An open Agent Skill (SKILL.md format) for creating and rebuilding web content so generative engines (ChatGPT, Gemini, Perplexity, Google AI Overviews) extract, cite, and mention it.
What it does The skill turns a general agent into a GEO content specialist. It walks the agent through the retrieval mechanic (chunk, embed, retrieve, ground, cite) and applies it as a repeatable workflow: gate crawler access, structure text into extractable blocks, force citations with concrete data, cover query fan-out, keep content fresh, add verifiable authorship, apply correct semantic markup and JSON-LD, strip machine-tell language, publish with an input register, and measure Share of Mentions against a competitor benchmark. It covers two modes: creating new content, and rebuilding existing pages (baseline first). Structure geo-content-engineering/ ├── SKILL.md # workflow core + reference map ├── references/ # deep concept files, loaded on demand ├── assets/ # paste-ready templates and JSON-LD └── LICENSE.md # CC BY 4.0
Skill from dembrandt: authentic-product-representation
Skill from nexu-io: html-ppt-retro-quarterly-review
Skill from nexu-io: 8-bit-orbit-video-template