Bencium Aeo

bencium/bencium-claude-code-design-skill

This generates content optimized for AI citations in ChatGPT, Claude, and Gemini rather than traditional search rankings. You'd use it when creating FAQ schemas, analyzing pages for LLM extraction, or building evidence panels that AI models actually quote. The core insight is the 18-token extraction rule: LLMs pull self-contained sentences of roughly 15-20 words, so your claims need to stand alone without context. It pushes single-topic pages over comprehensive guides, requires citations on everything, and treats authority level as strategy (aggressive optimization for new sites, light touch for established ones). Includes templates for FAQPage schema, evidence panels, and a testing protocol across major AI models.

skills.sh installs: 297
GitHub stars: 267
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add bencium/bencium-claude-code-design-skill --skill bencium-aeo --agent claude-code

Installs into .claude/skills of the current project.

Files

AEO Content Optimization Skill

Answer Engine Optimization - Optimize content for AI citations, not traditional search rankings.

When to Use This Skill

Use this skill when:

User asks to optimize content for AI search/citations
User mentions ChatGPT, Claude, Gemini visibility
User wants FAQ schema, JSON-LD, or structured data for AI
User asks about GEO (Generative Engine Optimization)
User wants to analyze content for AI extraction readiness
User mentions "AI Overviews" or "answer engines"

NOT for traditional SEO - This is specifically for AI/LLM citation optimization.

Core Reference

Full templates and guidelines: Read prd.md in this directory for complete implementation details.

Quick Reference: Key Principles

The 18-Token Extraction Rule

LLMs extract self-contained sentences of ~18 tokens (~15-20 words). Key claims must be complete, quotable statements requiring zero surrounding context.

Good: "Eight-API synthesis reduces property analysis errors by 67%." (9 tokens) Bad: "Our system is incredibly fast and delivers amazing results." (vague)

SKILL.md on GitHub