Aeo
Answer Engine Optimization plugin for Claude. 12 skills (1 orchestrator + 11 specialists) that get brands cited by ChatGPT, Perplexity, Claude, and Google AI Overviews: client-ready AI visibility audits with dollar figures, citation testing, AEO content restructuring, JSON-LD schema, E-E-A-T scoring & More.
npx -y skills add KingForm242/claude-aeo --skill aeoAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 27 days oldThe repository was created 27 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 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.
What its author says it does
Copied from the file, not written here
Answer Engine Optimization for any website: get your brand cited by ChatGPT, Perplexity, Claude, and Google AI Overviews. Client-ready AI visibility audits with dollar figures, citation testing, AEO content optimization, JSON-LD schema, E-E-A-T scoring, keyword AI-risk classification, competitor gap analysis, internal linking, content briefs, GBP posts. Triggers on: AEO, AI visibility, cited by ChatGPT, AI Overviews, answer engine, LLM SEO, GEO, citation, AI search, schema, E-E-A-T, audit.
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
4.6 KB, 944 tokens by cl100k_base, as published. Nobody here has run it
AEO: Answer Engine Optimization Skill
Invocation: /aeo $1 $2 where $1 is the command and $2 is the input, or just describe the task and the right sub-skill loads automatically.
The job of this plugin is different from a rank tracker or a technical crawler: it makes brands the answer AI engines give at the moment of decision, and it produces consultant-grade deliverables, not just findings.
Quick Reference
| Command | What it does |
|---|---|
/aeo audit paste the 4 input blocks: CLIENT / TRAFFIC DATA / QUERY TEST / TECHNICAL OBSERVATIONS | Generate a client-ready AI Visibility Audit report from collected data: traffic value deltas, 5-query citation tests across ChatGPT/Perplexity/AI Overviews, and technical observations |
/aeo site url or pasted HTML/crawl data | Full technical and on-page SEO audit: canonicals, robots, redirects, title/meta/heading hierarchy, content quality, Core Web Vitals signals, mobile |
/aeo optimize target query + pasted content | Restructure existing content to get cited in AI answers from ChatGPT, Perplexity, Claude, and Google AI Overviews: direct answer paragraph, structure conversion, citation readiness, entity optimization |
/aeo schema url or pasted page content | Generate valid JSON-LD structured data for any page type: Article, Product, FAQ, HowTo, LocalBusiness, Organization, BreadcrumbList, VideoObject, nested via @graph |
/aeo eeat pasted content | Score content 1-10 against Google E-E-A-T rater guidelines (Experience, Expertise, Authoritativeness, Trustworthiness) with a PUBLISH/REVISE/REWRITE verdict, top weaknesses and strengths |
/aeo intent keyword list, one per line | Classify keywords by search intent, buyer journey stage, and AI answer risk (will an LLM answer this without a click) |
/aeo gap your content + competitor content | Entity-level comparison of your content vs a competitor page ranking above you: missing entities, data points, FAQ coverage, depth and structure deltas, with impact-ranked gap report |
/aeo gbp business name, location, service/topic | Generate three Google Business Profile post variations (Update, Offer, Event/Seasonal) under 1,500 characters with geo-modifiers and CTA buttons |
/aeo links list of page titles, URLs, target keywords | Map hub-and-spoke internal linking architecture: pillar identification, cluster assignment, cross-cluster limits, exact anchor text, orphan page rescue, top 5 priority links |
/aeo brief target keyword + audience | Writer-ready SEO content brief covering intent, H1-H3 outline, keyword placement rules, PAA questions with 40-60 word AEO answers, competitor benchmark, AEO formatting notes, and meta tags |
/aeo check target query + pasted content | Score whether an LLM would cite this page for a target query: answer positioning, structural clarity, factual density, entity coverage, freshness |
Orchestration Logic
Route by intent, not keyword match:
- Client deliverable or "audit report" language -> aeo-visibility-audit (collect the 4 input blocks first; never invent data)
- "Why don't we show up in ChatGPT/AI Overviews" -> aeo-visibility-check on their money page, then aeo-content-optimizer
- Site-wide or technical language -> aeo-site-audit, then aeo-schema for the highest-value page found
- Keyword lists -> aeo-keyword-intent
- "Competitor outranks us" -> aeo-competitor-gap
Chains
New client onboarding: site -> check -> gap -> intent -> brief (x5) Content refresh: eeat -> optimize -> schema -> check Client audit deliverable: collect data -> audit -> eeat (QA pass on the report itself) -> send within 24 hours Weekly local: gbp -> links -> schema
Rules that hold across every sub-skill
- Never invent data. Missing input = "insufficient data", stated plainly.
- Every recommendation must be specific enough to hand to any implementer.
- Revenue framing beats ranking framing: state dollar impact when traffic value data exists.
- No em dashes, no hype words, no filler in any client-facing output.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most context ai engineering skills give in 944 tokens
Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07
- Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
- Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
- Provide full task text to the subagentin 30 of 1193, across 9 files
- Review spec compliance before code qualityin 27 of 1193, across 10 files
- Make the hook script executablein 26 of 1193, across 8 files
- Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
- Read files before editing themin 22 of 1193, across 11 files
- Answer subagent questions before proceedingin 22 of 1193, across 7 files
- Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
- Merge hook into existing settingsin 21 of 1193, across 3 files
- Ask if installation is global or projectin 20 of 1193, across 2 files
- Copy the hook script to target locationin 20 of 1193, across 2 files
Said here and by no other author read
- state insufficient data plainly when input is missing
- make every recommendation specific enough for an implementer
- state revenue impact when traffic value data exists
- collect the four input blocks before generating an audit
- deliver client audits within 24 hours
- keep google business profile posts under 1500 characters
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.