agentleFS
Sign inStart free
harshsinghmpharshsinghmp/muse-skills/skills/agency-delivery/seo/SKILL.md

seo

Skill1 starsChanged 18 days agoMITView on GitHub

Full SEO and AEO department: technical SEO, on-page optimization, content strategy, local SEO, link building, answer-engine optimization (AEO/GEO for AI search), programmatic SEO landing page scaling, and full audits — routed through eight modes. Use when asked to improve organic search visibility, generate programmatic comparison or directory pages, fix crawlability or indexing issues, optimize pages or content for search, build or disavow links, optimize for local/maps visibility, or make a site citable by AI answer engines (ChatGPT, Perplexity, AI Overviews). Not for paid ads (paidads) or analytics setup (analytics).

We split this skill into the rules it gives an agent

4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 139 edited versions we read keep these.

  • 4

    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
  1. Distinctive:

    Every invocation resolves to exactly one mode.

    line 38
  2. Distinctive:

    Only the resolved mode's reference is loaded — the rest stay on disk, saving tokens on every run.

    line 51
  3. Distinctive:

    Every mode starts from measured state, not assumed state:

    line 78
  4. Distinctive:

    No baseline → gather it first.

    line 87

“Common” is measured: kept by at least 6 in 10 of the 139 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

🔎 seo — Search & Answer Engine Optimization Department

One head skill for the search department. Organic visibility is earned through a crawlable, fast, indexable site (technical), pages structured for relevance (on-page), content worth citing (content + AEO), and authority (links + local). Every mode outputs prioritized, evidence-cited work.

Modes

Every invocation resolves to exactly one mode. Match the request, then load only the matched reference:

ModeTrigger phrasesBehaviorReference
technical"technical seo", "crawlability", "indexing issues", "site architecture", "trailing slash", "breadcrumbs"Crawl, render, index, canonical, sitemap, robots, hreflang, trailing-slash normalizer, breadcrumb schemareferences/technical.md
onpage"on-page seo", "optimize this page", "title tags", "internal linking"Title/meta/H-structure, internal links, schema, snippet optimizationreferences/onpage.md
content"seo content strategy", "keyword research", "topic clusters", "content brief"Keyword/topic universe → clusters → briefs (content writes them)references/content.md
local"local seo", "google business profile", "maps ranking", "nap consistency"GBP, local citations, NAP, local landing pagesreferences/local.md
links"link building", "backlinks", "disavow", "digital pr"Link profile analysis, acquisition (earned), toxic-link handlingreferences/links.md
aeo"aeo", "geo", "ai overviews", "chatgpt visibility", "perplexity citations", "llm seo"Answer-engine citability: entities, extractable facts, schema, prompt-set testingreferences/aeo.md
programmatic"programmatic seo", "pseo", "dataset landing pages", "scale comparison pages", "directory seo", "sitemap splitting"Large-scale dataset-driven landing pages, anti-thin content invariants, dynamic schema, and hub-and-spoke clustersreferences/programmatic.md
audit"full seo audit", "site audit", "why did traffic drop", "search health check"Full search-health audit: all modes synthesizedreferences/audit.md

Only the resolved mode's reference is loaded — the rest stay on disk, saving tokens on every run.

When to Use

  • Improving organic rankings or visibility for a site or page.
  • Diagnosing crawlability, indexing, or canonicalization issues.
  • Optimizing existing pages (titles, structure, internal linking, schema).
  • Planning content that should rank or be cited by AI engines.
  • Local/maps visibility, GBP, and NAP consistency work.
  • Building, evaluating, or disavowing links.
  • Running a full search-health audit (SEO + AEO together).

Anti-Triggers

  • Paid search or shopping → paidads (google mode).
  • GA4/GTM/dashboards setup → analytics.
  • Site speed as a build task → webdev (performance mode); seo technical mode verifies the result.
  • Writing the actual long-form article → content (blog mode); seo content mode defines the brief.

Quick Reference

Baseline-first doctrine

Every mode starts from measured state, not assumed state:

InputSource
Index coverage / crawl stateSearch Console (or equivalent)
Query & page performanceSearch Console + GA4
Current SERP shapelive SERP check per target query
AI engine visibilitymanual/automated prompt set across ChatGPT, Perplexity, AI Overviews

No baseline → gather it first. Proposing changes without one is guessing.

Priority order (multi-problem sites)

  1. Indexability (can it be crawled and indexed at all?) — nothing else matters until this is true.
  2. Rendering & speed (Core Web Vitals as threshold, not trophy).
  3. Relevance (on-page, internal links, titles).
  4. Authority (links, local).
  5. AEO/answer-engine citability.

Entity-first AEO principle

AI engines cite what they can parse as entities and facts: clear entity definitions (about-page, schema, consistent naming), extractable claims with sources, and quotable stat-blocks beat keyword density every time.

Suite contracts

  • UTM/organic segmentation: follow the analytics measurement contract.
  • Content briefs for ranking pages: hand to content (blog mode) for drafting; seo defines the brief.

OpenGraph & Social Preview Tooling

  • Audit OpenGraph & Social Cards: bun skills/agency-delivery/seo/scripts/og-audit.ts --audit [dir|file] [--json]
  • Generate OpenGraph Tags: bun skills/agency-delivery/seo/scripts/og-audit.ts --generate-meta [--title "..." --desc "..." --url "..." --image "..."]

AEO & AI Crawler Citability Tooling

  • Audit Content Citability: bun skills/agency-delivery/seo/scripts/aeo-audit.ts --audit <file|dir> [--extract-quotables] [--json]
  • Audit Robots.txt for AI Search Retrieval: bun skills/agency-delivery/seo/scripts/aeo-audit.ts --robots-check <robots.txt> [--json]

Procedure

  1. Intake. pull the Search Console / analytics baseline before proposing changes — no baseline, no diagnosis.
  2. Resolve the mode. Match the request against the mode table; exactly one mode. Ambiguous → ask one question, then proceed.
  3. Execute the mode playbook. Load references/<mode>.md and follow its Intake → Deliverable → Procedure → Quality gate in order.
  4. Gate and deliver. Pass this file's Verification checklist plus the mode's quality gate, then deliver the artifact where the client expects it.

Pitfalls

  • Proposing changes without a Search Console/analytics baseline — guessing.
  • Fixing relevance when the page isn't even indexed — indexability first.
  • Chasing Core Web Vitals as a trophy when it's only a tie-breaker threshold.
  • Keyword-stuffing titles/H1s — write for the SERP snippet and the user, not the crawler.
  • Buying links without vetting — one PBN penalty outweighs a year of white-hat work.
  • Treating AEO as magic prompts — it's entity clarity + extractable facts + structured data.
  • NAP inconsistency across local citations — silently kills maps rankings.
  • Disavowing without a manual action or clear toxicity evidence — usually unnecessary and risky.

Verification

  • Baseline captured before recommendations; every finding cites measured evidence.
  • Priority order respected (indexability before relevance before authority).
  • Every recommendation is prioritized with impact × effort.
  • Structured-data changes validate against the schema.org type being used.
  • Local work includes NAP consistency check across the citation set.
  • AEO claims are testable (prompt-set visibility check before/after).

Download now (ZIP)

  • Other versions148 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 148

    1. AgriciDaniel/claude-seo★ 20ksame name
    2. midudev/preguntas-entrevista-react★ 7.8ksame name
    3. legions-developer/evilcharts★ 3.2ksame name
    4. gridaco/grida★ 2.7ksame name
    5. midudev/la-velada-web-oficial★ 1.9ksame name
    6. midudev/tailwind-animations★ 1.5ksame name
    7. Bhanunamikaze/Agentic-SEO-Skill★ 993same name
    8. legions-developer/invoicely★ 923same name
    9. Nexus-JPF/note-companion★ 874same name
    10. AgriciDaniel/codex-seo★ 795same name

    138 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.

  • Used alongsideProjects with it also use seo-maps, seo-sitemap 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.
    • webdevarifSkill

      seo-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, competitor radius mapping, and LocalBusiness schema generation. Three tiers: free (Overpass + Geoapify), DataForSEO, and DataForSEO + Google. Use when user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", or "SoLV".

      Also in 16 projects that use this

    • megastepSkill

      seo-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 25 projects that use this

    • megastepSkill

      seo-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 23 projects that use this

    • webdevarifSkill

      seo-ecommerce

      E-commerce SEO analysis: Google Shopping visibility, Amazon marketplace intelligence, product schema validation, competitor pricing analysis, and marketplace keyword gaps. Combines on-page product SEO with marketplace data from DataForSEO Merchant API. Use when user says "ecommerce SEO", "product SEO", "Google Shopping", "marketplace SEO", "product schema", "Amazon SEO", "product listings", "shopping ads", or "merchant SEO".

      Also in 14 projects that use this

    • ronmkrSkill

      vite-patterns

      Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.

      Also in 7 projects that use this

    • ronmkrSkill

      dart-flutter-patterns

      Production-ready Dart and Flutter patterns covering null safety, immutable state, async composition, widget architecture, popular state management frameworks (BLoC, Riverpod, Provider), GoRouter navigation, Dio networking, Freezed code generation, and clean architecture.

      Also in 5 projects that use this

    • +2 more from megastep
    • +3 more from webdevarif
  • In this repository49 other files it gives its agents.

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free