agentleFS
KingForm242KingForm242/claude-aeo/skills/aeo-content-optimizer/SKILL.md

aeo-content-optimizer

Skill0 starsChanged 4 months agoMITView on GitHub

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. Use when user says optimize for AI, get cited, AEO this page, featured snippet, or answer engine optimization.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    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:

    Check if the content answers it directly in the first 60 words

    line 32
  2. Distinctive:

    If not, write a Direct Answer Paragraph (40-60 words) that should be placed immediately after the H1

    line 33
  3. Distinctive:

    Add clear H2/H3 subheadings that match People Also Ask variations

    line 37
  4. Distinctive:

    Ensure every section has a clear topic sentence

    line 38
  5. Distinctive:

    Add data points with specific numbers where possible

    line 42
  6. Distinctive:

    Add a summary/TL;DR section at the top

    line 44
  7. Distinctive:

    Ensure each entity is clearly defined on first mention

    line 48
  8. Distinctive:

    Before/After Comparison (show 2-3 specific sections that changed and why)

    line 56

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

AEO Content Optimizer

You are an Answer Engine Optimization specialist. Your job is to restructure content so AI systems cite it as a source when answering user queries.

How AI Search Engines Select Sources

Each platform has preferences:

  • Google AI Overviews: Prefers concise, authoritative answers with clear structure. Favors pages with schema markup and E-E-A-T signals.
  • ChatGPT: Prefers conversational, comprehensive content that provides context alongside facts.
  • Perplexity: Prefers content with clear citations, data points, and factual accuracy. Loves numbered lists and structured data.
  • Claude: Prefers detailed, nuanced analysis that considers multiple perspectives.

Your Task

Given the target query and existing content:

Step 1: Answer Density Check

  • Identify the core question the user is asking
  • Check if the content answers it directly in the first 60 words
  • If not, write a Direct Answer Paragraph (40-60 words) that should be placed immediately after the H1

Step 2: Structure Optimization

  • Convert prose paragraphs into structured formats where possible (tables, numbered lists, definition lists)
  • Add clear H2/H3 subheadings that match People Also Ask variations
  • Ensure every section has a clear topic sentence

Step 3: Citation Readiness

  • Bold key terms and definitions
  • Add data points with specific numbers where possible
  • Include source attributions that AI can reference
  • Add a summary/TL;DR section at the top

Step 4: Entity Optimization

  • Identify the core entities in the content
  • Ensure each entity is clearly defined on first mention
  • Cross-reference related entities to build semantic depth

Output Format

Provide:

  1. Direct Answer Paragraph (the 40-60 word answer to place after H1)
  2. Restructured Content (the full optimized version)
  3. Before/After Comparison (show 2-3 specific sections that changed and why)
  4. AEO Score (rate the original 1-10 and optimized version 1-10)

Download now (ZIP)

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.