seo-firecrawl
Skill10 starsChanged 27 days agoMITView on GitHub
Site crawling, mapping, and JS-rendered scraping via the Firecrawl MCP when connected; otherwise builds a URL inventory from the sitemap and does targeted page fetches with the built-in fetcher, naming what a full crawl would add. Trigger when the user says "crawl site", "map site", "full crawl", "find all pages", "broken links", "site structure", "discover pages", "JS rendering", "scrape with javascript".
- Reads credentials
4 other projects use a version of this.
Adopted by
Most recently taken up by
- seranking/seo-skillstheir own version, first seen Nov 8, 2026
- webdevarif/claude-skillstheir own version, first seen Oct 20, 2026
- Biznomad/claude-skillstheir own version, first seen Jul 14, 2026
- amirjahfar1/automate-seo-with-claudetheir own version, first seen Jun 9, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- seranking/seo-skills★ 201same name
- amirjahfar1/automate-seo-with-claude★ 2same name
- Biznomad/claude-skills★ 0same name
- webdevarif/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- blast-promptSkill
- client-outreachSkill
- content-draftSkill
- copywritingSkill
- csv-to-reportSkill
- design-accessibilitySkill
- design-buildSkill
- design-croSkill
- design-dimensionsSkill
- design-motionSkill
- design-researchSkill
- design-system-genSkill
- design-system-persistSkill
- design-tokens-emitSkill
- design-visual-qaSkill
- html-extractSkill
- parallel-buildSkill
- portable-html-portSkill
- qa-gateSkill
- route-codex-reviewSkill
- route-gemini-contextSkill
- route-three-brainSkill
- seo-auditSkill
- seo-backlinksSkill
- seo-clusterSkill
- seo-competitor-pagesSkill
- seo-content-briefSkill
- seo-contentSkill
- seo-dataforseoSkill
- seo-driftSkill
- seo-ecommerceSkill
- seo-geoSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-image-auditSkill
- seo-image-genSkill
- seo-local-unifiedSkill
- seo-pageSkill
- seo-programmaticSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-strategySkill
- seo-sxoSkill
- seo-technicalSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 3 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 34
Detect tooling: Check whether the Firecrawl MCP is exposed this session (run python3 …
- Very specific: line 36
Crawl path (Tier 1, if connected): Run the Firecrawl MCP crawl/map/scrape for the requested depth.
- Distinctive: line 49
Tier 1 — Firecrawl MCP: If connected, use it for multi-page crawl, JS rendering, and batch scrape.
- Distinctive: line 54
Tier 4 — guided: If the site is JS-rendered and Firecrawl isn't connected, deliver the sitemap inventory and note that full rendering needs …
- Distinctive: line 58
Always state which tier ran and what a full crawl would add.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
seo-firecrawl
Family: seo Status: Stable
Purpose
Site-level discovery and scraping. Tool-aware: with the Firecrawl MCP connected it does true multi-page crawling and JS-rendered scraping (for sites where a plain HTTP fetch returns an empty shell); without it, it builds a URL inventory from the sitemap and fetches the pages you point it at — a real, useful map on the free path.
Triggers
- "crawl site" / "full crawl"
- "map site" / "site structure"
- "find all pages" / "discover pages"
- "broken links"
- "JS rendering" / "scrape with javascript"
Inputs
- Starting URL (and sitemap URL if known)
- Crawl depth / page cap (Tier 1) or the specific pages to fetch (Tier 2)
- Output format (URL inventory | per-page markdown | broken-link list)
Steps
- Detect tooling. Check whether the Firecrawl MCP is exposed this session
(run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/workflow/capability_probe.py"— it also reportsFIRECRAWL_API_KEY). - Crawl path (Tier 1, if connected). Run the Firecrawl MCP crawl/map/scrape for the requested depth; return the URL inventory + per-page markdown + broken links.
- Built-in path (Tier 2, always available). Fetch
sitemap.xml(or the given sitemap) and runpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/sitemap_tools.py" --validateto get a structured URL inventory; fetch the priority pages with WebFetch; flag fetch failures as likely broken links. State that JS-rendered-only content and large-scale crawls need Tier 1. - Report which tier ran and what a full Firecrawl crawl would add.
Capability routing
This skill follows the plugin's capability-tier cascade
(references/CAPABILITY-TIERS.md):
- Tier 1 — Firecrawl MCP. If connected, use it for multi-page crawl, JS rendering, and batch scrape.
- Tier 2 — built-in (default). Otherwise
sitemap_tools.pyfor the URL inventory + WebFetch for targeted pages. Produces a real site map for static/server-rendered sites. - Tier 4 — guided. If the site is JS-rendered and Firecrawl isn't connected, deliver the sitemap inventory and note that full rendering needs Firecrawl (or the Playwright extension for interaction-heavy pages).
Always state which tier ran and what a full crawl would add.
Outputs
- URL inventory (from crawl on Tier 1; from sitemap on Tier 2)
- Per-page content as markdown for the pages retrieved
- Broken-link list (crawl-wide on Tier 1; from fetch failures on Tier 2)
Dependencies
- Optional (Tier 1): Firecrawl MCP (
extensions/firecrawl/) — adds full crawl + JS rendering; free path works without it - Built-in (Tier 2): WebFetch;
scripts/seo/sitemap_tools.py scripts/workflow/capability_probe.py
Notes
Backbone of seo-audit and design-research when a full crawl is needed. For pages
that require interaction beyond rendering, pair with the Playwright extension.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

