[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-firecrawl-structured-extraction":3,"mdc--v0mgz2-key":31,"related-org-firecrawl-structured-extraction":302,"related-repo-firecrawl-structured-extraction":458},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":20,"repoUrl":21,"updatedAt":22,"license":23,"forks":24,"topics":25,"repo":26,"sourceUrl":29,"mdContent":30},"structured-extraction","extract structured data from websites","Extract structured data matching a JSON schema from websites. Handles complex nested schemas, arrays, pagination, and validation. Always outputs via formatOutput.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"firecrawl","Firecrawl","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Ffirecrawl.png",[12,16,19],{"name":13,"slug":14,"type":15},"Data Engineering","data-engineering","tag",{"name":17,"slug":18,"type":15},"Web Scraping","web-scraping",{"name":9,"slug":8,"type":15},1130,"https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Fweb-agent","2026-05-15T06:15:32.092034",null,157,[],{"repoUrl":21,"stars":20,"forks":24,"topics":27,"description":28},[],"🔥 Open-source web data agent optimized for structured web research","https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Fweb-agent\u002Ftree\u002FHEAD\u002Fagent-core\u002Fsrc\u002Fskills\u002Fdefinitions\u002Fstructured-extraction","---\nname: structured-extraction\ndescription: Extract structured data matching a JSON schema from websites. Handles complex nested schemas, arrays, pagination, and validation. Always outputs via formatOutput.\ncategory: Research\n---\n\n# Structured Extraction\n\nUse this skill when extracting data that must match a specific JSON schema.\n\n## Strategy by task type\n\n### Simple query (single fact or small object)\n1. Search for relevant results.\n2. Scrape promising results with a targeted query.\n3. Build the result object and call formatOutput immediately.\n\n### Single target research (one entity, multiple fields)\n1. Search for relevant URLs.\n2. Scrape to extract data — stay in the orchestrator unless you have many independent sources (roughly 5+) where parallel workers clearly help.\n3. Compile findings and call formatOutput.\n\n### List of items (array in schema)\n1. Search\u002Fscrape to get the list of items.\n2. Are all requested details included in the list?\n   - Yes: Build the result and call formatOutput.\n   - No: If there are many items (roughly 5+), use spawnAgents so each worker gets the item and fields; otherwise fetch details sequentially in the orchestrator.\n3. Aggregate all results and call formatOutput.\n\n### All items from a website\n1. Check sitemaps (sitemap.xml, robots.txt) for an easy route to all pages.\n2. Scrape the entry page. Determine: pagination? Categories? Subcategories?\n3. For pagination, use interact to click through every page.\n4. For categories, scrape each category — use spawnAgents only when many independent categories warrant parallel fan-out.\n5. Aggregate and call formatOutput.\n\n## Scraping for structured data\n- PREFER scrape with a targeted query over raw page dumps. It keeps context lean.\n- When scraping lists, ALWAYS ask about pagination in your query: \"How many total results? Is there a next page?\"\n- For many independent URLs (roughly 5+), spawnAgents can help — each worker gets specific URLs and fields. Fewer URLs: handle in the orchestrator.\n- If a scrape returns a 404 or bot-check, do NOT retry. Move on to alternative sources.\n\n## Building the output\n- Match the schema EXACTLY. Every required field must be present.\n- Use null for missing fields — never omit keys.\n- Arrays must be arrays even for single items.\n- Numbers must be actual numbers, not strings (10.99 not \"$10.99\").\n- Use bashExec with jq to merge data from multiple sources:\n  ```\n  jq -s '.[0] * .[1]' \u002Fdata\u002Fpart1.json \u002Fdata\u002Fpart2.json > \u002Fdata\u002Fmerged.json\n  ```\n\n## Validation before output\nBefore calling formatOutput, verify:\n1. All required fields from the schema are present.\n2. Types match (numbers are numbers, arrays are arrays).\n3. No duplicate entries in arrays.\n4. Source URLs are included where the schema has citation fields.\n\n## CRITICAL: Always call formatOutput\nWhen you have gathered ALL data, call formatOutput with format \"json\" and the structured data.\nDo NOT stream data inline as markdown tables or JSON code blocks.\nDo NOT skip formatOutput — downstream systems depend on the structured output.\n",{"data":32,"body":34},{"name":4,"description":6,"category":33},"Research",{"type":35,"children":36},"root",[37,45,51,58,65,85,91,109,115,147,153,181,187,210,216,257,263,268,291,297],{"type":38,"tag":39,"props":40,"children":41},"element","h1",{"id":4},[42],{"type":43,"value":44},"text","Structured Extraction",{"type":38,"tag":46,"props":47,"children":48},"p",{},[49],{"type":43,"value":50},"Use this skill when extracting data that must match a specific JSON schema.",{"type":38,"tag":52,"props":53,"children":55},"h2",{"id":54},"strategy-by-task-type",[56],{"type":43,"value":57},"Strategy by task type",{"type":38,"tag":59,"props":60,"children":62},"h3",{"id":61},"simple-query-single-fact-or-small-object",[63],{"type":43,"value":64},"Simple query (single fact or small object)",{"type":38,"tag":66,"props":67,"children":68},"ol",{},[69,75,80],{"type":38,"tag":70,"props":71,"children":72},"li",{},[73],{"type":43,"value":74},"Search for relevant results.",{"type":38,"tag":70,"props":76,"children":77},{},[78],{"type":43,"value":79},"Scrape promising results with a targeted query.",{"type":38,"tag":70,"props":81,"children":82},{},[83],{"type":43,"value":84},"Build the result object and call formatOutput immediately.",{"type":38,"tag":59,"props":86,"children":88},{"id":87},"single-target-research-one-entity-multiple-fields",[89],{"type":43,"value":90},"Single target research (one entity, multiple fields)",{"type":38,"tag":66,"props":92,"children":93},{},[94,99,104],{"type":38,"tag":70,"props":95,"children":96},{},[97],{"type":43,"value":98},"Search for relevant URLs.",{"type":38,"tag":70,"props":100,"children":101},{},[102],{"type":43,"value":103},"Scrape to extract data — stay in the orchestrator unless you have many independent sources (roughly 5+) where parallel workers clearly help.",{"type":38,"tag":70,"props":105,"children":106},{},[107],{"type":43,"value":108},"Compile findings and call formatOutput.",{"type":38,"tag":59,"props":110,"children":112},{"id":111},"list-of-items-array-in-schema",[113],{"type":43,"value":114},"List of items (array in schema)",{"type":38,"tag":66,"props":116,"children":117},{},[118,123,142],{"type":38,"tag":70,"props":119,"children":120},{},[121],{"type":43,"value":122},"Search\u002Fscrape to get the list of items.",{"type":38,"tag":70,"props":124,"children":125},{},[126,128],{"type":43,"value":127},"Are all requested details included in the list?\n",{"type":38,"tag":129,"props":130,"children":131},"ul",{},[132,137],{"type":38,"tag":70,"props":133,"children":134},{},[135],{"type":43,"value":136},"Yes: Build the result and call formatOutput.",{"type":38,"tag":70,"props":138,"children":139},{},[140],{"type":43,"value":141},"No: If there are many items (roughly 5+), use spawnAgents so each worker gets the item and fields; otherwise fetch details sequentially in the orchestrator.",{"type":38,"tag":70,"props":143,"children":144},{},[145],{"type":43,"value":146},"Aggregate all results and call formatOutput.",{"type":38,"tag":59,"props":148,"children":150},{"id":149},"all-items-from-a-website",[151],{"type":43,"value":152},"All items from a website",{"type":38,"tag":66,"props":154,"children":155},{},[156,161,166,171,176],{"type":38,"tag":70,"props":157,"children":158},{},[159],{"type":43,"value":160},"Check sitemaps (sitemap.xml, robots.txt) for an easy route to all pages.",{"type":38,"tag":70,"props":162,"children":163},{},[164],{"type":43,"value":165},"Scrape the entry page. Determine: pagination? Categories? Subcategories?",{"type":38,"tag":70,"props":167,"children":168},{},[169],{"type":43,"value":170},"For pagination, use interact to click through every page.",{"type":38,"tag":70,"props":172,"children":173},{},[174],{"type":43,"value":175},"For categories, scrape each category — use spawnAgents only when many independent categories warrant parallel fan-out.",{"type":38,"tag":70,"props":177,"children":178},{},[179],{"type":43,"value":180},"Aggregate and call formatOutput.",{"type":38,"tag":52,"props":182,"children":184},{"id":183},"scraping-for-structured-data",[185],{"type":43,"value":186},"Scraping for structured data",{"type":38,"tag":129,"props":188,"children":189},{},[190,195,200,205],{"type":38,"tag":70,"props":191,"children":192},{},[193],{"type":43,"value":194},"PREFER scrape with a targeted query over raw page dumps. It keeps context lean.",{"type":38,"tag":70,"props":196,"children":197},{},[198],{"type":43,"value":199},"When scraping lists, ALWAYS ask about pagination in your query: \"How many total results? Is there a next page?\"",{"type":38,"tag":70,"props":201,"children":202},{},[203],{"type":43,"value":204},"For many independent URLs (roughly 5+), spawnAgents can help — each worker gets specific URLs and fields. Fewer URLs: handle in the orchestrator.",{"type":38,"tag":70,"props":206,"children":207},{},[208],{"type":43,"value":209},"If a scrape returns a 404 or bot-check, do NOT retry. Move on to alternative sources.",{"type":38,"tag":52,"props":211,"children":213},{"id":212},"building-the-output",[214],{"type":43,"value":215},"Building the output",{"type":38,"tag":129,"props":217,"children":218},{},[219,224,229,234,239],{"type":38,"tag":70,"props":220,"children":221},{},[222],{"type":43,"value":223},"Match the schema EXACTLY. Every required field must be present.",{"type":38,"tag":70,"props":225,"children":226},{},[227],{"type":43,"value":228},"Use null for missing fields — never omit keys.",{"type":38,"tag":70,"props":230,"children":231},{},[232],{"type":43,"value":233},"Arrays must be arrays even for single items.",{"type":38,"tag":70,"props":235,"children":236},{},[237],{"type":43,"value":238},"Numbers must be actual numbers, not strings (10.99 not \"$10.99\").",{"type":38,"tag":70,"props":240,"children":241},{},[242,244],{"type":43,"value":243},"Use bashExec with jq to merge data from multiple sources:\n",{"type":38,"tag":245,"props":246,"children":250},"pre",{"className":247,"code":249,"language":43},[248],"language-text","jq -s '.[0] * .[1]' \u002Fdata\u002Fpart1.json \u002Fdata\u002Fpart2.json > \u002Fdata\u002Fmerged.json\n",[251],{"type":38,"tag":252,"props":253,"children":255},"code",{"__ignoreMap":254},"",[256],{"type":43,"value":249},{"type":38,"tag":52,"props":258,"children":260},{"id":259},"validation-before-output",[261],{"type":43,"value":262},"Validation before output",{"type":38,"tag":46,"props":264,"children":265},{},[266],{"type":43,"value":267},"Before calling formatOutput, verify:",{"type":38,"tag":66,"props":269,"children":270},{},[271,276,281,286],{"type":38,"tag":70,"props":272,"children":273},{},[274],{"type":43,"value":275},"All required fields from the schema are present.",{"type":38,"tag":70,"props":277,"children":278},{},[279],{"type":43,"value":280},"Types match (numbers are numbers, arrays are arrays).",{"type":38,"tag":70,"props":282,"children":283},{},[284],{"type":43,"value":285},"No duplicate entries in arrays.",{"type":38,"tag":70,"props":287,"children":288},{},[289],{"type":43,"value":290},"Source URLs are included where the schema has citation fields.",{"type":38,"tag":52,"props":292,"children":294},{"id":293},"critical-always-call-formatoutput",[295],{"type":43,"value":296},"CRITICAL: Always call formatOutput",{"type":38,"tag":46,"props":298,"children":299},{},[300],{"type":43,"value":301},"When you have gathered ALL data, call formatOutput with format \"json\" and the structured data.\nDo NOT stream data inline as markdown tables or JSON code blocks.\nDo NOT skip formatOutput — downstream systems depend on the structured output.",{"items":303,"total":457},[304,317,329,340,355,368,374,389,401,418,433,445],{"slug":305,"name":305,"fn":306,"description":307,"org":308,"tags":309,"stars":20,"repoUrl":21,"updatedAt":316},"competitor-analysis","analyze competitors across features and pricing","Compare two or more companies, products, or platforms across pricing, features, positioning, and docs. Use this skill whenever the user says \"compare X vs Y\", \"how does X stack up against Y\", \"alternatives to X\", \"competitive landscape of …\", \"X vs Y vs Z\", or asks for a competitor matrix. Uses search to discover competitors when the user only names a category, then scrape for each competitor's homepage, pricing page, and features\u002Fdocs. Returns a normalized comparison matrix as JSON.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[310,313,314],{"name":311,"slug":312,"type":15},"Competitive Intelligence","competitive-intelligence",{"name":9,"slug":8,"type":15},{"name":33,"slug":315,"type":15},"research","2026-04-17T05:00:44.623049",{"slug":318,"name":318,"fn":319,"description":320,"org":321,"tags":322,"stars":20,"repoUrl":21,"updatedAt":328},"deep-research","conduct multi-source deep research","Multi-source research with source triangulation and fact-checking. Use for any research task requiring 3+ sources.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[323,324,327],{"name":9,"slug":8,"type":15},{"name":325,"slug":326,"type":15},"Knowledge Management","knowledge-management",{"name":33,"slug":315,"type":15},"2026-04-17T05:00:45.852512",{"slug":330,"name":330,"fn":331,"description":332,"org":333,"tags":334,"stars":20,"repoUrl":21,"updatedAt":339},"e-commerce","extract product data from e-commerce sites","Navigate e-commerce sites to extract products, pricing, categories, and inventory. Handles pagination, variants, and JS-heavy storefronts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[335,337,338],{"name":336,"slug":330,"type":15},"E-commerce",{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},"2026-05-15T06:15:30.880268",{"slug":341,"name":341,"fn":342,"description":343,"org":344,"tags":345,"stars":20,"repoUrl":21,"updatedAt":354},"financial-research","pull financial data for public companies","Pull company financials, SEC filings, and analyst consensus for a public company. Use this skill whenever the user says \"10-K\", \"10-Q\", \"earnings\", \"revenue of\", \"financials for\", \"analyst rating for\", \"price target for\", or provides a stock ticker. Combines SEC EDGAR for official filings with Yahoo Finance \u002F TipRanks for analyst data. Search + scrape only; no interact needed.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[346,349,350,351],{"name":347,"slug":348,"type":15},"Finance","finance",{"name":9,"slug":8,"type":15},{"name":33,"slug":315,"type":15},{"name":352,"slug":353,"type":15},"SEC Filings","sec-filings","2026-05-15T06:15:33.293957",{"slug":356,"name":356,"fn":357,"description":358,"org":359,"tags":360,"stars":20,"repoUrl":21,"updatedAt":367},"pricing-tracker","track and compare vendor pricing tiers","Extract and normalize pricing tiers from any SaaS, API, cloud, or LLM vendor's pricing page. Use this skill whenever the user says \"pricing for X\", \"how much does X cost\", \"pricing tiers\", \"cost comparison\", provides a URL ending in `\u002Fpricing` or `\u002Fplans`, or asks to monitor pricing over time. Pairs well with `exportSkill` to turn a run into a cron-friendly workflow. Scrape-driven; no interact needed for typical pricing pages.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[361,362,363,364],{"name":311,"slug":312,"type":15},{"name":9,"slug":8,"type":15},{"name":33,"slug":315,"type":15},{"name":365,"slug":366,"type":15},"SaaS","saas","2026-04-17T05:00:43.349332",{"slug":4,"name":4,"fn":5,"description":6,"org":369,"tags":370,"stars":20,"repoUrl":21,"updatedAt":22},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[371,372,373],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"slug":375,"name":375,"fn":376,"description":377,"org":378,"tags":379,"stars":386,"repoUrl":387,"updatedAt":388},"firecrawl-company-directories","extract company directories with Firecrawl","Extract structured company lists from directories with Firecrawl. Use for scraping YC, Crunchbase, Product Hunt, G2, startup directories, category directories, or custom company databases into JSON, CSV, CRM-ready lists, or research tables.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[380,383,384,385],{"name":381,"slug":382,"type":15},"Automation","automation",{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},99,"https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Ffirecrawl-workflows","2026-06-30T07:02:21.468",{"slug":390,"name":390,"fn":391,"description":392,"org":393,"tags":394,"stars":386,"repoUrl":387,"updatedAt":388},"firecrawl-competitive-intel","monitor competitor product changes with Firecrawl","Monitor competitor pricing, features, changelogs, dashboards, and product changes with Firecrawl. Use for recurring competitive intelligence, pricing tier extraction, feature change tracking, or structured competitor alerts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[395,396,397,400],{"name":311,"slug":312,"type":15},{"name":9,"slug":8,"type":15},{"name":398,"slug":399,"type":15},"Marketing","marketing",{"name":17,"slug":18,"type":15},{"slug":402,"name":402,"fn":403,"description":404,"org":405,"tags":406,"stars":386,"repoUrl":387,"updatedAt":388},"firecrawl-dashboard-reporting","pull metrics from analytics dashboards","Pull metrics from analytics dashboards and internal web tools with Firecrawl browser. Use when the user needs dashboard reporting, cross-platform metric summaries, authenticated analytics extraction, date-range reports, or structured metrics from web dashboards.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[407,410,413,414,417],{"name":408,"slug":409,"type":15},"Analytics","analytics",{"name":411,"slug":412,"type":15},"Dashboards","dashboards",{"name":9,"slug":8,"type":15},{"name":415,"slug":416,"type":15},"Reporting","reporting",{"name":17,"slug":18,"type":15},{"slug":419,"name":419,"fn":420,"description":421,"org":422,"tags":423,"stars":386,"repoUrl":387,"updatedAt":388},"firecrawl-deep-research","conduct deep research with Firecrawl","Produce an intensive, cited analytical report: executive summary, multi-angle\nfindings, contrarian views, open questions, and full sources. Use only when the\nuser needs rigorous synthesis of a complex topic (scientific, technical, policy,\nor market-analytical) that cannot be answered with a short search, and wants\na formal written report, not a recommendation list.\n\nDo not use for product picks, top-N lists, quick lookups, or routine \"find out\nabout X\" tasks. If the request does not clearly need this kind of report, do\nnot use this skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[424,425,428,429,432],{"name":9,"slug":8,"type":15},{"name":426,"slug":427,"type":15},"Firecrawl Research","firecrawl-research",{"name":33,"slug":315,"type":15},{"name":430,"slug":431,"type":15},"Summarization","summarization",{"name":17,"slug":18,"type":15},{"slug":434,"name":434,"fn":435,"description":436,"org":437,"tags":438,"stars":386,"repoUrl":387,"updatedAt":388},"firecrawl-demo-walkthrough","generate product walkthroughs with Firecrawl","Walk through a product's key flows with Firecrawl browser and produce a structured UX\u002Fproduct walkthrough. Use for signup, onboarding, pricing, docs, dashboard, product demo prep, UX teardown, and first-run experience analysis.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[439,440,441,444],{"name":381,"slug":382,"type":15},{"name":9,"slug":8,"type":15},{"name":442,"slug":443,"type":15},"UX Design","ux-design",{"name":17,"slug":18,"type":15},{"slug":446,"name":446,"fn":447,"description":448,"org":449,"tags":450,"stars":386,"repoUrl":387,"updatedAt":388},"firecrawl-knowledge-base","build knowledge bases from web content","Build a knowledge base from web content with Firecrawl. Use for local reference docs, RAG-ready chunks, fine-tuning datasets, documentation mirrors, topic corpora, or LLM-ready markdown organized from web sources.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[451,452,453,454],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":325,"slug":326,"type":15},{"name":455,"slug":456,"type":15},"Search","search",36,{"items":459,"total":498},[460,466,472,478,485,492],{"slug":305,"name":305,"fn":306,"description":307,"org":461,"tags":462,"stars":20,"repoUrl":21,"updatedAt":316},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[463,464,465],{"name":311,"slug":312,"type":15},{"name":9,"slug":8,"type":15},{"name":33,"slug":315,"type":15},{"slug":318,"name":318,"fn":319,"description":320,"org":467,"tags":468,"stars":20,"repoUrl":21,"updatedAt":328},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[469,470,471],{"name":9,"slug":8,"type":15},{"name":325,"slug":326,"type":15},{"name":33,"slug":315,"type":15},{"slug":330,"name":330,"fn":331,"description":332,"org":473,"tags":474,"stars":20,"repoUrl":21,"updatedAt":339},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[475,476,477],{"name":336,"slug":330,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},{"slug":341,"name":341,"fn":342,"description":343,"org":479,"tags":480,"stars":20,"repoUrl":21,"updatedAt":354},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[481,482,483,484],{"name":347,"slug":348,"type":15},{"name":9,"slug":8,"type":15},{"name":33,"slug":315,"type":15},{"name":352,"slug":353,"type":15},{"slug":356,"name":356,"fn":357,"description":358,"org":486,"tags":487,"stars":20,"repoUrl":21,"updatedAt":367},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[488,489,490,491],{"name":311,"slug":312,"type":15},{"name":9,"slug":8,"type":15},{"name":33,"slug":315,"type":15},{"name":365,"slug":366,"type":15},{"slug":4,"name":4,"fn":5,"description":6,"org":493,"tags":494,"stars":20,"repoUrl":21,"updatedAt":22},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[495,496,497],{"name":13,"slug":14,"type":15},{"name":9,"slug":8,"type":15},{"name":17,"slug":18,"type":15},6]