Firecrawl CLI
Use Firecrawl's CLI to scrape single pages, crawl entire sites, search the web, and map site structures — all returning clean, LLM-ready markdown. Handles JavaScript-rendered pages, bypasses common anti-bot measures, and extracts structured data. Use it when you need to pull content from websites for analysis, research, data extraction, or content migration.
MCP-powered — requires setup
This skill uses external tools via the Model Context Protocol. You'll need to configure the following MCPs before installing.
Required MCPs
Web scraping, crawling, and search via the Firecrawl API
View config snippet
{
"mcpServers": {
"firecrawl": {
"command": "npx",
"args": ["-y", "firecrawl-mcp"],
"env": {
"FIRECRAWL_API_KEY": "your_firecrawl_api_key"
}
}
}
}Setup steps
- Set up each required MCP using the configs above
- Download the skill file below
- Open the skill manager in Claude — in the desktop app underCode → Customize, or on claude.ai underCustomize → Skills
- Click Create a new skill (use + on claude.ai) and upload the downloaded file
- Start a new session — your MCPs and skill will both be active
- Use a trigger phrase to activate
The MCP setup steps above are written for Claude. If your platform also supports MCP, configure the same servers using its own MCP settings. The skill file works either way.
- Download the skill file below
- Place it at
.cursor/skills/firecrawl-cli/SKILL.md(rename the downloaded file toSKILL.md). The shared.agents/skills/firecrawl-cli/SKILL.mdpath also works - Cursor loads the skill when your task matches its description. Say a trigger phrase to activate it
The MCP setup steps above are written for Claude. If your platform also supports MCP, configure the same servers using its own MCP settings. The skill file works either way.
- Download the skill file below
- In ChatGPT, create a Project and attach the file (or paste its contents into the project instructions). For a reusable setup, build a Custom GPT via Explore GPTs → Create and add the file there
- Start a chat in that Project or GPT, then say a trigger phrase to activate it
The MCP setup steps above are written for Claude. If your platform also supports MCP, configure the same servers using its own MCP settings. The skill file works either way.
- Download the skill file below
- Place it at
.github/skills/firecrawl-cli/SKILL.mdin your repository (rename the downloaded file toSKILL.md) - Copilot loads the skill when it is relevant to your task. Say a trigger phrase to activate it
The MCP setup steps above are written for Claude. If your platform also supports MCP, configure the same servers using its own MCP settings. The skill file works either way.
- Download the skill file below
- Place it at
.agents/skills/firecrawl-cli/SKILL.mdin your repository (rename the downloaded file toSKILL.md) - Codex loads the skill when your task matches, or invoke it explicitly with
/skills. Say a trigger phrase to activate it
Your skill is downloading.
Get an email when we ship new skills and updates.
You're on the list. We'll email you when new skills drop.
What Claude does with this skill
The following is the exact SKILL.md content Claude reads when this skill is active. It defines Claude's role, what triggers it, and the step-by-step instructions it follows.
Firecrawl CLI
Role
You are a web data extraction specialist. You use Firecrawl to scrape, crawl, search, and map websites, returning clean structured content for analysis or downstream use.
When to Activate
Activate when the user wants to scrape a webpage, crawl a site, search the web, extract structured data from URLs, or map a site’s structure.
Prerequisites Check
Verify the Firecrawl MCP is connected with a valid API key. If not, guide setup.
Step-by-Step Instructions
Step 1: Determine the Operation
- Scrape: Single page → clean markdown
- Crawl: Entire site or section → multiple pages as markdown
- Search: Web search → relevant results with content
- Map: Site structure → URL tree / sitemap
- Extract: Structured data extraction with a schema
Step 2: Configure
For the chosen operation, determine:
- Target URL(s) or search query
- Depth/limits for crawls (max pages, URL patterns to include/exclude)
- Output format preferences (markdown, structured JSON, specific fields)
- Any extraction schema for structured data
Step 3: Execute
Run the operation via Firecrawl MCP. For large crawls, set reasonable limits and report progress.
Step 4: Deliver Results
Present the extracted content in the most useful format:
- Single scrapes: clean markdown content
- Crawls: summary with key pages and their content
- Searches: ranked results with snippets
- Maps: hierarchical URL structure
- Extractions: structured data in the requested format
Output Format
Clean, well-formatted content appropriate to the operation type. For large result sets, summarize and offer to drill into specific pages.