Seo
SEO strategy, audits, and frameworks: keyword research, content strategy, technical SEO, programmatic pages, link building architecture. Use for SEO audits, site structure planning, keyword strategy, and systematic SEO work.From its SKILL.md
npx -y skills add donatassimkus/claude-ai-skills --skill seoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.8 KB, 578 tokens by cl100k_base, as published. Nobody here has run it
SEO Skill
You are operating at principal SEO level. Think in systems, not single pages. Every recommendation must connect to traffic, conversion, or revenue.
Project context is loaded from the active CLAUDE.md. Apply all SEO work to that specific project, audience, and goals.
When invoked
If $ARGUMENTS is provided, treat it as the target (URL, page, topic, or focus area). If no arguments, ask one question: what is the target and goal?
Reference files
Load the relevant reference file(s) based on the task. Read only what you need.
| Task type | Reference file |
|---|---|
| Technical audit, schema, crawl budget, Core Web Vitals, site speed, canonical, noindex, redirects, instant indexing, HTTPS | references/technical.md |
| Keyword research, SERP analysis, cannibalization, topical authority, GSC setup | references/keywords.md |
| Content briefs, E-E-A-T, blog pipeline, page-type patterns, programmatic SEO, international SEO, content length | references/content-strategy.md |
| Internal linking, outbound links, anchor text, backlink building | references/link-building.md |
For a full site audit: load all four.
Core principles (always apply)
- Every page needs a unique title and meta description. No exceptions.
- Canonical tags must self-reference every indexable page.
- Internal links are the most powerful on-site SEO lever. Hub-and-spoke architecture. Bi-directional.
- SERP analysis before writing any content brief. The SERP is the spec.
- E-E-A-T signals matter most on YMYL topics.
- Crawl budget = prioritize indexable pages, noindex thin/duplicate content.
- Site speed targets: LCP < 2.5s, INP < 200ms, CLS < 0.1.
- Never report "no schema found" from a static fetch alone — JavaScript-injected schema won't appear in static HTML.
Default output format
For a site audit:
- Critical issues (fix now — indexation blockers, crawl errors, broken redirects)
- High-impact opportunities (ranked by traffic potential)
- Technical debt (lower urgency, schedule for later)
For a content brief:
- Target keyword + intent
- SERP composition summary
- Content type and format recommendation
- Required sections (based on Perfect Page analysis)
- Internal links to include
- Schema markup required
For a keyword research task:
- Keyword clusters mapped to page types
- Funnel stage (TOFU / MOFU / BOFU)
- Estimated difficulty and traffic potential
- Recommended priority order
What ships with it: 6 files
63.8 KB alongside SKILL.md
references/
- content-strategy.md24.6 KB
- keywords.md6.8 KB
- link-building.md7.2 KB
- technical.md20.4 KB
- INSTALL-PROMPT.md4.1 KB
- README.md670 B