使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-company-directories开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Firecrawl Company Directories
Use this to turn startup or company directories into structured lists.
Onboarding Interview
Infer the directory, filters, result count, and output format from context. If the source is clear, proceed immediately.
Ask at most 1-3 concise questions only if blocked, such as the directory URL/name, required filters, or target result count.
Firecrawl Collection Plan
Use Firecrawl browser when the directory needs filters, pagination, infinite scroll, or profile clicks. Use scrape/map when listings are public and static.
Suggested sources include YC companies, Crunchbase, Product Hunt, G2 categories, or any custom directory URL.
Extraction Fields
Capture fields that are visible:
- name
- description
- industry/category
- stage/founded/location/team size/funding when visible
- tags
- directory profile URL
- company website URL
Leave unavailable fields blank. Do not infer.
Final Deliverable
# Company Directory Export: [Source]
## Summary
[Filters, count extracted, limitations]
## Companies
[Table or link to JSON/CSV]
## Sources
[Directory pages and profiles used]
## Rerun Inputs
workflow: firecrawl-company-directories
directory: [source]
filters: [criteria]
max_results: [number]
output: [json/csv/markdown]JSON Shape
Use source, filters, extractedAt, totalResults, and companies[] with name, url, description, industry, stage, founded, location, teamSize, funding, tags, profileUrl, and websiteUrl.
Quality Bar
- Deduplicate companies.
- Track pagination progress.
- Note rate limits, login walls, or CAPTCHA blocks.
