Aeo Optimization logo

Aeo Optimization

Community
alinaqi
aeo-optimization

AI Engine Optimization - semantic triples, page templates, content clusters for AI citations

Overview

Publisheralinaqi
Repositorymaggy
Skill nameaeo-optimization
Stars
707
Forks
57
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by alinaqi on GitHub. Read the source before you install it.

Installation

Install the Aeo Optimization AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/alinaqi/maggy/tree/main/skills/aeo-optimization
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/alinaqi/maggy.git /tmp/maggy
mkdir -p .claude/skills
cp -r /tmp/maggy/skills/aeo-optimization .claude/skills/aeo-optimization
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Aeo Optimization in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Aeo Optimization on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Aeo Optimization is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

AI Engine Optimization (AEO) Skill

Purpose: Optimize content for AI engines (ChatGPT, Claude, Perplexity, Google AI Overviews) so your brand gets cited in AI-generated answers.

Source: Based on HubSpot's AEO Guide and industry best practices.


Why AEO Matters Now

┌────────────────────────────────────────────────────────────────┐
│  THE GREAT DECOUPLING                                          │
│  ────────────────────────────────────────────────────────────  │
│  Impressions ≠ Clicks anymore.                                 │
│  AI engines compile answers from multiple sources.             │
│  More buyer journey happens inside chat experiences.           │
│  58% of Google searches = zero clicks (AI overviews).          │
├────────────────────────────────────────────────────────────────┤
│  THE OPPORTUNITY                                               │
│  ────────────────────────────────────────────────────────────  │
│  Shape what AI engines say about your category and product.    │
│  Get cited as the authoritative source.                        │
│  Best answer > Best page ranking.                              │
└────────────────────────────────────────────────────────────────┘

Key Stats:

  • 70% of consumers use ChatGPT for searches
  • 47% of Google queries show AI overviews
  • Average ChatGPT prompt: 23 words (vs 4.2 for Google)
  • AEO market: $886M (2024) → $7.3B (2031)

How AI Engines Choose Answers

AI engines use three main signals to select content for answers:

1. Consensus

Facts that appear across multiple credible sources get trusted and reused.

How to build consensus:

  • Repeat key facts consistently across your own pages
  • Use same terminology as industry leaders
  • Link to and from authoritative external sources
  • Create internal content clusters that reinforce each other

2. Information Gain

Net-new insight beats generic advice. AI engines prefer content that adds value.

How to add information gain:

  • Original research and data
  • Concrete examples with specifics
  • Clear point of view (not fence-sitting)
  • Expert quotes with credentials
  • Case studies with metrics

3. Entities & Structure

Clear entities and tidy structure reduce ambiguity and boost quotability.

How to optimize structure:

  • Use semantic triples (Subject → Verb → Object)
  • Clear headings with entity names
  • Schema markup (Article, FAQ, Product)
  • Short, scannable paragraphs (2-4 sentences)

Semantic Triples (Critical for AEO)

What they are: Compact facts that AI engines (and humans) can't misread.

Pattern: [Subject] [verb] [object].

Examples

✅ GOOD (clear triples):
- HubSpot CRM syncs contact and company data.
- Lead Scoring assigns priority based on engagement.
- Workflows trigger email sequences from events.

❌ BAD (vague, no clear entity):
- The system helps with various tasks.
- It can do many things for users.
- This improves overall performance.

Triple Checklist

For every key claim, ask:

  • Is the subject a clear entity (product, feature, brand)?
  • Is the verb specific and active?
  • Is the object concrete and measurable?

Paragraph Pattern (Feature → How → Outcome)

Every substantive paragraph should follow this structure:

[Feature] helps [User/Role] with [Job].
It [mechanism/inputs] to [process].
Teams see [metric/result] in [timeframe/context].

Triples:
- [Subject] [verb] [object].
- [Subject] [verb] [object].

Example

markdown
Lead Scoring helps sales teams prioritize prospects. It combines
page views, email engagement, and firmographic data to assign a
numeric score, then auto-enrolls high scorers into follow-up
sequences. Reps focus on qualified accounts and book 40% more
meetings.

- Lead Scoring assigns scores from engagement data.
- High scorers trigger automated follow-up sequences.

Page Templates

Template 1: Category Explainer

Goal: Define the category, tie it to your product, earn citations.

markdown
# What is [Category]? — [1-2 line value promise]

## What is [Category]? (~80 words)
[Plain definition in everyday language. Name adjacent entities.]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

## Why it matters now (~60 words)
[One paragraph. Mention shift to answers over links; tie to buyer outcomes.]

## How to apply it (3-5 bullets)
- [Action 1]
- [Action 2]
- [Action 3]

## FAQ
**Q: [Question]?**
A: [~1 sentence answer]

**Q: [Question]?**
A: [~1 sentence answer]

**Q: [Question]?**
A: [~1 sentence answer]

---
**Links:** [Category hub] | [Product/Feature] | [Credible source 1] | [Credible source 2]
**CTA:** [Demo / Template / Signup]
**Schema:** Article + FAQ. Author + last updated.

Template 2: Product & Feature Page

Goal: Clarify capability, fit, and next step; reinforce category linkage.

markdown
# [Product/Feature] — [Outcome in 3-5 words]

**[Product/Feature] enables [Outcome] for [User/Role].**

## [Feature Area 1]
[2-4 sentences using Feature → How → Outcome]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

## [Feature Area 2]
[2-4 sentences using Feature → How → Outcome]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

## [Feature Area 3]
[2-4 sentences using Feature → How → Outcome]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

## FAQ
**Q: [Question]?**
A: [~1 sentence]

**Q: [Question]?**
A: [~1 sentence]

**Q: [Question]?**
A: [~1 sentence]

---
**Links:** Back to [Category Explainer] | Forward to [Demo/Trial]
**Proof:** [Benchmark/Analyst/Customer proof]
**Notes:** Requirements/limits (pricing tier, integrations)
**Schema:** Article + FAQ. Author + last updated.

Template 3: Comparison / Alternatives Page

Goal: Help readers decide with clear criteria; earn fair citations.

markdown
# [Product] vs. [Alternative] — Which fits [Use case]?

## Comparison Table

| Criterion | [Product] | [Alt A] | [Alt B] | Source |
|-----------|-----------|---------|---------|--------|
| [Feature/Limit] | [value] | [value] | [value] | [link] |
| [Requirement] | [value] | [value] | [value] | [link] |
| [Best for] | [value] | [value] | [value] | [link] |

*Source-back all claims in the table or footnotes.*

## Fit Statements

1. **[Product]** suits [Team/Use case] when [Condition].
2. **[Alt A]** fits [Team/Use case] when [Condition].
3. **[Alt B]** works for [Team/Use case] when [Condition].

---
**Links:** [Category Explainer] | [Feature pages]
**CTA:** [Try / Demo / Talk to Sales]
**Schema:** Article. Author + last updated.

Template 4: Use Case / Industry Page

Goal: Connect product to outcomes in a context readers recognize.

markdown
# [Industry/Use Case] — [Outcome KPI]

**Teams reduce [Metric] by [Y%] in [Timeframe].**

## Mini Case Study
[Company/Role] used [Product/Feature] to [Action], resulting in
[Metric improvement] within [Timeframe].

## How It Works

### [Feature 1]
[Feature → How → Outcome paragraph]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

### [Feature 2]
[Feature → How → Outcome paragraph]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

## Who Uses This
**Roles:** [Role 1], [Role 2], [Role 3]
**Workflows:** [Workflow 1], [Workflow 2]
**Integrations:** [Integration 1], [Integration 2]

---
**Links:** [Product/Feature pages] | [Supporting blog]
**CTA:** [Industry template / Demo variant]
**Schema:** Article. Author + last updated.

Template 5: Supporting Blog Post

Goal: Add information gain and support your content cluster.

markdown
# [Topic] — [Specific promise]

## Opening (~60-80 words)
[State the problem. Align terminology with Category Explainer. Preview outcome.]

## [Section 1 Heading] (~120 words max)
[Feature → How → Outcome]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

**Internal link:** [Related page]
**External citation:** [Credible source]

## [Section 2 Heading] (~120 words max)
[Feature → How → Outcome]

Triples:
1. [Subject] [verb] [object].
2. [Subject] [verb] [object].

**Internal link:** [Related page]
**External citation:** [Credible source]

## Key Takeaway
[1-2 lines summarizing the main point]

**CTA:** [Single primary action]

---
**Schema:** Article. Author + last updated.

Site-Wide Trust Signals

Required on Every Page

ElementImplementation
Schema markupArticle + FAQ (if FAQ exists)
Author attributionName, bio, credentials, photo
Last updated dateVisible, machine-readable
Internal links3-5 per page (upstream/downstream)
External citations1-2 credible sources per section
Single CTADemo, template, or signup (repeated once near end)

Schema Implementation

html
<!-- Article Schema -->
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Article",
  "headline": "[Page Title]",
  "author": {
    "@type": "Person",
    "name": "[Author Name]",
    "url": "[Author Bio URL]"
  },
  "datePublished": "[ISO Date]",
  "dateModified": "[ISO Date]",
  "publisher": {
    "@type": "Organization",
    "name": "[Company]",
    "logo": "[Logo URL]"
  }
}
</script>

<!-- FAQ Schema (if FAQ section exists) -->
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "FAQPage",
  "mainEntity": [
    {
      "@type": "Question",
      "name": "[Question 1]",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "[Answer 1]"
      }
    },
    {
      "@type": "Question",
      "name": "[Question 2]",
      "acceptedAnswer": {
        "@type": "Answer",
        "text": "[Answer 2]"
      }
    }
  ]
}
</script>

Content Cluster Architecture

                    ┌─────────────────────┐
                    │  Category Explainer │
                    │   "What is AEO?"    │
                    └──────────┬──────────┘
                               │
        ┌──────────────────────┼──────────────────────┐
        │                      │                      │
        ▼                      ▼                      ▼
┌───────────────┐    ┌───────────────┐    ┌───────────────┐
│ Product Page  │    │ Product Page  │    │ Product Page  │
│  "Feature A"  │    │  "Feature B"  │    │  "Feature C"  │
└───────┬───────┘    └───────┬───────┘    └───────┬───────┘
        │                    │                    │
        ▼                    ▼                    ▼
┌───────────────┐    ┌───────────────┐    ┌───────────────┐
│  Blog Post    │    │  Use Case     │    │  Comparison   │
│  (supports)   │    │  (industry)   │    │  (vs. alt)    │
└───────────────┘    └───────────────┘    └───────────────┘

Linking Rules:

  • Category Explainer links DOWN to all product pages
  • Product pages link UP to Category Explainer
  • Product pages link ACROSS to related features
  • Blog posts link UP to Product pages
  • Comparison pages link to Category Explainer + relevant Product pages

AEO Writing Checklist

Per-Paragraph Checklist

  • Follows Feature → How → Outcome pattern
  • Contains 2-4 sentences (scannable)
  • Includes 1-2 semantic triples
  • Names specific entities (not vague "it" or "this")
  • Uses active voice verbs

Per-Section Checklist

  • Has 1 internal link (upstream or downstream)
  • Has 1 external citation (credible source)
  • Section heading names an entity
  • ~120 words max

Per-Page Checklist

  • H1 contains primary entity + value promise
  • Opening claim is a semantic triple
  • 3-5 internal links total
  • 1-2 external citations total
  • Mini-FAQ with 3 questions (if applicable)
  • Single primary CTA
  • Schema markup (Article + FAQ)
  • Author name + bio link
  • Last updated date visible

Site-Wide Checklist

  • Category Explainer exists for each key category
  • Product pages link back to Category Explainer
  • Content cluster architecture documented
  • Author bio pages exist with credentials
  • Consistent terminology across all pages

Measuring AEO Success

Key Metrics

MetricHow to Track
AI citationsManual checks in ChatGPT, Claude, Perplexity
Brand mentions in AISearch "[brand] + [category]" in AI engines
Share of answerHow often you're cited vs competitors
LLM trafficGA4 referral from chatgpt.com, claude.ai, perplexity.ai
Impressions-to-clicks gapGSC impressions vs actual clicks

Tools

  • HubSpot AEO Grader - Grade your brand's AI visibility
  • Google Analytics 4 - Track LLM referral traffic
  • Google Search Console - Monitor impressions vs clicks gap
  • Manual AI queries - Regularly test your brand in AI engines

Common AEO Mistakes

MistakeFix
Vague language ("it helps with things")Use specific entities and triples
No clear structureUse Feature → How → Outcome
Missing schemaAdd Article + FAQ schema
No author attributionAdd author name, bio, credentials
Generic contentAdd original data, examples, POV
Orphan pagesLink into content cluster
Fence-sitting ("it depends")Take a clear position
No external citationsAdd 1-2 credible sources per section

AEO vs Traditional SEO

AspectTraditional SEOAEO
GoalRank on page 1Get cited in AI answers
Success metricClick-through rateShare of answer
Content focusKeywordsEntities + facts
StructureHeaders for scanningTriples for extraction
LinksBacklinks for authorityCitations for consensus
UpdatesPeriodic refreshContinuous accuracy

Quick Reference

Semantic Triple Pattern

[Entity/Product] [active verb] [concrete object/result].

Paragraph Pattern

[Feature] helps [User] with [Job].
It [mechanism] to [process].
Teams see [result] in [timeframe].

Page Minimums

  • 3-5 internal links
  • 1-2 external citations per section
  • 3 FAQ questions with schema
  • Author + last updated
  • Single CTA

Content Hierarchy

  1. Category Explainer (top)
  2. Product/Feature pages (middle)
  3. Use case / Comparison / Blog (supporting)

Frequently asked questions

What does the Aeo Optimization AI skill do?

AI Engine Optimization - semantic triples, page templates, content clusters for AI citations

Why use Aeo Optimization on TypingMind?

Because you install it once and use it with any model. Aeo Optimization is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Aeo Optimization in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alinaqi/maggy/tree/main/skills/aeo-optimization. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Aeo Optimization?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Aeo Optimization?

As many as you like. As long as a model supports skills, you can use Aeo Optimization with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Aeo Optimization AI skill free?

Yes. It is published on GitHub by alinaqi under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇