Install
$ agentstack add skill-donatassimkus-claude-ai-skills-seo ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
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
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: donatassimkus
- Source: donatassimkus/claude-ai-skills
- License: MIT
- Homepage: https://donatassimkus.com/ai-skills
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.