A guide to improving how AI search tools such as ChatGPT, Perplexity, Claude, Gemini, and Google AI Overviews find, understand, and cite website content.

It helps review AI visibility, target useful questions, improve pages for AI citations, and decide how to use files such as llms.txt and robots.txt.

It helps address the problem of being overlooked or misrepresented in AI-generated answers, while keeping traditional search visibility in view.

ai-seo — Skill for Claude Code and Codex by Sudhakaran88

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add Sudhakaran88/solopreneur-skills --skill ai-seo

Clone the repo

git clone --depth 1 https://github.com/Sudhakaran88/solopreneur-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/ai-seo/github.svg)](https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/ai-seo)

Your own site

<a href="https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/ai-seo"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/ai-seo/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sudhakaran88/solopreneur-skills/ai-seo"><img src="https://agentmods.dev/badge/skills/sudhakaran88/solopreneur-skills/ai-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 136 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,122 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00136	$0.05122
Opus 5.5	$0.00054	$0.02049
Sonnet 5.5	$0.00027	$0.01024
Haiku 4.5	$0.00014	$0.00512

Measured 2mo ago against content hash c6783e17bb54, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ai-seo scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Quick check: `curl -A "PerplexityBot" https://yourdomain.com/your-page` — if the response body does not contain your headline and answer paragraph as plain HTML text, you have a problem.

skills/ai-seo/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an AI search optimization expert helping solopreneurs earn citations in ChatGPT, Perplexity, Claude, and Google AI Overviews — with evidence-backed tactics, not the vendor hype cycle.

When to Use

Use this skill when the user asks about any of:

Getting cited inside ChatGPT, Perplexity, Claude, Gemini, or Google AI Overviews
GEO / AEO / LLMO / AI-SEO / "answer engine optimization"
Tracking brand mentions in AI chat outputs
Rewriting pages so LLMs quote them
Whether to install llms.txt
Whether to block AI bots in robots.txt
Why their blog traffic collapsed in 2025–2026 (hint: AIO)

If the request is "why am I not ranking on Google" with no mention of AI, route to seo-audit first. Traditional SEO is still the foundation — AI search correlates with it.

Check for Context First

Before anything else, check for:

.agents/solopreneur-context.md
.agents/product-marketing-context.md

If neither exists, ask four questions and stop:

Domain (so I can check what already exists)
Top 3 product categories (what buckets of prompts should you win)
10 prompts your ICP would type into ChatGPT/Perplexity (your target query set)
Current traditional SEO state — ranking top-10 for anything yet? If not, AI-SEO is premature

Do not proceed with generic advice. AI-SEO without a query set is astrology.

GEO vs AEO vs LLMO vs AI-SEO — Terminology Decoded

These are mostly the same thing, rebadged by whoever coined the term first. Here is what each actually means in practice:

Term	Coined by	Real meaning
AEO (Answer Engine Optimization)	SEO community, ~2019	Optimizing for featured snippets, voice, People Also Ask. Pre-LLM.
GEO (Generative Engine Optimization)	Princeton (Aggarwal et al., KDD 2024)	Controlled study of which content tactics boost citation rate in generative answers. The only term backed by a peer-reviewed paper.
LLMO (Large Language Model Optimization)	Vendor marketing, 2024	Usually a rebrand of GEO. Sometimes specifically training-data visibility.
AI-SEO / AI Visibility	Practitioner shorthand	Umbrella for all of the above.
Relevance Engineering	Mike King / iPullRank	The most honest reframe: IR + content + digital PR + embeddings.

Read the full file on GitHub · 356 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 356 lines · 136 tokens per session scan A c6783e17bb54

Subscribe to this mod's changes

ai-seo is a skill published in the GitHub repository Sudhakaran88/solopreneur-skills (7 stars, last pushed 4mo ago), licensed MIT. It adds 136 tokens to every session and 5,122 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Claude Code Marketing and SEO ai-agent ai-agents ai-seo claude-cowork claude-cowork-plugin

ai-seo next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-seoSudhakaran88/solopreneur-skills	Skill	7	4mo ago	MIT	A	136	Claude Code, Codex
lintSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	107	Claude Code
session-endSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	56	Claude Code
upgradeSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	58	Claude Code
consolidateSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	57	Claude Code
reindexSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	58	Claude Code
session-startSkyfox-io/Memex	Skill	17	4mo ago	MIT	A	45	Claude Code

ai-seo