ai-seo

ai-seo is a skill for Claude Code from alebgl77/claude-inc. It costs 114 tokens per session (974 once invoked), scanned A, original, MIT.

A content reviewer and rewriting guide for improving visibility in web search and answers from AI assistants. It checks how clearly a page defines its subject, answers questions, links related pages, and includes machine-readable details.

In plain words
What is it for?
Use it to audit or rewrite articles and other web pages, create question-based headings and concise answers, add structured page data, and improve internal links and AI-reading guidance.
Why use it?
It helps fix pages that are hard for search engines or AI assistants to understand, quote, or rank. It can identify structural problems before publication or rewrite an existing page when asked.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the claude-inc plugin — 54 skills, 3 commands, 9 agents shipped together

Good fit Use it to audit or rewrite articles and other web pages, create question-based headings and concise answers, add structured page data, and improve internal links and AI-reading guidance.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alebgl77/claude-inc/ai-seo
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 alebgl77/claude-inc --skill ai-seo
Clone the repo
git clone --depth 1 https://github.com/alebgl77/claude-inc

Made for: Claude Code.

Or install claude-inc, the plugin that ships this one along with the rest of its 54 skills, 3 commands, 9 agents.

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.

agentmods badge for ai-seo

README.md
[![agentmods](https://agentmods.dev/badge/skills/alebgl77/claude-inc/ai-seo/github.svg)](https://agentmods.dev/skills/alebgl77/claude-inc/ai-seo)
Your own site
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/ai-seo"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/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.

agentmods 80×15 button for ai-seo

Your own site · 80×15
<a href="https://agentmods.dev/skills/alebgl77/claude-inc/ai-seo"><img src="https://agentmods.dev/badge/skills/alebgl77/claude-inc/ai-seo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 974 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00114 $0.00974
Opus 5 $0.00057 $0.00487
Sonnet 5 $0.00023 $0.00195
Haiku 4.5 $0.00011 $0.00097

Measured 9d ago against content hash 9087e3451006, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ai-seo scanned grade A with 0 findings 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 9d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai-seo/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI SEO — Search Whisperer

"Rank in AI search"

When to use

  • A page must rank in Google and get quoted by AI answers — "make this pillar page rank"
  • Diagnosing invisibility — "why doesn't Perplexity ever cite our docs?"
  • Pre-publish optimization pass — "SEO-check this post before it ships"
  • Site-level AI readiness — "do we need an llms.txt? Set it up"
  • Not for net-new persuasion copy — that's copywriting

Workflow

  1. Pick the mode. Audit (score an existing page, list fixes) or rewrite (produce the optimized version). If the page exists, audit first; rewrite on request or when most findings are structural.
  2. Entity pass. The first 100 words must name the entity, its category, and 1-2 differentiators in plain declarative sentences ("X is a Y that Z"). AI systems quote pages that define themselves.
  3. Map real queries to H2s. Rewrite headings as the questions users actually ask — People Also Ask phrasing, support-ticket phrasing. One question, one H2.
  4. Write extractable answers. Directly under each H2, a 40-60 word standalone answer: complete sentences, no "as mentioned above", quotable verbatim by an AI. Depth and nuance follow after it.
  5. Emit schema. JSON-LD matching the page type — Article, FAQPage, Product, HowTo. Fill every required property; no empty fields, no invented ratings.
  6. Create or update llms.txt. Site purpose, key pages with one-line descriptions, canonical sources.
  7. Internal linking. 3-5 contextual links with descriptive anchors (never "click here"), pointing at the money page and its supporting cluster.
  8. E-E-A-T pass. Author byline with credentials, published/updated dates, cited primary sources, and at least one first-hand signal — original data, screenshots, a tested-by-us statement.
  9. Deliver the scorecard (audit) or the full rewrite plus schema and llms.txt snippet (rewrite).

Output format

MODE: <audit | rewrite>
PAGE: <path or URL>
TARGET QUERIES: <3-5 real queries this page should own>

SCORECARD (audit mode)
| Check | Status | Finding | Fix |
|---|---|---|---|
| Entity-rich intro | PASS/FAIL | ... | ... |
| Question-shaped H2s | ... | ... | ... |
| Extractable answers (40-60 w) | ... | ... | ... |
| Schema JSON-LD | ... | ... | ... |
| llms.txt | ... | ... | ... |
| Internal links | ... | ... | ... |
| E-E-A-T signals | ... | ... | ... |

REWRITE (rewrite mode)
<optimized page content>

SCHEMA
<script type="application/ld+json">{ ... }</script>

LLMS.TXT ENTRY
<lines to add>

Read the full file on GitHub · 75 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.

  1. 9d ago First seen · 75 lines · 114 tokens per session scan A 9087e3451006

Subscribe to this mod's changes

ai-seo is a skill published in the GitHub repository alebgl77/claude-inc (14 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 974 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.