# Firecrawl Crawl

> Use when bulk extracting a website or site section through Firecrawl CLI, especially docs sections, many pages on one site, or ArkSpace web_crawl routing that selects Firecrawl.

- **Type:** Skill
- **Install:** `agentstack add skill-arch3rpro-ark-space-firecrawl-crawl`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [arch3rPro](https://agentstack.voostack.com/s/arch3rpro)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [arch3rPro](https://github.com/arch3rPro)
- **Source:** https://github.com/arch3rPro/ark-space/tree/main/skills/firecrawl-crawl

## Install

```sh
agentstack add skill-arch3rpro-ark-space-firecrawl-crawl
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Firecrawl Crawl

Use Firecrawl Crawl as a CLI-backed `web_crawl` provider when ArkSpace needs multi-page extraction from a known site or site section.

## Before Use

Resolve the installed ArkSpace package root before running commands. Replace `` with the directory two levels above this loaded `SKILL.md`, such as `/Users//.claude/plugins/cache/ark-space/ark-space/0.1.2`. Use the installed package path, not a repository-relative command.

Check configuration:

```bash
python3 /scripts/arkspace.py provider check firecrawl --capability web_crawl
```

Set up Firecrawl:

```bash
python3 /scripts/arkspace.py provider setup firecrawl --wizard
```

## Missing Configuration Recovery

If the provider check reports missing configuration, ask whether to start setup with `python3 /scripts/arkspace.py provider setup firecrawl --wizard`. Do not crawl with Firecrawl until the provider check succeeds.

## Helper Script

Crawl a docs section:

```bash
python3 /scripts/arkspace.py site crawl --provider firecrawl "https://docs.example.com" \
  --include-paths /docs \
  --limit 50 \
  --output json
```

## Routing Notes

- Use `registry/web-crawl-providers.yaml` before execution.
- Start with shallow depth and small limits.
- Use map first when the user only needs a specific page from a large site.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [arch3rPro](https://github.com/arch3rPro)
- **Source:** [arch3rPro/ark-space](https://github.com/arch3rPro/ark-space)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-arch3rpro-ark-space-firecrawl-crawl
- Seller: https://agentstack.voostack.com/s/arch3rpro
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.