
aeo-optimization
AI Engine Optimization - semantic triples, page templates, content clusters for AI citations
- Installs
- 437
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/alinaqi/maggy --skill aeo-optimization- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads aeo-optimization automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
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
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.
# 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.
# [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.
# [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.
# [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.
# [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
| Element | Implementation |
|---|---|
| Schema markup | Article + FAQ (if FAQ exists) |
| Author attribution | Name, bio, credentials, photo |
| Last updated date | Visible, machine-readable |
| Internal links | 3-5 per page (upstream/downstream) |
| External citations | 1-2 credible sources per section |
| Single CTA | Demo, template, or signup (repeated once near end) |
Schema Implementation
<!-- 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
| Metric | How to Track |
|---|---|
| AI citations | Manual checks in ChatGPT, Claude, Perplexity |
| Brand mentions in AI | Search "[brand] + [category]" in AI engines |
| Share of answer | How often you're cited vs competitors |
| LLM traffic | GA4 referral from chatgpt.com, claude.ai, perplexity.ai |
| Impressions-to-clicks gap | GSC 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
| Mistake | Fix |
|---|---|
| Vague language ("it helps with things") | Use specific entities and triples |
| No clear structure | Use Feature → How → Outcome |
| Missing schema | Add Article + FAQ schema |
| No author attribution | Add author name, bio, credentials |
| Generic content | Add original data, examples, POV |
| Orphan pages | Link into content cluster |
| Fence-sitting ("it depends") | Take a clear position |
| No external citations | Add 1-2 credible sources per section |
AEO vs Traditional SEO
| Aspect | Traditional SEO | AEO |
|---|---|---|
| Goal | Rank on page 1 | Get cited in AI answers |
| Success metric | Click-through rate | Share of answer |
| Content focus | Keywords | Entities + facts |
| Structure | Headers for scanning | Triples for extraction |
| Links | Backlinks for authority | Citations for consensus |
| Updates | Periodic refresh | Continuous 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
- Category Explainer (top)
- Product/Feature pages (middle)
- Use case / Comparison / Blog (supporting)
FAQ
What does the aeo-optimization skill do?
AI Engine Optimization - semantic triples, page templates, content clusters for AI citations
How do I install aeo-optimization?
Run npx skills add https://github.com/alinaqi/maggy --skill aeo-optimization in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/aeo-optimization/ (personal) or .claude/skills/aeo-optimization/ (project).
Which AI agents can use aeo-optimization?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is aeo-optimization safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains aeo-optimization?
It is published by alinaqi in alinaqi/maggy. It has 437 recorded installs.
More from alinaqi/maggy
pwa-development
alinaqi/maggy
Progressive Web Apps - service workers, caching strategies, offline, Workbox
playwright-testing
alinaqi/maggy
E2E testing with Playwright - Page Objects, cross-browser, CI/CD
android-kotlin
alinaqi/maggy
Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing
code-review
alinaqi/maggy
Mandatory code reviews via /code-review before commits and deploys
ui-mobile
alinaqi/maggy
Mobile UI patterns - React Native, iOS/Android, touch targets
posthog-analytics
alinaqi/maggy
PostHog analytics, event tracking, feature flags, dashboards
Popular other skills
hyperframes-cli
heygen-com/hyperframes
The HyperFrames CLI by job - scaffold, check, look at frames, edit the timeline, preview, render locally or in the cloud, publish, project history - plus reading its JSON and recovering from build or render failures.
triage
mattpocock/skills
Move issues and external PRs through a state machine of triage roles, categorise, verify, grill if needed, and write agent-ready briefs.
ask-matt
mattpocock/skills
Ask which skill or flow fits your situation. A router over the skills in this repo.
to-questionnaire
mattpocock/skills
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
loop-me
mattpocock/skills
Grill me about specs for the workflows I want to build, within this workspace.