Skill

/crawl4ai:setup

Set up the Crawl4AI plugin for Claude Code.

npx claudepluginhub unclecode/crawl4ai-cloud-sdk --plugin crawl4ai

Tool Access

This skill uses the workspace's default tool permissions.

Preview

Set up the Crawl4AI plugin for Claude Code.

SKILL.md

Similar Skills

firecrawl

Scrapes URLs to markdown/HTML/JSON, crawls websites for multi-page extraction, searches the web, maps sites, and extracts structured data using Firecrawl MCP tools.

7 tools

b00t

firecrawl

365

Searches the web, scrapes URLs, crawls sites, and interacts with dynamic pages using Firecrawl CLI for clean markdown output.

2 files2 tools

firecrawl

tavily-crawl

203

Crawls websites to extract content from multiple pages via Tavily CLI. Saves pages as local markdown files with depth/breadth limits, path filtering, and semantic instructions. Use for bulk doc downloads or site content collection.

1 tool

tavily

Stats

Parent Repo Stars3

Parent Repo Forks1

Last CommitFeb 9, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

/crawl4ai:setup

Set up the Crawl4AI plugin for Claude Code.

Instructions

Guide the user through setup:

Check current config: Read ~/.crawl4ai/claude_config.json if it exists. Report current mode and whether API key is set.

Choose mode: Ask the user:

Cloud mode (default): Uses the Crawl4AI cloud API. Requires an API key from https://crawl4ai.com. Fast, no local browser needed.
Local mode: Uses OSS crawl4ai with a local Chromium browser. Free, no API key needed. Requires pip install crawl4ai && crawl4ai-setup.

Configure based on choice:

For cloud mode:

Ask for API key (starts with sk_live_ or sk_test_)
Write config to ~/.crawl4ai/claude_config.json:
```
{"mode": "cloud", "api_key": "sk_live_xxx"}
```
Or suggest setting CRAWL4AI_API_KEY env var

For local mode:

Check if crawl4ai is installed: python3 -c "import crawl4ai; print(crawl4ai.__version__)"
If not installed, run: pip install crawl4ai && crawl4ai-setup
Write config: {"mode": "local"}

Verify setup: Use the crawl MCP tool to crawl https://example.com. Confirm it returns markdown content.

Report status: Tell the user their setup is complete and which mode is active.

/crawl4ai:setup

Set up the Crawl4AI plugin for Claude Code.

Instructions

Guide the user through setup:

Check current config: Read ~/.crawl4ai/claude_config.json if it exists. Report current mode and whether API key is set.
Choose mode: Ask the user:
- Cloud mode (default): Uses the Crawl4AI cloud API. Requires an API key from https://crawl4ai.com. Fast, no local browser needed.
- Local mode: Uses OSS crawl4ai with a local Chromium browser. Free, no API key needed. Requires pip install crawl4ai && crawl4ai-setup.
Configure based on choice:

For cloud mode:
- Ask for API key (starts with sk_live_ or sk_test_)
- Write config to ~/.crawl4ai/claude_config.json:
```
{"mode": "cloud", "api_key": "sk_live_xxx"}
```
- Or suggest setting CRAWL4AI_API_KEY env var
For local mode:
- Check if crawl4ai is installed: python3 -c "import crawl4ai; print(crawl4ai.__version__)"
- If not installed, run: pip install crawl4ai && crawl4ai-setup
- Write config: {"mode": "local"}
Verify setup: Use the crawl MCP tool to crawl https://example.com. Confirm it returns markdown content.
Report status: Tell the user their setup is complete and which mode is active.