Autosearch fetch-firecrawl

Use to scrape a URL into clean Markdown when the page is JS-rendered, behind anti-bot, or a PDF — and FIRECRAWL_API_KEY is available. Degrades gracefully to warn when key is missing.

install

source · Clone the upstream repo

git clone https://github.com/0xmariowu/Autosearch

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/0xmariowu/Autosearch "$T" && mkdir -p ~/.claude/skills && cp -r "$T/autosearch/skills/tools/fetch-firecrawl" ~/.claude/skills/0xmariowu-autosearch-fetch-firecrawl && rm -rf "$T"

manifest: autosearch/skills/tools/fetch-firecrawl/SKILL.md

source content

Overview

Firecrawl turns any URL into clean Markdown via a managed browser cluster. Handles JS rendering, anti-bot defenses, and PDFs. Paid per-page; requires

FIRECRAWL_API_KEY

. When the key is missing,

doctor()

reports

warn

When to Choose It

Page is heavily JS-rendered (SPA, React, Next.js)
Target site blocks
```
fetch-jina
```
or
```
fetch-crawl4ai
```
PDF or document conversion needed

How To Use

Call via

run_channel("fetch-firecrawl", url)

where the query IS the URL to scrape. Returns one Evidence item with

body

= full Markdown content.

Quality Bar

Evidence items have non-empty title and url.
No crash on empty or malformed API response.
Source channel field matches the channel name.