seo
Skill258 starsChanged 28 days agoMITView on GitHub
Use this skill to audit a site's code for search and AI-answer visibility and fix what matters: 'audit my SEO,' 'how do I rank,' 'why don't I show up on Google,' 'SEO review,' 'optimize for AI answers,' 'what pages should I create for SEO,' or 'meta tags and sitemap.' Claude scans the codebase, grades it, writes a prioritized plan with file paths, and offers to make the fixes. Not for writing blog posts in the founder's voice (use content) or for the sales page itself (use landing-page).
156 other projects use a version of this.
Adopted by
Most recently taken up by
- Rojios/everything-claude-codetheir own version, first seen Nov 8, 2026
- mazzeoia/MazyOStheir own version, first seen Nov 8, 2026
- ahmadvahidi/skill-atlastheir own version, first seen Nov 8, 2026
- GstMirabal/Token-Optimized-Agent-Pipelinetheir own version, first seen Nov 8, 2026
- alpit-patel/seo-aeo-geo-kittheir own version, first seen Nov 8, 2026
- Mahesh-Bishnoi/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use seo-agentic, seo-maps and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AgriciDanielSkillseo-agentic
Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Use when the user asks whether AI agents can use or browse the site, or about llms.txt or WebMCP. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).
Also in 5 projects that use this
timruebenachSkillseo-maps
Maps intelligence for local SEO — geo-grid rank tracking, GBP profile auditing via API, review intelligence across Google/Tripadvisor/Trustpilot, cross-platform NAP verification (Google/Bing/Apple/OSM), competitor radius mapping, and LocalBusiness schema generation from API data. Three-tier capability: free (Overpass + Geoapify), DataForSEO (full intelligence), DataForSEO + Google (maximum coverage). Use when user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", "maps analysis", "local rank tracking", "Share of Local Voice", or "SoLV".
Also in 17 projects that use this
megastepSkillseo-images
Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, and CLS prevention. Use when user says "image optimization", "alt text", "image SEO", "image size", or "image audit".
Also in 24 projects that use this
timruebenachSkillseo-image-gen
AI image generation for SEO assets: OG/social preview images, blog hero images, schema images, product photography, infographics. Powered by Gemini via nanobanana-mcp. Requires banana extension installed. Use when user says \"generate image\", \"OG image\", \"social preview\", \"hero image\", \"blog image\", \"product photo\", \"infographic\", \"seo image\", \"create visual\", \"image-gen\", \"favicon\", \"schema image\", \"pinterest pin\", \"generate visual\", \"banner\", or \"thumbnail\".
Also in 15 projects that use this
megastepSkillseo-sitemap
Analyze existing XML sitemaps or generate new ones with industry templates. Validates format, URLs, and structure. Use when user says "sitemap", "generate sitemap", "sitemap issues", or "XML sitemap".
Also in 26 projects that use this
renepfSkillorch-pipeline
Shared orchestration engine for the orch-* skill family. Defines the gated Research-Plan-TDD-Review-Commit pipeline, the size classifier, the agent map, and the two human gates that the orch-* operation skills delegate to. Not usually invoked directly.
Also in 4 projects that use this
- +3 more from timruebenach
- +1 more from megastep
Other versions156 projects use a version of this.
Word for word · 1
- whawkinsiv/solo-founder-skills★ 260100% same
Edited · 0
None found.
Wrote their own version · 155
- AgriciDaniel/claude-seo★ 20ksame name
- midudev/preguntas-entrevista-react★ 7.8ksame name
- legions-developer/evilcharts★ 3.2ksame name
- gridaco/grida★ 2.7ksame name
- midudev/la-velada-web-oficial★ 1.9ksame name
- midudev/tailwind-animations★ 1.5ksame name
- Bhanunamikaze/Agentic-SEO-Skill★ 993same name
- legions-developer/invoicely★ 923same name
- Nexus-JPF/note-companion★ 874same name
- iannuttall/seo★ 610same name
145 more not listed
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 repository20 other files it gives its agents.
- about-meSkill
- beautifySkill
- buildSkill
- contentSkill
- domain-nameSkill
- emailSkill
- financesSkill
- first-customersSkill
- focusSkill
- go-liveSkill
- humanizeSkill
- is-this-an-appSkill
- journeySkill
- landing-pageSkill
- legalSkill
- paymentsSkill
- pricingSkill
- retentionSkill
- secureSkill
- validateSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 144 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Read CLAUDE.md or README to learn what the product is and who it is for.
- Distinctive: line 29
No render-blocking scripts.
- Distinctive: line 46
Search Console is verified, or a step to verify it is listed.
- Distinctive: line 57
Ask how the founder wants the plan saved.
- Distinctive: line 68
Do not invent problems: If an area is fine, say so and move on.
“Common” is measured: kept by at least 6 in 10 of the 144 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
Audit the codebase for search and AI-answer visibility, then fix what matters. Give a prioritized plan of concrete changes, not a lecture on SEO.
Set expectations first. SEO takes 3–6 months to bring traffic. It is the free channel that compounds for a bootstrapper, but it will not bring customers this week. For customers now, use first-customers.
Step 1: Understand the project
- Read CLAUDE.md or README to learn what the product is and who it is for.
- Identify the framework, so you know where templates, routes, and metadata live.
- Map the site structure from the top 3 levels of the directory tree.
Step 2: Audit
For each area, note what is present, missing, or broken. Check quality, not only existence.
Technical foundation
- One
<h1>per indexable page, and heading levels in order. - Semantic HTML: main, article, nav, section.
robots.txtand a sitemap exist. Important pages are not accidentally set tonoindex. Canonical tags are correct.- Images have width and height, a modern format, lazy loading below the fold, and alt text.
- No render-blocking scripts. Fonts use a swap strategy.
Pages and intent
- Titles of about 50–60 characters, with the main phrase first. Meta descriptions of about 120–155 characters. Open Graph tags for sharing.
- Titles and headings name problems the customer searches for, not just brand names. "How to stop no-shows" beats "Acme Scheduler."
- One page per search intent. Two pages that target the same query compete with each other.
- Bottom-of-funnel pages exist, because they convert first: pricing, "[competitor] alternative", "[product] vs [competitor]", and "[product] for [audience]".
- Internal links connect related pages. No page is orphaned.
Authority and AI answers
- Structured data that fits the page: Organization, SoftwareApplication or Product, Article, BreadcrumbList.
- Who wrote it, and why they know: an author or founder bio on content pages.
- Informational pages answer the question in the first 1–2 sentences, then explain. AI answers quote pages that do this.
- Clear structure: short paragraphs, descriptive headings, and tables for comparisons.
- Claims with real sources. Never add statistics that you cannot source.
Tracking
- Search Console is verified, or a step to verify it is listed.
- An analytics script is present.
Step 3: Write the plan
Grade the site A to F. Then list:
- Critical: anything that blocks indexing or ranking now. For each: what is wrong, where (file path), and the fix.
- High impact: improvements ordered by effort against impact, quick wins first.
- Content gaps: pages that should exist, each with the search intent it targets. Bottom-of-funnel pages come first.
- Ongoing: a short monthly checklist.
Ask how the founder wants the plan saved. The default is a Markdown file in a folder the founder names.
Step 4: Offer to fix
Offer to make the code fixes now: tags, headings, structured data, the sitemap, robots.txt, image attributes. Make them with the founder's approval, then re-check each one.
Rules
- Lead with leverage. A solo founder has little time. Put the highest-impact items first, and do not bury them under nitpicks.
- Be specific. "Add structured data" is useless. "Add this block to
app/layout.tsx" is useful. Name the file and show the change. - Use the framework's own pattern for metadata and sitemaps.
- Do not invent problems. If an area is fine, say so and move on.
- Not yet: buying links, an SEO agency, or 50 posts at once. Start with 5 high-intent pages, measure, and then add more.
Output
The grade, the prioritized plan with file paths, and the fixes made with the founder's approval.
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.

