[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7C3S9VHBCP94M7TKJS3DP76":3,"skill-same:01M7C3S9VHBCP94M7TKJS3DP76":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":40,"updatedAt":41,"install":42,"resources":54},"01M7C3S9VHBCP94M7TKJS3DP76","firecrawl-website-design-clone",null,"Extract any website's design system into an agent-ready DESIGN.md using Firecrawl scrape evidence. Use when the user wants colors, fonts, spacing, components, layout patterns, or brand\u002FUI guidance from a website so AI agents can create new websites, clone a look, or build pages inspired by that design.","om-scogo\u002Fskillsh-scraper","om-scogo","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160466840?v=4","01M79AWB6DFVCQ7RK70CS34B96","Om Achrekar","01M79AWB6ZM9SKR8KDH1WSSM22",0,"ISC","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Ffirecrawl-firecrawl-workflows\u002Ffirecrawl-website-design-clone\u002Fskills\u002Ffirecrawl-website-design-clone\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: firecrawl-website-design-clone\ndescription: Extract any website's design system into an agent-ready DESIGN.md using Firecrawl scrape evidence. Use when the user wants colors, fonts, spacing, components, layout patterns, or brand\u002FUI guidance from a website so AI agents can create new websites, clone a look, or build pages inspired by that design.\nlicense: ISC\nmetadata:\n  author: firecrawl\n  version: \"0.1.0\"\n  homepage: https:\u002F\u002Fwww.firecrawl.dev\n  source: https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Ffirecrawl-workflows\ninputs:\n  - name: FIRECRAWL_API_KEY\n    description: Firecrawl API key for hosted Firecrawl requests when the workflow runs through the CLI or API.\n    required: true\n---\n\n# Firecrawl Website Design Clone\n\nUse this when the user wants one URL turned into a practical design system file agents can use immediately.\n\nDefault outcome: **extract any website's design system in one line** and format it as `DESIGN.md`.\n\nThe skill should feel like a thin workflow around Firecrawl scrape: gather the page's visible content, structure, metadata, links, and available visual signals, then synthesize those findings into a clean design-system markdown file.\n\n## Onboarding Interview\n\nInfer the source URL, target stack, and whether implementation is requested from context. If the user gives a URL and asks for a design system, proceed immediately.\n\nAsk at most 1-3 concise questions only if blocked, such as the website URL, whether to output only `DESIGN.md` or also implement, or a required target stack.\n\nUse the host agent's normal prompt or modal UI. Do not name a harness-specific question function.\n\n## Firecrawl Collection Plan\n\nUse Firecrawl through the CLI or equivalent tool surface. Always start with two parallel scrapes of the supplied URL:\n\n1. The `branding` and `images` formats together for structured design tokens and the full set of page images.\n2. A full-page screenshot for visual context.\n\nExample:\n\n```bash\nfirecrawl scrape \"https:\u002F\u002Fexample.com\" --format branding,images -o \".firecrawl\u002Fexample-branding.json\" --pretty &\nfirecrawl scrape \"https:\u002F\u002Fexample.com\" --full-page-screenshot -o \".firecrawl\u002Fexample-screenshot.png\" &\nwait\n```\n\nCombining `branding` and `images` in one call still costs a single credit and is required: the `branding` block only surfaces curated brand assets (`logo`, `favicon`, `ogImage`, `logoHref`), so without `images` the agent will miss the page's actual content imagery (heroes, product shots, carousel slides, feature visuals, illustrations, accessory photos, end-of-page artwork, and similar). On a product page like `tesla.com\u002Fcybertruck` the `branding` block has no hero — only `images` returns the main Cybertruck hero (e.g. `Cybertruck-Hero-Desktop-NA-SA-APAC.png`) and the rest of the page's photography.\n\nIf the screenshot scrape returns a remote image URL (e.g. signed storage link) instead of a local file, download it to the same `.firecrawl\u002F` path so `DESIGN.md` can reference a stable local asset.\n\nUse the structured `branding` output as the primary source for colors, typography, components, brand assets (logo, favicon, ogImage), personality, and confidence notes. Use the `images` list as the source of truth for the page's content imagery — hero photography, product shots, carousels, feature visuals, illustrations, and decorative graphics. Use the screenshot as the primary visual reference for layout, hierarchy, and overall feel. Add supplemental formats only when these are insufficient for the final artifact.\n\nCollect:\n\n- branding data for colors, typography, spacing, buttons, logos, brand imagery, personality, and confidence\n- the full `images` list for hero, product, feature, and section imagery beyond the curated brand assets\n- a full-page screenshot saved locally in `.firecrawl\u002F` so it can be embedded in `DESIGN.md`\n- page markdown for headings, copy hierarchy, CTAs, navigation, and section order when needed\n- metadata and links for brand, product, and page-purpose clues when needed\n- HTML only when the branding output, images list, and screenshot are insufficient to infer classes, font names, CSS variables, or component structure\n- related pages only when the user asks for a broader site system\n\nDo not over-crawl by default. The first version should be useful from a single representative page.\n\n## What To Extract\n\nInfer and document the site's design language:\n\n- colors: primary, secondary, accents, backgrounds, borders, text, states\n- typography: font families if detectable, type scale, weights, line heights, heading\u002Fbody treatment\n- spacing: container widths, section rhythm, grid gaps, padding scale, density\n- layout: page structure, hero patterns, cards, grids, nav, footer, responsive assumptions\n- components: buttons, inputs, cards, badges, nav items, pricing blocks, testimonials, feature rows, forms\n- imagery and icons: style, shape language, illustration\u002Fphoto treatment, logo constraints; pull representative hero, product, feature, and section images from the full `images` list rather than relying on `branding.images`, which only carries `logo`, `favicon`, `ogImage`, and `logoHref`\n- motion and interaction: hover states, transitions, animation style when observable or inferable\n- voice and content patterns: CTA wording, heading style, product copy rhythm\n\nWhen a value cannot be measured exactly from scrape output, label it as inferred and give a practical approximation.\n\n## Parallel Work\n\nIf appropriate, use sub-agents or equivalent parallel task runners. Natural splits include one page per researcher for multi-page sites, or one reviewer each for colors, typography, spacing, and components.\n\nEach parallel researcher should return source URLs, extracted evidence, inferred design tokens, and confidence notes.\n\n## Final Deliverable\n\nCreate or return a `DESIGN.md` with this structure. Embed the full-page screenshot near the top so a coding agent gets visual context alongside the tokens.\n\n```markdown\n# DESIGN.md: [Source Site]\n\n## Source\n- URL: [source URL]\n- Capture date: [date]\n- Evidence: [scrape\u002Fscreenshot\u002Fhtml\u002Flinks used]\n\n## Reference Screenshot\n![Full-page screenshot of [Source Site]](.\u002F.firecrawl\u002F[source]-screenshot.png)\n\nUse this screenshot as the visual source of truth for layout, hierarchy, density, and feel. Tokens below describe the same page in machine-readable form.\n\n## Design Summary\n[Short description of the visual language and what an agent should recreate]\n\n## Design Tokens\n\n### Colors\n[Named color roles with hex values when known; mark inferred values clearly]\n\n### Typography\n[Fonts, fallback recommendations, scale, weights, heading\u002Fbody rules]\n\n### Spacing And Layout\n[Spacing scale, containers, grids, radius, shadows, borders]\n\n## Components\n[Buttons, cards, nav, forms, hero, feature sections, pricing, footer, etc.]\n\n## Page Patterns\n[Section order, common layouts, responsive behavior]\n\n## Content Style\n[Voice, CTA style, heading patterns, copy density]\n\n## Agent Build Instructions\n[Concrete instructions an AI coding agent can follow to create a new site in this style]\n\n## Rerun Inputs\nworkflow: firecrawl-website-design-clone\nsource_url: [url]\ntarget_stack: [stack]\noutput: DESIGN.md\n```\n\nIf the user asks to implement, first produce or update `DESIGN.md`, then use it as the source of truth for the build.\n\n## Quality Bar\n\n- Do not imply the user has rights to third-party logos, images, trademarks, or copy.\n- Prefer reusable design tokens over one-off observations.\n- Distinguish observed facts from inferred approximations.\n- Keep the output compact enough that another agent can paste it into context and build from it.\n- Preserve source URLs and scrape artifacts for review.\n","# Firecrawl Website Design Clone\n\nUse this when the user wants one URL turned into a practical design system file agents can use immediately.\n\nDefault outcome: **extract any website's design system in one line** and format it as `DESIGN.md`.\n\nThe skill should feel like a thin workflow around Firecrawl scrape: gather the page's visible content, structure, metadata, links, and available visual signals, then synthesize those findings into a clean design-system markdown file.\n\n## Onboarding Interview\n\nInfer the source URL, target stack, and whether implementation is requested from context. If the user gives a URL and asks for a design system, proceed immediately.\n\nAsk at most 1-3 concise questions only if blocked, such as the website URL, whether to output only `DESIGN.md` or also implement, or a required target stack.\n\nUse the host agent's normal prompt or modal UI. Do not name a harness-specific question function.\n\n## Firecrawl Collection Plan\n\nUse Firecrawl through the CLI or equivalent tool surface. Always start with two parallel scrapes of the supplied URL:\n\n1. The `branding` and `images` formats together for structured design tokens and the full set of page images.\n2. A full-page screenshot for visual context.\n\nExample:\n\n```bash\nfirecrawl scrape \"https:\u002F\u002Fexample.com\" --format branding,images -o \".firecrawl\u002Fexample-branding.json\" --pretty &\nfirecrawl scrape \"https:\u002F\u002Fexample.com\" --full-page-screenshot -o \".firecrawl\u002Fexample-screenshot.png\" &\nwait\n```\n\nCombining `branding` and `images` in one call still costs a single credit and is required: the `branding` block only surfaces curated brand assets (`logo`, `favicon`, `ogImage`, `logoHref`), so without `images` the agent will miss the page's actual content imagery (heroes, product shots, carousel slides, feature visuals, illustrations, accessory photos, end-of-page artwork, and similar). On a product page like `tesla.com\u002Fcybertruck` the `branding` block has no hero — only `images` returns the main Cybertruck hero (e.g. `Cybertruck-Hero-Desktop-NA-SA-APAC.png`) and the rest of the page's photography.\n\nIf the screenshot scrape returns a remote image URL (e.g. signed storage link) instead of a local file, download it to the same `.firecrawl\u002F` path so `DESIGN.md` can reference a stable local asset.\n\nUse the structured `branding` output as the primary source for colors, typography, components, brand assets (logo, favicon, ogImage), personality, and confidence notes. Use the `images` list as the source of truth for the page's content imagery — hero photography, product shots, carousels, feature visuals, illustrations, and decorative graphics. Use the screenshot as the primary visual reference for layout, hierarchy, and overall feel. Add supplemental formats only when these are insufficient for the final artifact.\n\nCollect:\n\n- branding data for colors, typography, spacing, buttons, logos, brand imagery, personality, and confidence\n- the full `images` list for hero, product, feature, and section imagery beyond the curated brand assets\n- a full-page screenshot saved locally in `.firecrawl\u002F` so it can be embedded in `DESIGN.md`\n- page markdown for headings, copy hierarchy, CTAs, navigation, and section order when needed\n- metadata and links for brand, product, and page-purpose clues when needed\n- HTML only when the branding output, images list, and screenshot are insufficient to infer classes, font names, CSS variables, or component structure\n- related pages only when the user asks for a broader site system\n\nDo not over-crawl by default. The first version should be useful from a single representative page.\n\n## What To Extract\n\nInfer and document the site's design language:\n\n- colors: primary, secondary, accents, backgrounds, borders, text, states\n- typography: font families if detectable, type scale, weights, line heights, heading\u002Fbody treatment\n- spacing: container widths, section rhythm, grid gaps, padding scale, density\n- layout: page structure, hero patterns, cards, grids, nav, footer, responsive assumptions\n- components: buttons, inputs, cards, badges, nav items, pricing blocks, testimonials, feature rows, forms\n- imagery and icons: style, shape language, illustration\u002Fphoto treatment, logo constraints; pull representative hero, product, feature, and section images from the full `images` list rather than relying on `branding.images`, which only carries `logo`, `favicon`, `ogImage`, and `logoHref`\n- motion and interaction: hover states, transitions, animation style when observable or inferable\n- voice and content patterns: CTA wording, heading style, product copy rhythm\n\nWhen a value cannot be measured exactly from scrape output, label it as inferred and give a practical approximation.\n\n## Parallel Work\n\nIf appropriate, use sub-agents or equivalent parallel task runners. Natural splits include one page per researcher for multi-page sites, or one reviewer each for colors, typography, spacing, and components.\n\nEach parallel researcher should return source URLs, extracted evidence, inferred design tokens, and confidence notes.\n\n## Final Deliverable\n\nCreate or return a `DESIGN.md` with this structure. Embed the full-page screenshot near the top so a coding agent gets visual context alongside the tokens.\n\n```markdown\n# DESIGN.md: [Source Site]\n\n## Source\n- URL: [source URL]\n- Capture date: [date]\n- Evidence: [scrape\u002Fscreenshot\u002Fhtml\u002Flinks used]\n\n## Reference Screenshot\n![Full-page screenshot of [Source Site]](.\u002F.firecrawl\u002F[source]-screenshot.png)\n\nUse this screenshot as the visual source of truth for layout, hierarchy, density, and feel. Tokens below describe the same page in machine-readable form.\n\n## Design Summary\n[Short description of the visual language and what an agent should recreate]\n\n## Design Tokens\n\n### Colors\n[Named color roles with hex values when known; mark inferred values clearly]\n\n### Typography\n[Fonts, fallback recommendations, scale, weights, heading\u002Fbody rules]\n\n### Spacing And Layout\n[Spacing scale, containers, grids, radius, shadows, borders]\n\n## Components\n[Buttons, cards, nav, forms, hero, feature sections, pricing, footer, etc.]\n\n## Page Patterns\n[Section order, common layouts, responsive behavior]\n\n## Content Style\n[Voice, CTA style, heading patterns, copy density]\n\n## Agent Build Instructions\n[Concrete instructions an AI coding agent can follow to create a new site in this style]\n\n## Rerun Inputs\nworkflow: firecrawl-website-design-clone\nsource_url: [url]\ntarget_stack: [stack]\noutput: DESIGN.md\n```\n\nIf the user asks to implement, first produce or update `DESIGN.md`, then use it as the source of truth for the build.\n\n## Quality Bar\n\n- Do not imply the user has rights to third-party logos, images, trademarks, or copy.\n- Prefer reusable design tokens over one-off observations.\n- Distinguish observed facts from inferred approximations.\n- Keep the output compact enough that another agent can paste it into context and build from it.\n- Preserve source URLs and scrape artifacts for review.\n",{"name":5,"inputs":24,"license":15,"metadata":29,"description":7},[25],{"name":26,"required":27,"description":28},"FIRECRAWL_API_KEY",true,"Firecrawl API key for hosted Firecrawl requests when the workflow runs through the CLI or API.",{"author":30,"source":31,"version":32,"homepage":33},"firecrawl","https:\u002F\u002Fgithub.com\u002Ffirecrawl\u002Ffirecrawl-workflows","0.1.0","https:\u002F\u002Fwww.firecrawl.dev","main","8859218955d9504cd18b59e7892100718039d3b4","data\u002Fskills\u002Ffirecrawl-firecrawl-workflows\u002Ffirecrawl-website-design-clone\u002Fskills\u002Ffirecrawl-website-design-clone",1,"https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper","https:\u002F\u002Fgithub.com\u002Fom-scogo","SDE-1 @ Scogo ","2026-07-18 12:22:46",{"source":8,"skillName":5,"commands":43,"prompt":53,"zipAvailable":27},[44,47,50],{"tool":45,"command":46},"npx","npx skills add om-scogo\u002Fskillsh-scraper --skill firecrawl-website-design-clone",{"tool":48,"command":49},"bunx","bunx skills add om-scogo\u002Fskillsh-scraper --skill firecrawl-website-design-clone",{"tool":51,"command":52},"pnpm","pnpm dlx skills add om-scogo\u002Fskillsh-scraper --skill firecrawl-website-design-clone","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Ffirecrawl-firecrawl-workflows\u002Ffirecrawl-website-design-clone\u002Fskills\u002Ffirecrawl-website-design-clone\u002FSKILL.md",[],[56,64,69,76,81,88],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":60,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7D6MC9FAAEV4CMNYX8W7JTG","arxiv-search","Search arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.","MIT","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002Fskills\u002Farxiv-search\u002FSKILL.md",[],[],{"skillNo":65,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":60,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7D6M85CKKN87TA98VCQV4H7","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fyorkeccak-scientific-skills\u002Farxiv-search\u002FSkill.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":60,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7D4ZTCS4DR3CE4JY06X84T2","working-with-legacy-code","Safely change and test untested codebases using Feathers' \"Working Effectively with Legacy Code\". Use when the user mentions \"legacy code\", \"no tests\", \"untested codebase\", \"how do I test this\", \"seams\", \"characterization tests\", \"golden master\", \"sprout method\", \"afraid to change this code\", \"monster method\", \"dependency breaking\", or \"inherited a messy codebase\". Also trigger when changing code without tests safely, getting a class under test when constructors, statics, or singletons block it, adding features to tangled modules, or planning incremental test coverage for an old codebase. Covers the legacy-code change algorithm, seams, characterization tests, sprout\u002Fwrap, and dependency-breaking techniques. For refactoring code that already has tests, see refactoring-patterns. For day-to-day code quality, see clean-code.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002Fworking-with-legacy-code\u002FSKILL.md",[],[],{"skillNo":77,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":60,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7D4ZHZKJD2RSNGAF63V14P4","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fworking-with-legacy-code\u002FSkill.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":60,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7D4ZB4CJBFW5JE67CPH2QRV","web-typography","Select, pair, and implement typefaces for web projects. Use when the user mentions \"font pairing\", \"which typeface\", \"line height\", \"responsive typography\", \"web font loading\", \"type hierarchy\", \"variable fonts\", \"FOUT\u002FFOIT\", \"typographic scale\", or \"the text is hard to read\". Also trigger when choosing between system fonts and web fonts, optimizing font-loading performance, or designing readable long-form content. Covers readability evaluation, CSS implementation, and performance optimization. For overall UI design systems, see refactoring-ui. For dramatic typographic experiences, see top-design.","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002Fweb-typography\u002FSKILL.md",[],[],{"skillNo":89,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":60,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7D4Z4MVYVY3NMJ18BNV6WNA","https:\u002F\u002Fgithub.com\u002Fom-scogo\u002Fskillsh-scraper\u002Fblob\u002Fmain\u002Fdata\u002Fskills\u002Fwondelai-skills\u002Fweb-typography\u002FSkill.md",[],[]]