's purpose is precisely defined as web search with full page extraction, with clear triggers and boundaries outlined.",{"category":40,"check":164,"severity":24,"summary":165},"Concise Frontmatter","The SKILL.md frontmatter is concise, self-contained, and accurately summarizes the core capability with relevant trigger phrases.",{"category":44,"check":167,"severity":24,"summary":168},"Concise Body","The SKILL.md file is well-structured, delegating deeper material to the README and maintaining conciseness.",{"category":170,"check":171,"severity":24,"summary":172},"Context","Progressive Disclosure","The SKILL.md is concise and links to the extensive README for detailed usage, options, and examples, employing progressive disclosure.",{"category":170,"check":174,"severity":151,"summary":175},"Forked exploration","This is a CLI tool and not an exploration-heavy skill; it does not use `context: fork`.",{"category":22,"check":177,"severity":24,"summary":178},"Usage examples","Both the SKILL.md and README provide numerous end-to-end examples covering basic and advanced usage of all commands.",{"category":22,"check":180,"severity":24,"summary":181},"Edge cases","The documentation addresses limitations like agent task duration and cost, and mentions handling invalid URLs. Error messages also cover failure modes.",{"category":110,"check":183,"severity":151,"summary":184},"Tool Fallback","This is a standalone CLI tool and does not rely on external MCP servers or tools that would require a fallback.",{"category":186,"check":187,"severity":24,"summary":188},"Safety","Halt on unexpected state","The CLI exits with clear error messages for invalid states like authentication failures or missing arguments, effectively halting on unexpected pre-state.",{"category":91,"check":190,"severity":151,"summary":191},"Cross-skill coupling","This CLI tool operates standalone and does not implicitly rely on other skills being loaded.",1778687239441,"Firecrawl CLI is a command-line interface for web data extraction, offering capabilities for searching the web, scraping full page content from URLs, discovering all URLs on a site, crawling websites, and running AI agents for autonomous data extraction.",[195,196,197,198,199,200,201],"Web search with full page content extraction","Scraping specific URLs or multiple URLs","Discovering all URLs on a website","Crawling entire websites","AI agent for autonomous web data extraction","Interactive browser session for page interaction","Configuration for API keys and self-hosted instances",[203,204,205],"Replacing a user's browser for general browsing","Performing destructive operations on websites","Storing or managing user-specific browsing history beyond session profiles",[],[],"3.0.0","4.4.0","To provide developers and users with a powerful, scriptable tool for efficiently retrieving and processing web content directly from the terminal.","Excellent documentation, active maintenance, and a clear scope with well-defined tools result in a high score. Minor areas like explicit idempotency guidance for mutations are not applicable to this read-focused CLI.",97,"Highly polished CLI for web scraping and search with excellent documentation and active maintenance.",[215,216,217,218,219,220,221],"web-scraping","search","cli","data-extraction","automation","research","content-analysis","global","verified",[225,226,227,228],"Researching topics and gathering information from the web","Extracting structured data from websites for analysis","Automating the process of finding and collecting web content","Building applications that require real-time web data",[230,231,232,233,234],"User specifies a web-related task (search, scrape, crawl, agent).","User provides query, URL(s), schema, or prompts.","CLI tool processes the input, potentially authenticating with Firecrawl API.","CLI executes the task using Firecrawl's backend services.","Results are outputted to stdout, a specified file, or processed via agent/interact sessions.",{"codeQuality":236,"collectedAt":238,"documentation":239,"maintenance":242,"popularity":249,"security":251,"testCoverage":252},{"hasLockfile":237},true,1778687210276,{"descriptionLength":240,"readmeSize":241},433,25712,{"closedIssues90d":243,"forks":244,"hasChangelog":245,"openIssues90d":246,"pushedAt":247,"stars":248},1,49,false,4,1778599393000,383,{"npmDownloads":250},51144,{"hasNpmPackage":237,"smitheryVerified":245},{"hasCi":237,"hasTests":237},{"updatedAt":254},1778687239795,{"basePath":256,"githubOwner":257,"githubRepo":217,"locale":18,"slug":258,"type":259},"skills/firecrawl-search","firecrawl","firecrawl-search","skill",{"_creationTime":261,"_id":262,"community":263,"display":264,"identity":267,"parentExtension":270,"providers":297,"relations":306,"tags":307,"workflow":308},1778686940775.5706,"k17axfavjpz72cd3qqzn86shb186ncqt",{"reviewCount":8},{"description":265,"installMethods":266,"name":257,"sourceUrl":14},"Scrape, search, crawl, and map the web with a single command.",{"claudeCode":257},{"basePath":268,"githubOwner":257,"githubRepo":217,"locale":18,"slug":217,"type":269},"","plugin",{"_creationTime":271,"_id":272,"community":273,"display":274,"identity":277,"providers":279,"relations":291,"tags":293,"workflow":294},1778686940775.5703,"k17be4khad1zr773wdg2m4yjhn86mjpr",{"reviewCount":8},{"description":275,"installMethods":276,"name":13,"sourceUrl":14},"CLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agents",{"claudeCode":12},{"basePath":268,"githubOwner":257,"githubRepo":217,"locale":18,"slug":217,"type":278},"marketplace",{"evaluate":280,"extract":285},{"promptVersionExtension":281,"promptVersionScoring":209,"score":212,"tags":282,"targetMarket":222,"tier":223},"3.1.0",[215,217,283,218,216,284,219],"ai-agents","crawl",{"commitSha":286,"license":287,"marketplace":288,"plugin":289},"HEAD","MIT",{"name":257,"pluginCount":243},{"mcpCount":8,"provider":290,"skillCount":8},"classify",{"repoId":292},"kd7csd1wb06dg9c1jfy5063f2586ne60",[283,219,217,284,218,216,215],{"evaluatedAt":295,"extractAt":296,"updatedAt":295},1778686962954,1778686940775,{"evaluate":298,"extract":303},{"promptVersionExtension":208,"promptVersionScoring":209,"score":299,"tags":300,"targetMarket":222,"tier":302},78,[215,217,219,218,216,284,301],"agent","community",{"commitSha":286,"plugin":304},{"mcpCount":8,"provider":290,"skillCount":305},9,{"parentExtensionId":272,"repoId":292},[301,219,217,284,218,216,215],{"evaluatedAt":309,"extractAt":296,"updatedAt":309},1778686985594,{"evaluate":311,"extract":313},{"promptVersionExtension":208,"promptVersionScoring":209,"score":212,"tags":312,"targetMarket":222,"tier":223},[215,216,217,218,219,220,221],{"commitSha":286,"license":287},{"parentExtensionId":262,"repoId":292},{"_creationTime":316,"_id":292,"identity":317,"providers":318,"workflow":493},1778686934511.6108,{"githubOwner":257,"githubRepo":217,"sourceUrl":14},{"classify":319,"discover":485,"extract":488,"github":489,"npm":492},{"commitSha":286,"extensions":320},[321,331,357,366,373,381,389,397,405,413,421,426],{"basePath":268,"displayName":257,"installMethods":322,"rationale":323,"selectedPaths":324,"source":330,"sourceLanguage":18,"type":278},{"claudeCode":12},"marketplace.json at .claude-plugin/marketplace.json",[325,328],{"path":326,"priority":327},".claude-plugin/marketplace.json","mandatory",{"path":329,"priority":327},"README.md","rule",{"basePath":268,"description":265,"displayName":257,"installMethods":332,"rationale":333,"selectedPaths":334,"source":330,"sourceLanguage":18,"type":269},{"claudeCode":257},"plugin manifest at .claude-plugin/plugin.json",[335,337,338,341,343,345,347,349,351,353,355],{"path":336,"priority":327},".claude-plugin/plugin.json",{"path":329,"priority":327},{"path":339,"priority":340},"skills/firecrawl-agent/SKILL.md","medium",{"path":342,"priority":340},"skills/firecrawl-cli/SKILL.md",{"path":344,"priority":340},"skills/firecrawl-crawl/SKILL.md",{"path":346,"priority":340},"skills/firecrawl-download/SKILL.md",{"path":348,"priority":340},"skills/firecrawl-interact/SKILL.md",{"path":350,"priority":340},"skills/firecrawl-map/SKILL.md",{"path":352,"priority":340},"skills/firecrawl-parse/SKILL.md",{"path":354,"priority":340},"skills/firecrawl-scrape/SKILL.md",{"path":356,"priority":340},"skills/firecrawl-search/SKILL.md",{"basePath":358,"description":359,"displayName":360,"installMethods":361,"rationale":362,"selectedPaths":363,"source":330,"sourceLanguage":18,"type":259},"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",[364],{"path":365,"priority":327},"SKILL.md",{"basePath":367,"description":368,"displayName":257,"installMethods":369,"rationale":370,"selectedPaths":371,"source":330,"sourceLanguage":18,"type":259},"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",[372],{"path":365,"priority":327},{"basePath":374,"description":375,"displayName":376,"installMethods":377,"rationale":378,"selectedPaths":379,"source":330,"sourceLanguage":18,"type":259},"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",[380],{"path":365,"priority":327},{"basePath":382,"description":383,"displayName":384,"installMethods":385,"rationale":386,"selectedPaths":387,"source":330,"sourceLanguage":18,"type":259},"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",[388],{"path":365,"priority":327},{"basePath":390,"description":391,"displayName":392,"installMethods":393,"rationale":394,"selectedPaths":395,"source":330,"sourceLanguage":18,"type":259},"skills/firecrawl-interact","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","firecrawl-interact",{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-interact/SKILL.md",[396],{"path":365,"priority":327},{"basePath":398,"description":399,"displayName":400,"installMethods":401,"rationale":402,"selectedPaths":403,"source":330,"sourceLanguage":18,"type":259},"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",[404],{"path":365,"priority":327},{"basePath":406,"description":407,"displayName":408,"installMethods":409,"rationale":410,"selectedPaths":411,"source":330,"sourceLanguage":18,"type":259},"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",[412],{"path":365,"priority":327},{"basePath":414,"description":415,"displayName":416,"installMethods":417,"rationale":418,"selectedPaths":419,"source":330,"sourceLanguage":18,"type":259},"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",[420],{"path":365,"priority":327},{"basePath":256,"description":10,"displayName":258,"installMethods":422,"rationale":423,"selectedPaths":424,"source":330,"sourceLanguage":18,"type":259},{"claudeCode":12},"SKILL.md frontmatter at skills/firecrawl-search/SKILL.md",[425],{"path":365,"priority":327},{"basePath":268,"description":427,"displayName":428,"installMethods":429,"license":430,"rationale":431,"selectedPaths":432,"source":330,"sourceLanguage":18,"type":217},"Command-line interface for Firecrawl. Scrape, crawl, and extract data from any website directly from your terminal.","firecrawl-cli",{"npm":428},"ISC","cli ecosystem detected at /",[433,435,436,439,441,443,445,447,449,451,453,455,457,459,461,463,465,467,469,471,473,475,477,479,481,483],{"path":434,"priority":327},"package.json",{"path":329,"priority":327},{"path":437,"priority":438},"src/index.ts","low",{"path":440,"priority":438},"src/commands/agent.ts",{"path":442,"priority":438},"src/commands/browser.ts",{"path":444,"priority":438},"src/commands/config.ts",{"path":446,"priority":438},"src/commands/crawl.ts",{"path":448,"priority":438},"src/commands/create.ts",{"path":450,"priority":438},"src/commands/credit-usage.ts",{"path":452,"priority":438},"src/commands/env.ts",{"path":454,"priority":438},"src/commands/experimental/backends.ts",{"path":456,"priority":438},"src/commands/experimental/index.ts",{"path":458,"priority":438},"src/commands/experimental/shared.ts",{"path":460,"priority":438},"src/commands/init.ts",{"path":462,"priority":438},"src/commands/interact.ts",{"path":464,"priority":438},"src/commands/login.ts",{"path":466,"priority":438},"src/commands/logout.ts",{"path":468,"priority":438},"src/commands/map.ts",{"path":470,"priority":438},"src/commands/parse.ts",{"path":472,"priority":438},"src/commands/scrape.ts",{"path":474,"priority":438},"src/commands/search.ts",{"path":476,"priority":438},"src/commands/setup.ts",{"path":478,"priority":438},"src/commands/skills-install.ts",{"path":480,"priority":438},"src/commands/skills-native.ts",{"path":482,"priority":438},"src/commands/status.ts",{"path":484,"priority":438},"src/commands/version.ts",{"sources":486},[487],"manual",{"npmPackage":428},{"closedIssues90d":243,"description":275,"forks":244,"homepage":490,"openIssues90d":246,"pushedAt":247,"readmeSize":241,"stars":248,"topics":491},"http://docs.firecrawl.dev/cli",[],{"downloads":250},{"classifiedAt":494,"discoverAt":495,"extractAt":496,"githubAt":496,"npmAt":497,"updatedAt":494},1778686940560,1778686934511,1778686936677,1778686938425,[219,217,221,218,220,216,215],{"evaluatedAt":254,"extractAt":296,"updatedAt":254},[],[502,530,561,583,609,629],{"_creationTime":503,"_id":504,"community":505,"display":506,"identity":512,"providers":516,"relations":523,"tags":525,"workflow":526},1778697205743.894,"k17ej9360g7468qswf3svnrx9186m1ng",{"reviewCount":8},{"description":507,"installMethods":508,"name":510,"sourceUrl":511},"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":509},"shanraisshan/claude-code-best-practice","agent-browser","https://github.com/shanraisshan/claude-code-best-practice",{"basePath":513,"githubOwner":514,"githubRepo":515,"locale":18,"slug":510,"type":259},".claude/skills/agent-browser","shanraisshan","claude-code-best-practice",{"evaluate":517,"extract":522},{"promptVersionExtension":208,"promptVersionScoring":209,"score":518,"tags":519,"targetMarket":222,"tier":223},100,[520,215,521,217,219],"browser-automation","testing",{"commitSha":286},{"repoId":524},"kd74710g49kxgwbfjxeb7s132d86myxr",[219,520,217,521,215],{"evaluatedAt":527,"extractAt":528,"updatedAt":529},1778697222051,1778697205743,1778697438718,{"_creationTime":531,"_id":532,"community":533,"display":534,"identity":540,"providers":545,"relations":554,"tags":557,"workflow":558},1778699234184.6157,"k177tdbfgqmwhtaqv771f2ych586nne9",{"reviewCount":8},{"description":535,"installMethods":536,"name":538,"sourceUrl":539},"Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions",{"claudeCode":537},"Yeachan-Heo/oh-my-claudecode","Project Session Manager","https://github.com/Yeachan-Heo/oh-my-claudecode",{"basePath":541,"githubOwner":542,"githubRepo":543,"locale":18,"slug":544,"type":259},"skills/project-session-manager","Yeachan-Heo","oh-my-claudecode","project-session-manager",{"evaluate":546,"extract":553},{"promptVersionExtension":208,"promptVersionScoring":209,"score":518,"tags":547,"targetMarket":222,"tier":223},[548,549,550,551,219,217,552],"git","development-environment","workflow","tmux","developer-tool",{"commitSha":286,"license":287},{"parentExtensionId":555,"repoId":556},"k17brg5egdw1jbncj1j4wfv3fh86n639","kd74zv63fryf9prygtq7gf4es986n22y",[219,217,552,549,548,551,550],{"evaluatedAt":559,"extractAt":560,"updatedAt":559},1778699613343,1778699234184,{"_creationTime":562,"_id":563,"community":564,"display":565,"identity":568,"providers":571,"relations":579,"tags":580,"workflow":581},1778699234184.611,"k179b6dkc777g1rgyecze04wqn86m6y4",{"reviewCount":8},{"description":566,"installMethods":567,"name":543,"sourceUrl":539},"Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly",{"claudeCode":537},{"basePath":569,"githubOwner":542,"githubRepo":543,"locale":18,"slug":570,"type":259},"skills/ask","ask",{"evaluate":572,"extract":578},{"promptVersionExtension":208,"promptVersionScoring":209,"score":518,"tags":573,"targetMarket":222,"tier":223},[217,219,574,575,576,577],"llm","prompting","code-review","artifact-generation",{"commitSha":286,"license":287},{"parentExtensionId":555,"repoId":556},[577,219,217,576,574,575],{"evaluatedAt":582,"extractAt":560,"updatedAt":582},1778699303045,{"_creationTime":584,"_id":585,"community":586,"display":587,"identity":593,"providers":597,"relations":603,"tags":605,"workflow":606},1778697652123.8928,"k171pew5empzzrfghyg9nqrk6n86nqa9",{"reviewCount":8},{"description":588,"installMethods":589,"name":591,"sourceUrl":592},"Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.",{"claudeCode":590},"steipete/clawdis","github","https://github.com/steipete/clawdis",{"basePath":594,"githubOwner":595,"githubRepo":596,"locale":18,"slug":591,"type":259},"skills/github","steipete","clawdis",{"evaluate":598,"extract":602},{"promptVersionExtension":208,"promptVersionScoring":209,"score":518,"tags":599,"targetMarket":222,"tier":223},[591,217,600,601,219],"api","developer-tools",{"commitSha":286},{"repoId":604},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[600,219,217,601,591],{"evaluatedAt":607,"extractAt":608,"updatedAt":607},1778698569289,1778697652123,{"_creationTime":610,"_id":611,"community":612,"display":613,"identity":617,"providers":619,"relations":625,"tags":626,"workflow":627},1778697652123.8857,"k179k1n5nw0md1x1j3dak31evn86mb5f",{"reviewCount":8},{"description":614,"installMethods":615,"name":616,"sourceUrl":592},"Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.",{"claudeCode":590},"telegram-crabbox-e2e-proof",{"basePath":618,"githubOwner":595,"githubRepo":596,"locale":18,"slug":616,"type":259},".agents/skills/telegram-crabbox-e2e-proof",{"evaluate":620,"extract":624},{"promptVersionExtension":208,"promptVersionScoring":209,"score":518,"tags":621,"targetMarket":222,"tier":223},[521,622,219,623,217],"telegram","qa",{"commitSha":286},{"repoId":604},[219,217,623,622,521],{"evaluatedAt":628,"extractAt":608,"updatedAt":628},1778698038113,{"_creationTime":630,"_id":631,"community":632,"display":633,"identity":639,"providers":643,"relations":650,"tags":653,"workflow":654},1778696833339.6243,"k174g80xa9zxhydbncvpf0xzy986nvx5",{"reviewCount":8},{"description":634,"installMethods":635,"name":637,"sourceUrl":638},"Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.",{"claudeCode":636},"sanjay3290/ai-skills","manus","https://github.com/sanjay3290/ai-skills",{"basePath":640,"githubOwner":641,"githubRepo":642,"locale":18,"slug":637,"type":259},"skills/manus","sanjay3290","ai-skills",{"evaluate":644,"extract":649},{"promptVersionExtension":208,"promptVersionScoring":209,"score":518,"tags":645,"targetMarket":222,"tier":223},[646,647,220,219,648],"ai-agent","autonomous-execution","api-integration",{"commitSha":286},{"parentExtensionId":651,"repoId":652},"k17es37z10n1sw6t2m3f0vsydx86mnje","kd71np0fyqg23qg8w2hcfw0h0h86nkn0",[646,648,219,647,220],{"evaluatedAt":655,"extractAt":656,"updatedAt":655},1778697107270,1778696833339]