Token导航 LogoToken导航

Agent Skill · 研究检索

geo-content-optimization(地理内容优化)

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-optimization 是研究检索类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为只读;许可证为 MIT-0,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 30,034。

总安装 2,946周安装 124GitHub Stars 公开资料未说明下载 1,032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
MIT-0
版本
0.3.0

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-optimization(地理内容优化)
来源仓库:https://github.com/jinhuadeng/geo-content-optimization
安装命令:
openclaw skills install geo-content-optimization
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install geo-content-optimization

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。

geo-content-optimization 用于辅助文档和内容稿件的整理与改写,适合提炼结构和统一术语。适用于优化文章、登录页和品牌内容,提高在 ChatGPT、Claude 等系统的引用率。通过 clawhub 安装,需结合原始 README 核验具体用法,注意权限与维护状态。

安装命令为 openclaw skills install geo-content-optimization,来源仓库为 jinhuadeng/geo-content-optimization。使用时应保留项目事实,避免过度营销或夸大能力。

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 OpenClaw;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 openclaw skills install geo-content-optimization;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-optimization 怎么安装?

在终端执行 openclaw skills install geo-content-optimization。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

geo-content-optimization 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。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-optimization 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-optimization 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

geo-content-optimization 用的人多吗?

公开数据是累计安装 2,946 次,近一周安装 124 次,下载 1,032 次。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-optimization 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

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 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

  • 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 OpenClaw,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。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 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-optimization

地理内容优化 · 本页

2,946—只读MIT-0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

name
geo-content-optimization
description
Optimize articles, landing pages, docs, and brand content for visibility, citation, and recommendation in generative AI systems such as ChatGPT, Claude, Gemini, Perplexity, and AI Overviews. Use when the user asks about GEO, AEO, AI SEO, LLM visibility, answer engine optimization, AI citations, AI share of voice, structured content for LLMs, rewriting content to be more citable/extractable, improving Chinese content for AI discovery, or building a repeatable workflow to improve how a brand or page gets surfaced in AI-generated answers.

GEO Content Optimization

Use this skill when the user wants to improve how content gets discovered, extracted, cited, and recommended by AI answer engines.

Default goal:

  • make content easier for AI systems to extract and quote
  • increase brand/topic association
  • improve odds of being cited in AI-generated answers
  • turn fuzzy “AI SEO” talk into a concrete editorial workflow

What GEO means in practice

Treat GEO as content clarity + extractability + authority + distribution for AI-mediated discovery.

Do not promise rankings. Do not claim a guaranteed placement in ChatGPT, Claude, Gemini, or Perplexity. Frame the work as improving:

  • visibility
  • citation likelihood
  • answer inclusion probability
  • brand/topic association

Core workflow

  1. Clarify the target

Identify: - brand / product / person / site - target topics and queries - target engines (ChatGPT, Claude, Gemini, Perplexity, Google AI Overviews) - page type: article, landing page, docs, FAQ, comparison page, glossary, category page - desired outcome: cited, summarized, compared, recommended, remembered

  1. Choose the GEO mode

- Audit mode: evaluate existing content and find gaps - Rewrite mode: rewrite an article/page for stronger extractability and citation value - Brief mode: create an outline for a GEO-first article - Entity mode: strengthen brand/entity-topic associations - Comparison mode: create “X vs Y”, alternatives, best-for, use-case content - FAQ mode: generate structured Q&A blocks optimized for answer engines - Chinese GEO mode: rewrite Chinese content for higher clarity, quotability, and AI citation fitness

  1. Evaluate against the GEO checklist

Check for: - clear topic-entity association in first 150 words - direct answer blocks near the top - headings that mirror user queries - scannable facts, comparisons, steps, pros/cons, definitions - updated facts and explicit dates when relevant - named entities, product names, use cases, and terminology consistency - quotable lines that an answer engine can easily lift - supporting evidence, examples, and concrete claims

  1. Rewrite for extraction

Prefer: - direct, plain answers before nuance - short paragraphs - clear subheads - structured lists and tables - definition-style sentences - use-case phrasing - comparison framing

  1. Add answer-engine hooks

Typical hooks: - “What is X?” - “How does X work?” - “Who is X for?” - “X vs Y” - “Best X for …” - “Common mistakes” - “FAQ”

  1. Package the deliverable

Return in this order when relevant: - GEO diagnosis - rewrite priorities - revised structure - rewritten content or sections - FAQ block - distribution suggestions - measurement suggestions

Chinese GEO guidance

For Chinese content, optimize for:

  • 开头 3 句内说清“它是什么 / 适合谁 / 为什么值得看”
  • 避免空泛抒情和长铺垫
  • 用可摘录句代替抽象判断
  • 多用“是什么 / 为什么 / 怎么做 / 和谁比 / 适合谁”结构
  • 补 FAQ、对比块、结论块
  • 让每个段落单独摘出来也能成立

Writing rules for GEO

  • Answer the implied question early.
  • Put the clearest version of the truth first.
  • Write for extraction, not suspense.
  • Use explicit nouns over vague pronouns.
  • Repeat the core entity-topic pair naturally.
  • Prefer “X is …” / “X helps …” / “X is best for …” structures.
  • Use tables when a reader may ask for comparison.
  • Keep strong, quotable sentences that can survive outside the page context.
  • When facts may age, add date context.

What usually hurts GEO

Avoid these anti-patterns:

  • long throat-clearing intros
  • vague thought-leadership with no answer blocks
  • brand pages that never clearly say what the product is
  • weak headings that don’t match user query language
  • only abstract benefits, no concrete use cases
  • excessive marketing language with low information density
  • hidden definitions buried deep in the page
  • no FAQ / no comparison / no direct answer sections

Deliverable patterns

Audit output

  • Current GEO score / diagnosis
  • Top 5 weaknesses
  • Top 5 fixes
  • Suggested new headings
  • Suggested FAQ block

Rewrite output

  • New title
  • Better intro
  • Revised H2/H3 structure
  • Rewritten sections
  • FAQ block
  • Suggested comparison table

Brief output

  • Target query cluster
  • Entity/topic framing
  • Search/answer intent
  • Outline
  • extraction hooks
  • proof/examples to include

Measurement guidance

Use these indicators when possible:

  • AI citation presence
  • AI mention frequency
  • share of voice in answer engines
  • branded query growth
  • referral traffic from AI surfaces when available
  • impression / click shifts on high-intent informational pages

Bundled resources

  • references/geo-principles.md — core GEO concepts, terminology, and practical heuristics
  • references/query-patterns.md — common answer-engine query patterns to map content against
  • references/rewrite-playbook.md — tactical rewrite moves for articles, landing pages, and docs
  • references/chinese-geo-playbook.md — Chinese GEO rewrite patterns for公众号/官网/品牌内容
  • references/demo-use-cases.md — demo-friendly before/after scenarios you can show or sell
  • scripts/geo_audit.py — lightweight audit for markdown/html/text pages using GEO heuristics
  • scripts/geo_rewrite_brief.py — generate a structured GEO rewrite brief from raw content

How to use the scripts

Quick audit:

python3 scripts/geo_audit.py <file>

Rewrite brief:

python3 scripts/geo_rewrite_brief.py <file>

Rewrite output package:

python3 scripts/geo_rewrite_output.py <file>

Use scripts for a fast first pass, then apply editorial judgment.

Default stance

Be concrete. Be skeptical of hype. Turn “AI SEO” into visible content changes, not buzzword theater. cripts/geo_rewrite_brief.py <file>


Use scripts for a fast first pass, then apply editorial judgment.

## Default stance

Be concrete.
Be skeptical of hype.
Turn “AI SEO” into visible content changes, not buzzword theater.

平台分布

OpenClaw

73.88%
按下载量换算762

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

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