firecrawl-download
将网站下载为本地文件
保存完整网站以供离线访问，无需手动逐页下载。Firecrawl-download 可自动映射站点并将内容提取到有条理的本地目录中。
Descargar el ZIP de la skill
Subir en Claude
Ve a Configuración → Capacidades → Skills → Subir skill
Activa y empieza a usar
Pruébalo
Usando "firecrawl-download". 以 Markdown 格式下载 https://docs.example.com
Resultado esperado:
- Created directory: .firecrawl/docs.example.com/
- Downloaded 23 pages to .firecrawl/docs.example.com/
- - index.md (Home page)
- - getting-started.md
- - api/reference.md
- - guides/quickstart.md
- ... (23 total files)
Usando "firecrawl-download". 启用截图下载
Resultado esperado:
- Created directory: .firecrawl/docs.example.com/
- Downloaded 15 pages with screenshots:
- - index.md + screenshot.png
- - installation.md + screenshot.png
- - configuration.md + screenshot.png
- Total: 30 files (15 markdown + 15 images)
Auditoría de seguridad
Riesgo bajoStatic analysis flagged 34 patterns across external_commands (23), network (6), and filesystem (3) categories. All findings evaluated as FALSE POSITIVES: external_commands are documented CLI usage with allowed-tools declaration, network URLs are documentation examples (docs.example.com), and filesystem references are markdown relative links to other skill files. No malicious intent detected. Minor risk from legitimate Bash command execution and network access for web scraping.
Problemas de riesgo bajo (3)
Factores de riesgo
⚙️ Comandos externos (4)
🌐 Acceso a red (6)
📁 Acceso al sistema de archivos (3)
Puntuación de calidad
Lo que puedes crear
文档归档
下载完整的软件文档站点，以便在旅行或低连接环境中离线参考。
竞品研究
保存竞争对手的产品页面和功能文档，以便进行分析比较，无需反复访问站点。
内容迁移备份
在迁移到新平台或重新设计之前，创建现有网站内容的本地备份。
Prueba estos prompts
Download all pages from https://docs.example.com as markdown files to my local machine.
Download the Firecrawl docs at https://docs.firecrawl.dev with screenshots of each page, limit to 50 pages.
Download only the SDK documentation from https://api.example.com/docs - include paths containing /sdks and /api, exclude all language translations.
Download https://knowledge.company.com including markdown, links, and full-page screenshots. Include only /features and /integration paths, exclude /internal and /draft. Wait for .content-loaded class before capturing.
Mejores prácticas
- 在自动化工作流程中始终使用 -y 标志以跳过交互式确认提示
- 使用 --limit 设置合理的页面限制，以避免意外的配额消耗
- 使用 --exclude-paths 过滤掉非必要内容，如翻译、草稿或内部页面
- 在进行大量下载之前，先使用较小的限制测试以验证配置
Evitar
- 在未设置页面限制的情况下下载整个大型站点
- 在缩略图视图就足够时对每个页面使用整页截图
- 在自动化脚本中运行下载时未使用 -y 标志导致挂起
- 包含不应本地缓存的敏感内部 URL