跳转到主要内容
此内容尚未提供您的语言版本,正在以英文显示。

Firecrawl CLI

技能 已验证 活跃
属于:Firecrawl

Web search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "search for", "find me", "look up", "what are people saying about", or "find articles about". Returns real search results with optional full-page markdown — not just snippets. Provides capabilities beyond Claude's built-in WebSearch.

目的

To provide developers and users with a powerful, scriptable tool for efficiently retrieving and processing web content directly from the terminal.

功能

  • Web search with full page content extraction
  • Scraping specific URLs or multiple URLs
  • Discovering all URLs on a website
  • Crawling entire websites
  • AI agent for autonomous web data extraction
  • Interactive browser session for page interaction
  • Configuration for API keys and self-hosted instances

使用场景

  • Researching topics and gathering information from the web
  • Extracting structured data from websites for analysis
  • Automating the process of finding and collecting web content
  • Building applications that require real-time web data

非目标

  • Replacing a user's browser for general browsing
  • Performing destructive operations on websites
  • Storing or managing user-specific browsing history beyond session profiles

工作流

  1. User specifies a web-related task (search, scrape, crawl, agent).
  2. User provides query, URL(s), schema, or prompts.
  3. CLI tool processes the input, potentially authenticating with Firecrawl API.
  4. CLI executes the task using Firecrawl's backend services.
  5. Results are outputted to stdout, a specified file, or processed via agent/interact sessions.

安装

请先添加 Marketplace

/plugin marketplace add firecrawl/cli
/plugin install cli@firecrawl

质量评分

已验证
97 /100
1 day ago 分析

信任信号

最近提交2 days ago
星标383
许可证MIT
状态
查看源代码

类似扩展

Agent Browser

100

AI 代理的浏览器自动化 CLI。当用户需要与网站交互时使用,包括浏览页面、填写表单、点击按钮、截屏、提取数据、测试 Web 应用或自动化任何浏览器任务。触发条件包括请求“打开网站”、“填表”、“点击按钮”、“截屏”、“抓取页面数据”、“测试此 Web 应用”、“登录网站”、“自动化浏览器操作”或任何需要以编程方式进行 Web 交互的任务。

技能
shanraisshan

Project Session Manager

100

Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions

技能
Yeachan-Heo

Oh My Claudecode

100

Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

技能
Yeachan-Heo

Github

100

Use gh for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.

技能
steipete

Telegram Crabbox E2e Proof

100

Use when reviewing, reproducing, or proving OpenClaw Telegram behavior with a real Telegram user on Crabbox, including PR review workflows that need an agent-controlled Telegram Desktop recording, TDLib user-driver commands, Convex-leased credentials, WebVNC observation, and motion-trimmed artifacts.

技能
steipete

Manus

100

Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.

技能
sanjay3290