Skill3.8k repo starsupdated 4mo ago

firecrawl-scrape

The firecrawl-scrape skill extracts content from web pages or search results using the Firecrawl API, returning structured data in markdown, HTML, or plain text formats. Use this skill when you need to retrieve and parse website content, gather information from specific URLs, or conduct web searches to extract relevant information for analysis or processing.

View source Repository: Continuous-Claude-v3

Install in Claude Code

Copy

git clone --depth 1 https://github.com/parcadei/Continuous-Claude-v3 /tmp/firecrawl-scrape && cp -r /tmp/firecrawl-scrape/.claude/skills/firecrawl-scrape ~/.claude/skills/firecrawl-scrape

Then start a new Claude Code session; the skill loads automatically.

Definition

SKILL.md

# Firecrawl Scrape Skill

## When to Use

- Scrape content from any URL
- Extract structured data from web pages
- Search the web and get content

## Instructions

```bash
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://example.com" \
    --format "markdown"
```

### Parameters

- `--url`: URL to scrape
- `--format`: Output format - `markdown`, `html`, `text` (default: markdown)
- `--search`: (alternative) Search query instead of direct URL

### Examples

```bash
# Scrape a page
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --url "https://docs.python.org/3/library/asyncio.html"

# Search and scrape
uv run python -m runtime.harness scripts/mcp/firecrawl_scrape.py \
    --search "Python asyncio best practices 2024"
```

## MCP Server Required

Requires `firecrawl` server in mcp_config.json with FIRECRAWL_API_KEY.