A German-language SEO review and improvement guide for the DACH region—Germany, Austria, and Switzerland—with a focus on how AI answer systems find, cite, and recommend websites.

Use it to assess a brand or website's search access, useful content, structured information, AI crawler access, and evidence of visibility in AI answers.

It helps separate documented facts from guesses about AI search visibility and avoids claiming unsupported ranking effects.

ai-seo — Skill for Claude Code by LOGIN-TB/claude-skills

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 LOGIN-TB/claude-skills --skill ai-seo

Clone the repo

git clone --depth 1 https://github.com/LOGIN-TB/claude-skills

Made for: Claude Code.

Or install marketing-dach, the plugin that ships this one along with the rest of its 13 skills.

Its marketplace also offers this one on its own, as the plugin ai-seo — /plugin install ai-seo after adding the marketplace above.

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/login-tb/claude-skills/ai-seo/github.svg)](https://agentmods.dev/skills/login-tb/claude-skills/ai-seo)

Your own site

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

Per session 166 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,544 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.

Model	Per session	Once invoked
Fable 5.1	$0.00166	$0.02544
Opus 5.5	$0.00066	$0.01018
Sonnet 5.5	$0.00033	$0.00509
Haiku 4.5	$0.00017	$0.00254

Measured 2mo ago against content hash 02faad005e62, 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 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 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.

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 · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KI-SEO

Verbessere, wie eine Marke oder Seite in KI-generierten Antworten abgerufen, zitiert, erwähnt und empfohlen wird. Klassische SEO, Crawlbarkeit, nützliche Inhalte und überprüfbare Autorität bilden die Grundlage; KI-spezifische Struktur ist nur eine zusätzliche Ebene.

Evidenzregeln

KI-Suchverhalten ändert sich schnell, viele Studien sind beobachtend. Vor aktuellen Prozentwerten, Crawlernamen, Plattform-Backends, Sichtbarkeitssteigerungen oder Mechanismen:

aktuelle Primärdokumentation oder Originalstudie prüfen;
Quelle, Datum, Plattform/Modell, Region und Methode nennen;
Korrelation nicht als Rankingfaktor oder Kausalität ausgeben;
keine Zitate, Rankings, Empfehlungen oder Trafficwirkung versprechen;
für Google-KI-Funktionen aktuelle Google-Hinweise zugrunde legen: normale Suchberechtigung und nutzerorientierte SEO; kein Spezial-Markup oder KI-Textfile als Pflicht behaupten.

Keine erfundenen Rankingfaktoren. Weder Strukturmuster, llms.txt, Schema, Erwähnungen, Autorenprofile noch Crawlerfreigaben als bestätigten KI-Rankingfaktor bezeichnen, sofern die jeweilige Plattform dies nicht aktuell und eindeutig dokumentiert.

Kontext und Sichtbarkeitsstufen

Erfasse Domain, Prioritätsseiten, Marke, Angebot, Zielgruppe, Region, Sprache, wichtige Prompts, Plattformen, Wettbewerber, Ausgangssichtbarkeit und Ziel. Keine privaten Verzeichnisse, Zugangsdaten oder personenbezogenen Daten durchsuchen.

Trenne:

Abgerufen: System liest die Seite während der Antwortbildung.
Zitiert: Seite erscheint als Quelle.
Erwähnt: Marke steht im Antworttext.
Empfohlen: Marke gelangt in eine Auswahlliste.

Ein nützlicher Inhalt kann zitiert werden, ohne dass der Anbieter empfohlen wird. Empfehlungen können von überprüfbarer, webweiter Bestätigung durch Rezensionen, Communities, Fachmedien, Videos, Podcasts oder Analysten abhängen; dies ist keine Garantie.

Audit-Ablauf

1. Reproduzierbare Baseline

Prompt	Plattform/Modell	Datum/Region/Sprache	Antwort	Abgerufen/zitiert/erwähnt/empfohlen	Quellen	Einordnung

Read the full file on GitHub · 142 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 · 142 lines · 166 tokens per session scan A 02faad005e62

Subscribe to this mod's changes

ai-seo is a skill published in the GitHub repository LOGIN-TB/claude-skills (82 stars, last pushed 8d ago), licensed MIT. It adds 166 tokens to every session and 2,544 once invoked, about $0.0007 per session on Opus 5.5. 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.

Marketing and SEO agent-skills ai claude claude-skills deutsch prompt-engineering

ai-seo next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ai-seoLOGIN-TB/claude-skills	Skill	82	8d ago	MIT	A	166	Claude Code
prompt-masternidhinjs/prompt-master	Skill	16k	15d ago	MIT	B	78	Claude Code, Codex
dep-auditorlaolaoshiren/claude-code-skills-zh	Skill	905	2d ago	MIT	A	72	Claude Code, Codex
github-actions-genlaolaoshiren/claude-code-skills-zh	Skill	905	2d ago	MIT	A	57	Claude Code, Codex
api-testerlaolaoshiren/claude-code-skills-zh	Skill	905	2d ago	MIT	A	86	Claude Code, Codex
skill-curatorlaolaoshiren/claude-code-skills-zh	Skill	905	2d ago	MIT	A	75	Claude Code, Codex
env-managerlaolaoshiren/claude-code-skills-zh	Skill	905	2d ago	MIT	A	22	Claude Code, Codex