Bencium Aeo
Generate machine-first pages, JSON-LD, and evidence-backed copy so ChatGPT, Claude, Gemini, and AI Overviews can cite your product accurately.
Overview
bencium-aeo is an agent skill most often used in Launch (also Grow content refresh) that runs an AEO content workflow: gap analysis, templated copy, JSON-LD, and paste-ready HTML for AI answer engines.
Install
npx skills add https://github.com/bencium/bencium-marketplace --skill bencium-aeoWhat is this skill?
- Content workflow (not a deployed tool): analyze AEO gaps, then generate optimized copy from research-backed templates
- Machine-first philosophy: ~90% AI-agent consumers, ~10% humans—18-token sentences, copyable JSON facts, evidence panels
- Outputs complete JSON-LD schema markup and copy-paste-ready HTML
- Input checklist: target URL, product details, top 15 customer questions, benchmarks and case-study evidence
- prd.md implementation checklist and story-structured.md Princeton-study strategic framework
- Input template asks for top 15 customer questions
- Machine-first framing: ~90% AI-agent consumers vs ~10% humans
- Delivers JSON-LD plus copy-paste-ready HTML
Adoption & trust: 1.1k installs on skills.sh; 273 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your site reads fine to humans but AI answer engines cannot extract verifiable facts, schema, or short quotable answers about your product.
Who is it for?
Founders shipping landing pages, docs, or product hubs who want AI-search-ready structure without hiring a separate SEO/AEO agency.
Skip if: Pure backend refactors, repos with zero public marketing surface, or teams that need automated crawling/indexing tools rather than generative content guidance.
When should I use this skill?
You need AEO-optimized content, schema, and HTML for a URL or page description with product details and customer questions.
What do I get? / Deliverables
You get structured AEO-aligned content, JSON-LD markup, and HTML blocks tuned for machine citation plus a checklist-driven implementation path from prd.md.
- AEO-optimized page copy
- JSON-LD schema blocks
- Copy-paste HTML sections
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Primary value appears at Launch when you optimize for AI answer engines and structured visibility—not during initial codebase scaffolding. GEO (generative engine optimization) is the canonical shelf; the workflow is explicitly for AI-powered answer engines, not classic ads-only distribution.
Where it fits
Shape a waitlist page with FAQ-style answers machines can quote before full build.
Rebuild product overview sections with 18-token sentences and JSON-LD for Gemini and ChatGPT Search.
Refresh case-study evidence panels and dated change logs so AI summaries stay current.
How it compares
Editorial AEO workflow skill—not an MCP crawler, rank tracker, or autogenerated site deployer.
Common Questions / FAQ
Who is bencium-aeo for?
Solo builders and indie teams using Claude Code to improve how AI answer engines quote and summarize their product pages.
When should I use bencium-aeo?
At Launch (GEO) when drafting or refreshing pages for AI Overviews; during Grow (content) when updating evidence panels and schema; after Validate when you have a clear offer and customer questions to target.
Is bencium-aeo safe to install?
It is a content workflow skill—review the Security Audits panel on this Prism page and treat generated claims as drafts you must fact-check before publishing.
SKILL.md
READMESKILL.md - Bencium Aeo
# AEO Content Generation Guide This skill provides guidance for generating Answer Engine Optimization (AEO) content - optimizing websites for AI-powered answer engines (ChatGPT, Claude, Gemini, AI Overviews). **This is NOT a tool or software project.** This is a content generation workflow for use with Claude Code. ## What This Skill Does When invoked, Claude should: 1. Analyze target website/content for AEO gaps 2. Generate optimized content using research-backed templates 3. Create complete JSON-LD schema markup 4. Provide copy-paste ready HTML ## Core Philosophy: Machine-First Content Optimize for **AI agents as primary consumers** (~90%), humans secondary (~10%): - Make facts **copyable** (JSON snippets, 18-token sentences) - Make claims **verifiable** (Evidence Panels with methods, dates, sources) - Make structure **scannable** (short answers, clear hierarchy, anchors) - Make updates **visible** (dated change logs, freshness signals) ## Key Files | File | Purpose | |------|---------| | `SKILL.md` | Skill definition and quick reference | | `prd.md` | **Main guide** - Complete templates, examples, implementation checklist | | `story-structured.md` | Princeton study insights and strategic framework | ## Content Generation Workflow ### Input Required - Target URL or page description - Product/service details (what, why, differentiators) - Top 15 customer questions - Evidence/data (benchmarks, research, case studies) ### Output Generated 1. **Product Overview** - 50 words + Product schema 2. **15 FAQs** - 30-50 word answers + FAQPage schema 3. **Evidence Panels** - Claim, methodology, source, date, limitations 4. **JSON-LD Schema** - FAQPage, HowTo, Product, Organization 5. **Implementation Checklist** - Validation steps ## Research-Backed Principles ### The 18-Token Rule LLMs extract self-contained sentences of ~18 tokens. Structure content with quotable, context-free statements. ### Single-Topic Focus One concept per page. `domain.com/specific-concept` beats comprehensive guides. ### Authority-Based Strategy - **Challengers:** Aggressive optimization (5-7 extraction points, heavy citations) - **Established sites:** Light touch (1-2 points, trust existing credibility) ### Freshness Requirement 95% of AI citations come from content updated in last 10 months. Static content dies. ## Anti-Patterns to Avoid - Keyword stuffing (actively harms GEO) - FAQ answers over 50 words - Missing dates and freshness signals - No schema markup - Pronoun ambiguity ("it" vs "the product") - Over-optimization on established sites ## Validation After generating content: 1. Validate schema: [Google Rich Results Test](https://search.google.com/test/rich-results) 2. Test with AI engines (ChatGPT, Claude, Gemini) 3. Track citations in scorecard over 4-8 weeks ## Full Documentation See `prd.md` for complete templates, HTML examples, and detailed implementation guidance. # AEO Content Generation Guide for Claude Code **Goal:** Generate machine-readable content that earns citations and links from ChatGPT, Claude, Gemini, and Google AI Overviews. **Not in scope:** Building automation tools or complex workflows. This is a content generation guide for manual/Claude-assisted implementation. --- ## Core AEO Principles (Research-Backed) These principles are derived from LLM citation behavior analysis and should inform all content optimization decisions: ### The 18-Token Extraction Rule - **Finding:** LLMs extract self-contained sentences of approximately 18 tokens (~15-20 words) - **Implication:** Key claims must be complete, quotable statements requiring zero surrounding context - **Example:** "Eight-API synthesis reduces property analysis errors by 67%." (9 tokens, self-contained) ### Single-Topic Focus Pages - **Finding:** Single-concept pages vastly outperform multi-topic content for AI citations - **Implication:** Create focused URLs like `domain.com/specific-concept` rather than comprehensive guides - **Structure:** One cle