SkillFoxx

GEO Content Optimizer Skill

Three GEO skills: a one-off page audit from a URL, step-by-step optimization and a platform for long-term monitoring.

  • 238 ★ on the repository
  • Last commit
Skill

Extended access

Why this level

  • The skills call search and external APIs, so queries and keys go to third-party services.
  • `geolook` launches a local web panel and installs Python libraries.
All reasons and checks

liangdabiao/geo-content-optimizer-skillAuthor:liangdabiao

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/geo-content-optimizer-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The skills call search and external APIs, so queries and keys go to third-party services.
  • `geolook` launches a local web panel and installs Python libraries.

This is third-party code. Review the repository files before installing.

What it does

A set of three skills for GEO: optimizing content for answers from AI search such as ChatGPT, Perplexity, Gemini and Google AI Overview. The skills live in `skills/` and trigger through slash commands. `geo-content-optimizer` takes a URL, reads the page title, expands the query through Google search, gets the Google AI Overview answer, compares it with the page and saves a report of gaps and recommendations to `output/<domain>/`. `geo-optimizer` guides step by step: generates Schema markup, checks text readability for AI, plans a cluster of a pillar page and child pages, measures brand visibility through a search API (Kimi by default, Perplexity optional) and builds a quarterly report. `geolook` launches a local web panel for ongoing GEO: per-engine snapshots, tasks with acceptance criteria and a client deliverable package. Reports and skill text are in Chinese.

Who it is for. Marketers and site owners who want to know how AI search mentions their brand, and agencies running GEO for clients.

Good fit when

  • You need a quick check of one page: what Google AI Overview said that the page did not.
  • A site needs organization or FAQ JSON-LD markup.
  • An article is checked for AI readability: long sentences, filler words, questions, figures.
  • An agency runs monthly and quarterly brand-mention monitoring for a client.

Not a fit when

  • You need keyword rankings in Yandex and Google: the skills do not replace a classic SEO audit.
  • You need reports in Russian or English without rework.
  • An external search service API key cannot be provided.

Example request

/geo-content-optimizer https://example.com — audit the page and show what is missing compared with the Google AI Overview answer.

Limitations

Reports and skill prompts are written in Chinese. `geo-content-optimizer` and `geo-optimizer` work without an API key except for visibility measurement, which needs a Kimi or Perplexity key. `geolook` requires Python 3.9 or newer with requests, beautifulsoup4 and lxml, and a 302.AI key for full coverage. Article drafts from `geolook` need manual fact checking because AI can invent figures and examples. Skills are installed manually by copying folders into the agent's skills directory.

How to disable. Delete the `geo-content-optimizer`, `geo-optimizer` and `geolook` folders from the skills directory and stop the local `geolook` panel if you started it.

FAQ

Which skill should I start with?

Start with `geo-content-optimizer`: it checks a single URL without Python or keys and shows how the page compares with the AI answer.

Are API keys required?

The first two skills mostly work without them. A key is needed for brand visibility measurement (Kimi or Perplexity) and for `geolook` (302.AI is recommended).

Where do I copy the skills?

To `~/.claude/skills/` on macOS and Linux or `%USERPROFILE%\.claude\skills\` on Windows. Then restart the agent.

Which agents are supported?

Claude Code, Codex and Workbuddy.

What does geolook do?

It launches a local web panel for ongoing GEO: per-engine snapshots, a map of places to be mentioned, a brand fact base, tasks with acceptance criteria and a client package.

Discussion

No questions or reviews yet.

Skills

24 skills for GEO: page audits for AI answers, articles and comparisons, brand mention sampling in ChatGPT and DeepSeek, Word and PDF reports

SkillBroad access917

SEO and AI-search optimization skill: a 100-point site score, an action plan, ready fixes and 20 diagnostic scripts.

SkillExtended access103

E-GEO scores a page on 10 GEO criteria, rewrites it and writes JSON-LD so AI search engines cite the site more often

SkillExtended access218

A skill that picks 3 to 5 SEO and GEO skills from a hand-checked list for a job: keywords, audits, content and AI answer citation.

SkillExtended access52

A GEO and SEO skill for the Chinese market: page scoring, rewrites for AI citation, llms.txt and competitor comparison

SkillMinimal access91

A CLI, Python library and MCP server that scores how ready a site is to be cited by ChatGPT, Perplexity and AI Overviews

CLIExtended access1.3K

README in short

The project frames GEO as optimizing for citation in AI answers and gives three tools of increasing depth, from a single-page check to a panel-based platform. MIT license.

README badge

Original SKILL.md

---
name: geo-content-optimizer
description: >
  AI 驱动的网页内容优化分析工具。输入 URL，自动抓取页面标题，通过 Google 搜索进行查询扩展，
  获取 Google AI 概览，对比有机搜索覆盖与 AI 生成概览，生成中文优化建议报告。
  当用户说"优化这个页面"、"分析这个网址"、"GEO 分析"、"内容优化"、"geo分析"或提供 URL
  并要求内容改进建议时触发。
argument-hint: <url>
allowed-tools: WebSearch, mcp__web_reader__webReader, mcp__playwright__browser_navigate, mcp__playwright__browser_snapshot, mcp__playwright__browser_take_screenshot, mcp__playwright__browser_click, mcp__playwright__browser_close, Read, Write, Bash
---

# GEO Content Optimizer

You are a content optimization specialist. Your task is to analyze a webpage and produce a comprehensive content optimization report by comparing organic search coverage with Google AI Overviews.

**Language requirement**: All output files (report, summaries, overviews) must be written in **Chinese (简体中文)**. Keep URLs, model names, and technical terms in their original English form, but all analysis text, headings, and recommendations should be in Chinese.

## Input

URL to analyze: `$ARGUMENTS`

If no URL is provided, ask the user to provide one before proceeding.

---

## Phase 0: Output Directory Setup

Each analysis must be saved to an **independent folder** to avoid overwriting previous results.

1. Extract the domain name from the input URL (e.g., `https://apimart.ai/` → `apimart-ai`, `https://www.example.com/path` → `example-com`).
2. Generate the folder name: strip `www.`, replace `.` with `-`, remove trailing slashes.
3. Create the directory: `output/<domain-slug>/`
4. All subsequent phases write to this directory.

**Convention**:
```
output/
  apimart-ai/
    report.md
    ai_overview.md
    query_fanout.md
    query_fanout_summary.md
  openai-com/
    report.md
    ...
```

Store the output path as `OUTPUT_DIR`.

---

Report a problem