Token导航 LogoToken导航

Agent Skill · 研究检索

geo-content-optimizer(地理内容优化器)

用于辅助文档、README、Markdown、说明文和内容稿件的整理与改写。它适合让 Agent 提炼结构、补齐章节、统一术语、检查链接或把零散材料整理成可读文档。使用时应保留项目已有事实、命令和路径,不要把未确认的信息写成确定结论;涉及对外文案时,还需要控制语气,避免过度营销或夸大能力。

geo-content-optimizer 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 65,351。

总安装 282周安装 12GitHub Stars 10下载 99核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:geo-content-optimizer(地理内容优化器)
来源仓库:https://github.com/geoly-ai/geo-skills
仓库路径:skills/geo-content-optimizer
安装命令:
npx skills add https://github.com/geoly-ai/geo-skills --skill geo-content-optimizer
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/geoly-ai/geo-skills --skill geo-content-optimizer

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

geoflow-content-automation 辅助文档、README 和内容稿件的整理与改写。适用于内容创作、文档编写和说明文撰写等场景。通过 npx skills add 命令从指定 GitHub 仓库安装并使用该技能。安装前需确认权限范围和维护状态,注意可能触发的联网或文件操作行为。

geo-content-optimizer 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/geo-content-optimizer

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/geoly-ai/geo-skills --skill geo-content-optimi…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

geo-content-optimizer 怎么安装?

在终端执行 npx skills add https://github.com/geoly-ai/geo-skills --skill geo-content-optimizer。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

geo-content-optimizer 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

geo-content-optimizer 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

geo-content-optimizer 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

geo-content-optimizer 用的人多吗?

公开数据是累计安装 282 次,近一周安装 12 次,下载 99 次,GitHub 10 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

geo-content-optimizer 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
geo-content-optimizer

地理内容优化器 · 本页

28210只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

GEO Content Optimizer

Methodology by GEOly AI (geoly.ai) — content that AI wants to cite follows predictable patterns.

Optimize existing content to maximize the probability of being cited by AI platforms.

Quick Start

Analyze and optimize content:

python scripts/analyze_content.py <file.md> [--output report.json]
python scripts/optimize_content.py <file.md> [--type article|product|faq|landing|about]

Example:

python scripts/analyze_content.py blog-post.md
python scripts/optimize_content.py product-page.md --type product --output optimized.md

The GEO Citation Framework

AI platforms prefer content with these signals:

SignalImplementation
Direct Answer FirstClear answer in first 2 sentences
Entity-RichBrand, product, topic named explicitly
Structured FormatH2/H3 headers, lists, tables
Fact-DenseNumbers, dates, statistics with sources
FAQ-FormattedExplicit Q&A blocks (2-3 minimum)
Definition ClarityKey terms defined in one sentence
Unique DataOriginal research or insights
Authoritative VoiceDeclarative statements, not hedging

Full framework details: See references/citation-framework.md

Content Types

Different content types need different optimization strategies:

TypeFocusKey Tactics
ArticleInformation densityLead paragraph, entity mentions, data
ProductFeature claritySpecifications, use cases, comparisons
FAQAnswer completenessDirect Q&A, comprehensive responses
LandingValue propositionClear benefits, social proof, CTA
AboutEntity authorityFounding story, credentials, mission

Type-specific guides: See references/content-types.md

Optimization Checklist

Before optimizing, audit content against these criteria:

  • First paragraph answers the core question directly
  • H2/H3 headers on every major section
  • 2-3 FAQ-format Q&A blocks present
  • Brand name appears in first 100 words
  • Claims backed by data or sources
  • Key terms defined clearly
  • Lists/tables used for complex information
  • Declarative voice (not hedging)

Run automated audit:

python scripts/analyze_content.py content.md --format checklist

The 8 Optimization Rules

Rule 1 — Lead with the Answer

❌ Before: "In today's digital landscape, many brands are wondering about AI search..." ✅ After: "GEO (Generative Engine Optimization) is the practice of optimizing content to appear in AI-generated answers on platforms like ChatGPT, Perplexity, and Gemini."

Rule 2 — Add Definition Blocks

Define key terms in a single clear sentence:

Entity SEO: The practice of optimizing content around specific entities (people, places, things) rather than just keywords.

Rule 3 — Structure with Headers

Use H2 for sections, H3 for subsections:

## What is GEO?

### Definition
[Clear one-sentence definition]

### Why It Matters
[Key points with data]

Rule 4 — Convert to FAQ Format

Turn implicit questions into explicit Q&A:

❌ Before: "Many people ask how GEO differs from SEO." ✅ After:

## Frequently Asked Questions

**Q: How is GEO different from SEO?**

A: While SEO optimizes for search engine rankings, GEO optimizes for AI-generated answers. SEO focuses on keywords and backlinks; GEO focuses on factual accuracy, entity clarity, and direct answers.

Rule 5 — Add Data Points

Include specific numbers and dates:

❌ Before: "Many businesses are adopting AI." ✅ After: "According to McKinsey's 2024 report, 72% of enterprises have adopted AI in at least one business function, up from 55% in 2023."

Rule 6 — Entity-First Writing

Mention entities early and often:

  • Brand name in first 100 words
  • Product names with descriptions
  • People with full names and titles
  • Locations with context

Rule 7 — Remove Hedging

Replace uncertain language with declarative statements:

❌ Hedging✅ Declarative
"might be""is"
"could potentially""does"
"some experts believe""research shows"
"it seems that"[remove entirely]

Rule 8 — Format for Scannability

Use:

  • Bullet lists for related items
  • Numbered lists for sequences
  • Tables for comparisons
  • Bold for key terms
  • Blockquotes for important statements

Complete rules with examples: See references/optimization-rules.md

Output Format

Optimized content should include:

  1. Optimized text — Ready-to-publish markdown
  2. Change log — What was changed and why
  3. Before/After comparison — Key improvements highlighted
  4. Score — Citation-readiness rating (0-100)

Advanced Usage

Batch Processing

Optimize multiple files:

python scripts/batch_optimize.py ./content/ --type article --output ./optimized/

Competitive Analysis

Compare your content to competitors':

python scripts/analyze_content.py your-article.md --compare competitor-article.md

Scoring System

Get a citation-readiness score:

python scripts/analyze_content.py article.md --score-only

Scores:

  • 80-100: Excellent (highly citeable)
  • 60-79: Good (minor improvements needed)
  • 40-59: Fair (significant work required)
  • 0-39: Poor (major rewrite needed)

See Also

平台分布

Codex

35.11%
按下载量换算35

Claude

29.46%
按下载量换算29

Cursor

17.47%
按下载量换算17

Gemini CLI

8.71%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills