agentsclimarketplace

Seo geo

Skill fusengine/agents/plugins/seo/skills/seo-geo

Redefining development through cognitive automation and collaborative agent systems.

Install
npx -y skills add fusengine/agents --skill seo-geo

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 22 stars22 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when optimizing for AI search engines (GEO) — AI Overviews, ChatGPT, Perplexity, Claude, Gemini, Copilot readiness.

SKILL.md

3.0 KB, as published. Nobody here has run it

<objective> Covers Generative Engine Optimization (GEO) 2026 for the six target AI engines (Google AI Overviews, ChatGPT with web search, Perplexity, Claude with web search, Gemini, Bing Copilot). Documents the `scripts/geo-score.ts` LLM-readiness scoring (0-100 across 10 weighted signals), quantified impact data (statistics/authoritative citations/expert quotes boost AI visibility up to +40%; keyword stuffing costs -10%), the recommended content structure for LLM extraction, and llms.txt placement (ignored by Google's crawlers, useful for other LLMs). Distinct from seo-featured-snippets (position-0 HTML recipes) and seo-entity (the schema/salience signals that feed AI citations). </objective>

GEO — Generative Engine Optimization 2026

Target Engines

  • Google AI Overviews (formerly SGE)
  • ChatGPT with web search
  • Perplexity
  • Claude with web search
  • Gemini
  • Bing Copilot

LLM-Readiness Score (0-100)

scripts/geo-score.ts checks:

SignalPoints
Quick answer in first 100 words15
Direct H2 questions ("What is X?")10
Tables/lists for comparable data10
Citations with dates + sources15
Statistics with attribution10
Author bio with credentials10
Schema.org markup10
Updated date < 12 months10
llms.txt present5
No JS-only content (SSR)5

Quantified Impact (Princeton / 2026 studies)

GEO techniques boost AI visibility by up to +40%. Ranked by impact:

TechniqueVisibility
Adding statistics+40%
Citing authoritative sources+40%
Quoting experts+28%
Improving text fluency+15–30%
Keyword stuffing-10% (worse than baseline)

AI Overviews cite ~13 sources on average per answer (2026); 59.6% of citations come from URLs outside the top-20 organic results.

Content Structure for LLMs

# <Topic>

**Quick answer** (40-60 words, factual, no fluff)

## What is <topic>?
Definition paragraph...

## Why does it matter?
Stats with sources...

## How to <task>?
Numbered steps...

## Comparison
| X | Y |
|---|---|

## FAQ
- Q: ...
- A: ...

llms.txt

Not required by Google (its crawlers ignore it) — useful for other LLMs, where early adopters report improved citation accuracy. Place at site root: https://example.com/llms.txt

# Site Name
> One-line description

## Pages
- [Homepage](https://example.com/): description
- [Docs](https://example.com/docs/): description

References

  • seo-entity — entity signals + schema that drive AI citations
  • skills/seo/04-geo-2026/ (ai-platforms, citation-strategies, content-structure, llm-crawlability, zero-click-optimization)
  • skills/seo/08-measurement/share-of-model.md

Gives 0 of the 12 instructions most context ai engineering skills give

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-06

  • dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
  • dispatch final reviewer after all tasksin 37 of 1193, across 11 files
  • provide full task text to the subagentin 31 of 1193, across 10 files
  • review spec compliance before code qualityin 27 of 1193, across 10 files
  • make the hook script executablein 26 of 1193, across 8 files
  • re-snapshot after navigation or DOM changesin 25 of 1193, across 17 files
  • answer subagent questions before proceedingin 22 of 1193, across 7 files
  • mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
  • merge hook into existing settingsin 21 of 1193, across 3 files
  • read files before editing themin 21 of 1193, across 9 files
  • ask if installation is global or projectin 20 of 1193, across 2 files
  • copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

  • place a quick answer in the first 100 words
  • use direct H2 questions
  • include attributed statistics
  • provide an author bio with credentials
  • keep the updated date under 12 months
  • place an llms.txt file at the site root

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.