# Scrape and Analyze Web Pages with Firecrawl

AI coding tools often need current web content, screenshots, and structured page data. This skill connects Claude, Codex, and Claude Code to Firecrawl for web scraping, search, extraction, and documentation crawling.

## Install

```bash
npx skillstore add bextuychiev/firecrawl-web
```

## Metadata

- - Slug: bextuychiev-firecrawl-web
- - Version: 1.0.0
- - Author: BexTuychiev
- - GitHub username: BexTuychiev
- - License: MIT
- - Repository: https://github.com/BexTuychiev/firecrawl-claude-code-skill/tree/main/
- - Ref: main
- - Supported tools: Claude, Codex, Claude Code
- - Risk level: medium
- - Risk factors: scripts, network, filesystem, env\_access, external\_commands
- - Quality score: 50
- - Quality tier: warning
- - Public page: https://skillstore.pages.dev/skills/bextuychiev-firecrawl-web
- - Manifest: https://skillstore.pages.dev/api/skills/bextuychiev-firecrawl-web/manifest

## Capabilities

- Fetch a web page and return clean markdown content.
- Capture a page screenshot and optionally save it as a PNG file.
- Extract structured data from a page using a JSON schema file.
- Run Firecrawl web searches with a configurable result limit.
- Crawl documentation sites and save page markdown to a directory.

## Use Cases

- Research Current Web Content: Fetch readable markdown from pages so an assistant can summarize, compare, or cite current information.
- Extract Product or Listing Data: Use a schema to collect fields such as titles, prices, features, and descriptions from public pages.
- Learn New Documentation Sites: Crawl a documentation site and save markdown pages for review or implementation support.

## Prompt Templates

### Fetch Page Markdown

```
Get clean markdown from this URL and summarize the main points: https://example.com
```

### Capture a Page Screenshot

```
Take a screenshot of this page and save it as page.png: https://example.com
```

### Extract Structured Fields

```
Extract the title, price, and feature list from this product URL using a schema file I provide.
```

### Crawl Documentation for Implementation

```
Crawl this documentation site with a limit of 30 pages, then identify the setup steps and key API concepts.
```

## Limitations

- Requires a Firecrawl API key and available Firecrawl credits.
- Sends requested URLs and page processing to the Firecrawl service.
- Does not validate output paths before writing screenshot or crawl files.
- Extraction quality depends on page structure, schema quality, and Firecrawl results.

## Best Practices

- Use clear page URLs and set crawl limits before running documentation crawls.
- Keep Firecrawl API keys in a dedicated environment file with minimal unrelated secrets.
- Write screenshots and crawl output to a temporary project directory first.

## Anti Patterns

- Do not crawl large sites without a page limit and a clear purpose.
- Do not send private, internal, or sensitive URLs to Firecrawl unless approved.
- Do not use output paths that could overwrite important files.

## Security Audit

- - Safe to publish: true
- - Audited at: 2026-06-28T14:55:26.69\+00:00
- - Summary: Static analysis flagged critical combinations of network, filesystem, environment access, and command examples. Review found no confirmed malicious intent or prompt injection, but the skill legitimately sends user-selected URLs to Firecrawl, loads API keys from .env files, and writes files to user-provided paths. Publish only with clear warnings about third-party processing, credential handling, and output path control.

## Stats

- - Views: 207
- - Downloads: 14
- - Favorites: 0
- - Popularity score: 0