seo-firecrawl
An agent skill by AgriciDaniel, from AgriciDaniel/claude-seo. Tags: crawling, scraping, seo, site-map, web.
What it does
Full-site crawling, scraping, and site mapping via Firecrawl MCP. Use when user says "crawl site", "map site", "full crawl", "find all pages", "broken links", "site structure", "discover pages", "JS rendering", or needs site-wide analysis.
Install
With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:
npx skills add AgriciDaniel/claude-seo --skill seo-firecrawlOr copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):
git clone --depth 1 https://github.com/AgriciDaniel/claude-seo
cp -r claude-seo/extensions/firecrawl/skills/seo-firecrawl ~/.claude/skills/seo-firecrawlSafety box score
Grade B, low risk: 16 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.
This skill adds Firecrawl-based site crawl/map/scrape/search capabilities for arbitrary URLs, so the main exposure is sending site data off-machine to a remote crawling service. It also asks the user to run an installer script and configure an API key, but it does not itself show destructive filesystem or privilege-changing behavior.
| Category | Level | Why |
|---|---|---|
| Code & shell execution | 1 (low) | It instructs the user to run `./extensions/firecrawl/install.sh`, which is a shell installer; the script itself is not included here, so its effects are not visible in this review. |
| Network access | 2 (moderate) | The core purpose is remote crawling and scraping via Firecrawl MCP (`firecrawl_crawl`, `firecrawl_map`, `firecrawl_scrape`, `firecrawl_search`), which sends target URLs and page content to an external service. |
| Filesystem reach | 0 (none) | The skill description only talks about crawling and scraping websites; it does not read, write, or delete local files outside the project. |
| Secrets & credentials | 1 (low) | It references `FIRECRAWL_API_KEY not set` and relies on Firecrawl configuration, implying use of an API credential that leaves the local machine when the service is used. |
| Privilege & persistence | 0 (none) | There is no request for sudo, global installs, services, scheduled tasks, or shell/OS settings changes in the visible skill text. |
| Instruction hijack surface | 0 (none) | The visible text does not tell the agent to ignore its rules, hide information, or follow remote instructions; it only describes how to use Firecrawl tools. |
| Irreversible actions | 0 (none) | It automates site analysis, but it does not push, publish, pay, book, or delete anything, so there is no high-risk autonomous action in the stated behavior. |
| Transparency | 0 (none) | The provided files are plain markdown; there are no binaries, blobs, or generated code in the visible skill content. |
Before installing
- Read `./extensions/firecrawl/install.sh` before running it.
- Confirm whether Firecrawl requests go through your own account/API key and what data is sent off-machine.
- Test on a non-sensitive site with a small crawl limit before using production or private URLs.
- Check the expected credit usage and rate limits for the target crawl size.
Rated 2026-10-19 by an automated review of 2 files from the skill's repository.
Source
- Repository
- AgriciDaniel/claude-seo (all skills from this repository)
- Path
- extensions/firecrawl/skills/seo-firecrawl/SKILL.md
- Branch
- main
- Collection
- claude-seo
- Updated
- 2026-09-21
Related skills
- seo — Comprehensive SEO analysis for any website or business type.
- seo-page — Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance.
- seo-sitemap — Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure.
- programmatic-seo — When the user wants to create SEO-driven pages at scale using templates and data.
- schema — When the user wants to add, fix, or optimize schema markup and structured data on their site.
- site-architecture — When the user wants to plan, map, or restructure their website's page hierarchy, navigation, URL structure, or internal linking.