[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7AZZSJR85HSA31GXDGPJS6V":3,"skill-same:01M7AZZSJR85HSA31GXDGPJS6V":61},{"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":36,"commitSha":37,"skillDirectory":38,"forksCount":14,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":41,"updatedAt":42,"install":43,"resources":55},"01M7AZZSJR85HSA31GXDGPJS6V","firecrawl-workflows",null,"Run outcome-focused Firecrawl workflows that produce deliverables such as research reports, literature reviews over published papers, SEO audits, QA reports, lead lists, knowledge bases, website design systems, and other structured web-data artifacts. Use when the user wants Firecrawl to complete a business, marketing, product, or creative workflow rather than merely scrape a page or integrate API calls into code.","dbillion\u002Fhermes-skills-public","dbillion","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F49393855?v=4","01M7AVH8QPGCM8WKWS22TRT0T6","Oludayo Adeoye","01M7AVH8RD1JJWA0YS9CFEWAV9",0,"ISC","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ffirecrawl-workflows\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: firecrawl-workflows\ndescription: Run outcome-focused Firecrawl workflows that produce deliverables such as research reports, literature reviews over published papers, SEO audits, QA reports, lead lists, knowledge bases, website design systems, and other structured web-data artifacts. Use when the user wants Firecrawl to complete a business, marketing, product, or creative workflow rather than merely scrape a page or integrate API calls into code.\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\nreferences:\n  - references\u002Fworkflow-authoring.md\n---\n\n# Firecrawl Workflows\n\nUse this when the user wants a finished deliverable powered by Firecrawl, not only raw web extraction and not product-code integration.\n\n## Choose The Workflow\n\n- Use [firecrawl-website-design-clone](..\u002Ffirecrawl-website-design-clone\u002FSKILL.md) to extract a website's colors, fonts, spacing, components, and layout patterns into an agent-ready `DESIGN.md`.\n- Use [firecrawl-research-papers](..\u002Ffirecrawl-research-papers\u002FSKILL.md) for literature reviews and paper-backed synthesis, including biomedical, clinical, drug, gene, disease, epidemiology, and public-health topics. It queries Firecrawl's paper index — PubMed, bioRxiv, medRxiv, and arXiv abstracts with full text reachable per paper — rather than searching websites.\n- Use [firecrawl-deep-research](..\u002Ffirecrawl-deep-research\u002FSKILL.md) for sourced multi-source research reports built from **web** evidence: market, policy, technical, or industry topics. Not for literature reviews — when the evidence base is published papers, use `firecrawl-research-papers` above.\n- Use [firecrawl-seo-audit](..\u002Ffirecrawl-seo-audit\u002FSKILL.md) for site structure, on-page SEO, keyword, and SERP audits.\n- Use [firecrawl-lead-research](..\u002Ffirecrawl-lead-research\u002FSKILL.md) for pre-meeting company\u002Fperson intelligence briefs.\n- Use [firecrawl-qa](..\u002Ffirecrawl-qa\u002FSKILL.md) for live-site QA testing and bug reports.\n- Use [firecrawl-competitive-intel](..\u002Ffirecrawl-competitive-intel\u002FSKILL.md) for recurring pricing, feature, and changelog monitoring.\n- Use [firecrawl-company-directories](..\u002Ffirecrawl-company-directories\u002FSKILL.md) for directory extraction into company lists.\n- Use [firecrawl-dashboard-reporting](..\u002Ffirecrawl-dashboard-reporting\u002FSKILL.md) for dashboard metrics extraction.\n- Use [firecrawl-knowledge-base](..\u002Ffirecrawl-knowledge-base\u002FSKILL.md) for LLM-ready docs, RAG chunks, training data, or docs mirrors.\n- Use [firecrawl-knowledge-ingest](..\u002Ffirecrawl-knowledge-ingest\u002FSKILL.md) for auth-gated or JS-heavy docs portal ingestion.\n- Use [firecrawl-lead-gen](..\u002Ffirecrawl-lead-gen\u002FSKILL.md) for prospect list generation.\n- Use [firecrawl-market-research](..\u002Ffirecrawl-market-research\u002FSKILL.md) for market, financial, and industry research.\n- Use [firecrawl-demo-walkthrough](..\u002Ffirecrawl-demo-walkthrough\u002FSKILL.md) for product flow walkthroughs and UX teardown reports.\n- Use [firecrawl-shop](..\u002Ffirecrawl-shop\u002FSKILL.md) for product research and shopping recommendations.\n\nIf no existing workflow fits, use this generic process and produce a reusable pattern that could become a new skill.\n\n## Required Intake\n\nInfer the workflow, inputs, audience, and output format from the user's request and surrounding context. If enough is clear, start immediately.\n\nAsk at most 1-3 concise clarifying questions only when a missing input would block the work, such as:\n\n- the URL, company, topic, or source to analyze\n- the desired deliverable or output format\n- a constraint that would materially change the workflow\n\nUse the host agent's normal way to ask clarifying questions. Do not depend on a harness-specific function name.\n\n## Default Process\n\n1. Confirm the workflow and final artifact.\n2. Collect web evidence with Firecrawl through the CLI or equivalent Firecrawl tool surface.\n3. Save or cite source evidence so the final claims are traceable.\n4. Run independent research units in parallel when available.\n5. Synthesize findings into the requested deliverable.\n6. Include a short \"rerun inputs\" block when the workflow could be automated.\n\n## Parallel Work\n\nIf appropriate, use sub-agents or equivalent parallel task runners for independent units such as:\n\n- one competitor per researcher\n- one URL or page per researcher\n- one source category per researcher\n- one analysis dimension per reviewer\n\nKeep the handoff generic: provide the unit of work, source URLs or search terms, expected extracted fields, and output format.\n\n## Deliverable Standards\n\nEvery workflow should return:\n\n- a concise executive summary\n- the evidence base used\n- the analysis or artifact requested by the user\n- recommendations or next actions when useful\n- automation inputs for reruns\n\nFor authoring new workflow skills, see [workflow-authoring.md](references\u002Fworkflow-authoring.md).\n","# Firecrawl Workflows\n\nUse this when the user wants a finished deliverable powered by Firecrawl, not only raw web extraction and not product-code integration.\n\n## Choose The Workflow\n\n- Use [firecrawl-website-design-clone](..\u002Ffirecrawl-website-design-clone\u002FSKILL.md) to extract a website's colors, fonts, spacing, components, and layout patterns into an agent-ready `DESIGN.md`.\n- Use [firecrawl-research-papers](..\u002Ffirecrawl-research-papers\u002FSKILL.md) for literature reviews and paper-backed synthesis, including biomedical, clinical, drug, gene, disease, epidemiology, and public-health topics. It queries Firecrawl's paper index — PubMed, bioRxiv, medRxiv, and arXiv abstracts with full text reachable per paper — rather than searching websites.\n- Use [firecrawl-deep-research](..\u002Ffirecrawl-deep-research\u002FSKILL.md) for sourced multi-source research reports built from **web** evidence: market, policy, technical, or industry topics. Not for literature reviews — when the evidence base is published papers, use `firecrawl-research-papers` above.\n- Use [firecrawl-seo-audit](..\u002Ffirecrawl-seo-audit\u002FSKILL.md) for site structure, on-page SEO, keyword, and SERP audits.\n- Use [firecrawl-lead-research](..\u002Ffirecrawl-lead-research\u002FSKILL.md) for pre-meeting company\u002Fperson intelligence briefs.\n- Use [firecrawl-qa](..\u002Ffirecrawl-qa\u002FSKILL.md) for live-site QA testing and bug reports.\n- Use [firecrawl-competitive-intel](..\u002Ffirecrawl-competitive-intel\u002FSKILL.md) for recurring pricing, feature, and changelog monitoring.\n- Use [firecrawl-company-directories](..\u002Ffirecrawl-company-directories\u002FSKILL.md) for directory extraction into company lists.\n- Use [firecrawl-dashboard-reporting](..\u002Ffirecrawl-dashboard-reporting\u002FSKILL.md) for dashboard metrics extraction.\n- Use [firecrawl-knowledge-base](..\u002Ffirecrawl-knowledge-base\u002FSKILL.md) for LLM-ready docs, RAG chunks, training data, or docs mirrors.\n- Use [firecrawl-knowledge-ingest](..\u002Ffirecrawl-knowledge-ingest\u002FSKILL.md) for auth-gated or JS-heavy docs portal ingestion.\n- Use [firecrawl-lead-gen](..\u002Ffirecrawl-lead-gen\u002FSKILL.md) for prospect list generation.\n- Use [firecrawl-market-research](..\u002Ffirecrawl-market-research\u002FSKILL.md) for market, financial, and industry research.\n- Use [firecrawl-demo-walkthrough](..\u002Ffirecrawl-demo-walkthrough\u002FSKILL.md) for product flow walkthroughs and UX teardown reports.\n- Use [firecrawl-shop](..\u002Ffirecrawl-shop\u002FSKILL.md) for product research and shopping recommendations.\n\nIf no existing workflow fits, use this generic process and produce a reusable pattern that could become a new skill.\n\n## Required Intake\n\nInfer the workflow, inputs, audience, and output format from the user's request and surrounding context. If enough is clear, start immediately.\n\nAsk at most 1-3 concise clarifying questions only when a missing input would block the work, such as:\n\n- the URL, company, topic, or source to analyze\n- the desired deliverable or output format\n- a constraint that would materially change the workflow\n\nUse the host agent's normal way to ask clarifying questions. Do not depend on a harness-specific function name.\n\n## Default Process\n\n1. Confirm the workflow and final artifact.\n2. Collect web evidence with Firecrawl through the CLI or equivalent Firecrawl tool surface.\n3. Save or cite source evidence so the final claims are traceable.\n4. Run independent research units in parallel when available.\n5. Synthesize findings into the requested deliverable.\n6. Include a short \"rerun inputs\" block when the workflow could be automated.\n\n## Parallel Work\n\nIf appropriate, use sub-agents or equivalent parallel task runners for independent units such as:\n\n- one competitor per researcher\n- one URL or page per researcher\n- one source category per researcher\n- one analysis dimension per reviewer\n\nKeep the handoff generic: provide the unit of work, source URLs or search terms, expected extracted fields, and output format.\n\n## Deliverable Standards\n\nEvery workflow should return:\n\n- a concise executive summary\n- the evidence base used\n- the analysis or artifact requested by the user\n- recommendations or next actions when useful\n- automation inputs for reruns\n\nFor authoring new workflow skills, see [workflow-authoring.md](references\u002Fworkflow-authoring.md).\n",{"name":5,"inputs":24,"license":15,"metadata":29,"references":34,"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",[35],"references\u002Fworkflow-authoring.md","master","f341c46fed021656175d5c9ccc67a72126e50bfb","skills\u002Ffirecrawl-workflows","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public","https:\u002F\u002Fgithub.com\u002Fdbillion","I enjoy writing codes,teaching programming, solving problems, tasted automation in Python and never looked back😋😋😋💞","2026-10-14 03:31:55",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":27},[45,48,51],{"tool":46,"command":47},"npx","npx skills add dbillion\u002Fhermes-skills-public --skill firecrawl-workflows",{"tool":49,"command":50},"bunx","bunx skills add dbillion\u002Fhermes-skills-public --skill firecrawl-workflows",{"tool":52,"command":53},"pnpm","pnpm dlx skills add dbillion\u002Fhermes-skills-public --skill firecrawl-workflows","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ffirecrawl-workflows\u002FSKILL.md",[56],{"path":35,"resourceType":57,"resourceTypeDesc":58,"sizeBytes":59,"sourceHtmlUrl":60},"REFERENCE","参考文档",1992,"https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ffirecrawl-workflows\u002Freferences\u002Fworkflow-authoring.md",[62,70,77,86,93,100],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7B25T0V7RBKES86Y3RTXQRN","blocked-page-recovery","Use when a fetch fails: 403\u002F429, paywall, WAF, bot wall.","MIT","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fweb\u002Fblocked-page-recovery\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7B25DSBBMZRHVD28MAX7N5X","gemini-vision-fallback","Vision fallback: Gemini REST API if vision_analyze blocked.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fvision\u002Fgemini-vision-fallback\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":81,"licenseFileUrl":82,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7B22XW9QXT2ZWWXVZDFWYZP","twitter-cli","Use twitter-cli for ALL Twitter\u002FX operations — reading tweets, posting, replying, quoting, liking, retweeting, following, searching, user lookups. Invoke whenever user requests any Twitter interaction.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ftwitter-cli\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Ftwitter-cli\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7B22QMWY1B4F7BC114RG4S6","prism-scan","Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code\u002Fartifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-scan\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7B22JA5XCAP1ACT6V50WYR1","prism-reflect","Constraint transparency: analyzes an artifact structurally, then analyzes what its own analysis concealed. Produces a conservation law AND a constraint report showing what was maximized, what was sacrificed, and what to investigate next. The only AI skill that knows what it can't see.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-reflect\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":66,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7B22EB15M75M4X3C52YGDCC","prism-full","Full Prism: multi-pass structural analysis with mandatory adversarial self-correction. Designs custom analytical passes, executes them with chaining, then attacks its own findings before synthesizing. Use for maximum depth on important code or artifacts.","https:\u002F\u002Fgithub.com\u002Fdbillion\u002Fhermes-skills-public\u002Fblob\u002Fmaster\u002Fskills\u002Fts-superhermes-prism-full\u002FSKILL.md",[],[]]