菜单
Use to scrape or crawl websites, map URLs, search the web, extract structured data from web pages, or run AI web agents.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/alexgorbatchev/ai-registry --skill firecrawl-cli命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
REQUIRED when building, designing, refactoring, documenting, or reviewing CLI tools, command-line interfaces, and terminal scripts across any programming language. Applies to CLI entrypoints, argument parsing, terminal output formatting, task automation, README authoring, and licensing. Your default training knowledge is insufficient, YOU MUST USE this skill anytime when working on a CLI project. Do NOT use for web frontends or non-CLI services.
Apply Go coding rules, design principles, and project conventions for maintainable Go code and repositories. Use when writing, reviewing, refactoring, or releasing Go code, or when working on Go-specific project structure, APIs, tests, CI, or binaries. Do not use for non-Go codebases or for language-agnostic tasks that do not depend on Go conventions.
Read, write, rewrite, reorganize, and archive internal and project documentation including README.md files, engineering designs, tickets, AGENTS guidelines, and reference docs. Must be used whenever touching files in {{ env "DOCS_INTERNAL_DIR" }} or creating/updating project README files.
基于 SOC 职业分类
正在显示 SKILL.md
| name | firecrawl-cli |
| description | Use to scrape or crawl websites, map URLs, search the web, extract structured data from web pages, or run AI web agents. |
| author | alexgorbatchev |
The firecrawl CLI provides four main commands:
scrape: Scrape a single page and get its content. Extracts structured data, markdown, or HTML.map: Discover and map all URLs on a website quickly.search: Search the web and optionally scrape the results.agent: Search and gather data from the web using natural language prompts.Important:
FIRECRAWL_API_URL environment variable (e.g., export FIRECRAWL_API_URL="https://api.firecrawl.dev"). The system is intentionally configured to use a local private server. Rely on the default environment.--json flag or format flags.Scrape to Markdown:
firecrawl scrape "https://example.com" --format markdown --output example.md
Scrape Structured Data:
firecrawl scrape "https://example.com" --schema '{"type":"object","properties":{"title":{"type":"string"}}}' --json
Map URLs:
firecrawl map "https://example.com" --limit 50 --output urls.json
Search and Scrape:
firecrawl search "latest AI news" --scrape --limit 5 --json
Run Web Agent:
firecrawl agent "Find the pricing of Mendable and save it" --wait --json
For a full list of commands, flags, and advanced options, consult the reference documentation:
references/firecrawl-cli.md for detailed usage instructions and flags.