firecrawl / firecrawl/firecrawl-claude-plugin

Claude Plugin page lists commands that don't exist

Open
#8 0 comments 1 reaction 0 assignees View on GitHub
Dominant language
No language data
Stars
218
Forks
27
Avg merge
1m
Merged PRs (30d)
9

Description

The [Firecrawl plugin page on Claude](https://claude.com/plugins/firecrawl) lists the following commands under "How to use":

> After installing, run `/firecrawl:setup` to configure your API key. Then use these commands to get started:
>
> - `/firecrawl:scrape` — Extract a single webpage as clean markdown.
> - `/firecrawl:crawl` — Crawl and extract content from an entire website.
> - `/firecrawl:search` — Search the web and get scraped results.
> - `/firecrawl:map` — Discover all URLs on a site.
> - `/firecrawl:agent` — Describe what data you need and let the AI agent autonomously find and extract it.

None of these commands exist in the plugin (v1.0.3). The plugin actually provides:

- `/firecrawl` — the skill that teaches Claude to use the `firecrawl` CLI
- `/firecrawl:skill-gen` — generates agent skills from documentation URLs

There is no `/firecrawl:setup` command. Authentication is handled by the CLI itself (`firecrawl login --browser` or the `FIRECRAWL_API_KEY` env var).

The listed commands (`scrape`, `crawl`, `search`, `map`, `agent`) are CLI subcommands, not plugin slash commands. The plugin's skill instructs Claude to call these via the CLI (e.g., `firecrawl scrape `), but they aren't available as `/firecrawl:*` commands.

This is confusing for new users who install the plugin and immediately try `/firecrawl:setup` with nothing happening.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.