geo-llmstxt by zubair-trabzada/geo-seo-claude
npx skills add https://github.com/zubair-trabzada/geo-seo-claude --skill geo-llmstxt此技能处理与 llms.txt 标准相关的一切事务——这是一项新兴的约定(由 Jeremy Howard 于 2024 年 9 月提出,在 2025-2026 年间逐渐被采纳),允许网站向 AI 系统提供关于其内容、结构和关键信息的结构化指导。它类似于 robots.txt(告诉爬虫不应访问什么),但相反,它告诉 AI 系统关于网站最需要了解的是什么。
AI 语言模型在处理网站时面临一个根本性挑战:它们必须确定哪些页面最重要、网站是关于什么的以及内容是如何组织的——通常需要通过爬取许多页面并推断结构。llms.txt 通过提供一个明确的、机器可读(且人类可读)的摘要来解决这个问题。
拥有一个精心制作的 llms.txt 的好处:
文件必须位于域的根目录:
https://example.com/llms.txt
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
该文件使用具有特定约定的 Markdown 格式:
# [网站名称]
> [关于网站/业务是做什么的一句话描述。保持在 200 个字符以内。]
## 文档
- [页面标题](https://example.com/page-url):关于此页面涵盖内容及其重要性的简洁描述。
- [另一个页面](https://example.com/another-page):内容描述。
## 可选
- [次要页面](https://example.com/optional-page):描述。
1. 标题(必需)
# 网站名称
#)。2. 描述(必需)
> 网站/业务的简要描述
>)。3. 主要部分(必需——至少一个)
使用 H2 标题(##)按类别组织页面。常见的部分名称:
| 部分名称 | 目的 | 示例内容 |
|---|---|---|
## 文档 | 主要文档或关键页面 | 产品页面、服务描述、核心内容 |
## 可选 | 值得了解的次要页面 | 博客文章、补充资源 |
## API | API 文档 | API 参考、认证指南 |
## 博客 | 博客或新闻内容 | 近期/热门文章 |
## 产品 | 产品目录 | 产品页面、定价 |
## 服务 | 服务项目 | 服务描述、流程页面 |
## 关于 | 公司信息 | 关于页面、团队、使命 |
## 资源 | 教育/参考内容 | 指南、教程、白皮书 |
## 法律 | 法律文件 | 服务条款、隐私政策 |
## 联系 | 联系信息 | 联系页面、支持渠道 |
4. 页面条目(必需)
每个条目遵循以下格式:
- [页面标题](URL): 页面内容描述
页面条目的规则:
5. 关键事实部分(推荐)
## 关键事实
- 成立于 [年份],由 [创始人] 创立
- 总部:[城市,国家]
- 在 [Y] 个国家拥有 [X] 名客户/用户
- 主要产品:[产品 A]、[产品 B]、[产品 C]
- 行业:[行业分类]
此部分提供了 AI 系统在回答有关您业务的用户查询时经常需要的快速参考数据。
6. 联系部分(推荐)
## 联系
- 网站:https://example.com
- 邮箱:hello@example.com
- 支持:support@example.com
- 电话:+1-555-123-4567
- 地址:123 Main St, City, State, ZIP, Country
除了 llms.txt,网站还可以提供 /llms-full.txt——一个包含更多细节的扩展版本。
与 llms.txt 的区别:
| 功能 | llms.txt | llms-full.txt |
|---|---|---|
| 长度 | 简洁(50-150 行) | 全面(150-500+ 行) |
| 页面条目 | 10-30 个关键页面 | 30-100+ 个页面 |
| 描述 | 每个条目 10-30 个词 | 每个条目 30-100 个词,可能包含每个页面的关键事实 |
| 受众 | 快速 AI 理解 | 深度 AI 分析 |
| 部分 | 3-6 个部分 | 8-15 个部分 |
| 关键事实 | 业务层面的事实 | 页面层面的事实和数据点 |
两个文件可以共存。AI 系统首先检查 llms.txt,然后可能选择性地加载 llms-full.txt 以进行更深入的理解。
当检查现有的 llms.txt 文件时:
[domain]/llms.txt。[domain]/llms-full.txt。检查每个结构元素:
| 元素 | 检查项 | 缺失时的严重性 |
|---|---|---|
| H1 标题 | 存在,与业务名称匹配 | 严重 |
| 块引用描述 | 存在,少于 200 个字符,实事求是 | 高 |
| 至少一个 H2 部分 | 存在 | 严重 |
| 带 URL 的页面条目 | 至少存在 5 个条目 | 高 |
| URL 是绝对的 | 所有 URL 使用完整的 https:// 路径 | 高 |
| URL 有效 | 所有 URL 返回 200 状态 | 中 |
| 描述存在 | 每个条目在冒号后都有描述 | 中 |
| 关键事实部分 | 存在,包含业务信息 | 中 |
| 联系部分 | 存在,至少包含邮箱 | 低 |
| 合理长度 | 30-200 行 | 低 |
| 无损坏的 Markdown | 整个文件格式正确 | 中 |
从以下维度对 llms.txt 进行评分:
完整性(0-100):
准确性(0-100):
实用性(0-100):
llms.txt 总分 = (完整性 * 0.40) + (准确性 * 0.35) + (实用性 * 0.25)
当从头创建新的 llms.txt 文件时:
<title>、<meta property="og:site_name"> 或 H1)/sitemap.xml 以发现所有公开页面。对所有发现的页面进行分类并选择最重要的页面:
始终包含:
如果质量高则包含:
跳过:
对于每个选定的页面:
好的描述示例:
解释了三个定价层级(免费、专业版、企业版),包含功能对比和年度/月度费用。详细说明了公司于 2018 年成立,拥有 45 名员工,以及在奥斯汀和伦敦的办公地点。涵盖了 Slack、Salesforce 和 HubSpot 的集成设置,包含分步指南和 API 端点。差的描述示例:
我们惊人的定价页面!(营销语言,不具体)了解更多关于我们公司的信息。(太模糊)点击此处查看详情。(没有描述性)从网站收集关键业务事实:
按照此模板构建 llms.txt:
# [网站名称]
> [一句清晰的话:业务是做什么的,为谁服务,以及其主要价值主张。少于 200 个字符。]
## 文档
- [最重要的页面](https://example.com/page):描述涵盖此页面的关键内容。
- [第二个页面](https://example.com/page-2):描述此页面的内容和价值。
- [第三个页面](https://example.com/page-3):用户和 AI 系统将在此处找到什么。
## 产品
- [产品 A](https://example.com/product-a):产品 A 的核心功能、目标用户和定价模式。
- [产品 B](https://example.com/product-b):产品 B 的功能及其与产品 A 的区别。
## 资源
- [指南标题](https://example.com/guide):涵盖 [主题] 的综合指南,包含 [X] 个部分和实际示例。
- [博客文章](https://example.com/blog/post):对 [主题] 的分析,包含来自 [来源] 的原始数据。
## 关键事实
- 成立于 [年份],由 [姓名] 创立
- 总部位于 [城市,国家]
- [具体指标:例如,"为 40 个国家的 10,000+ 家企业提供服务"]
- [关键差异化优势:例如,"唯一提供实时 X 和 Y 集成的平台"]
- 行业:[分类]
## 联系
- 网站:https://example.com
- 邮箱:[主要联系邮箱]
- 支持:[支持 URL 或邮箱]
在输出之前:
生成 GEO-LLMSTXT-ANALYSIS.md:
# llms.txt 分析:[域名]
**分析日期:**[日期]
**llms.txt 状态:**[在 URL 找到 / 未找到 / 错误]
**llms-full.txt 状态:**[找到 / 未找到]
---
## llms.txt 总分:[X]/100
| 维度 | 分数 |
|---|---|
| 完整性 | [X]/100 |
| 准确性 | [X]/100 |
| 实用性 | [X]/100 |
---
## 格式验证
| 元素 | 状态 | 备注 |
|---|---|---|
| H1 标题 | [通过/失败] | [备注] |
| 描述块引用 | [通过/失败] | [备注] |
| H2 部分 | [通过/失败] | [找到 X 个部分] |
| 页面条目 | [通过/失败] | [找到 X 个条目] |
| URL 有效性 | [通过/失败] | [X 个损坏的 URL] |
| 条目描述 | [通过/失败] | [X 个缺失的描述] |
| 关键事实 | [通过/失败] | [备注] |
| 联系部分 | [通过/失败] | [备注] |
---
## 缺失的页面
这些重要页面在网站上找到但未在 llms.txt 中列出:
1. [页面标题](URL) -- [为什么应该包含]
2. [页面标题](URL) -- [为什么应该包含]
## 改进建议
1. [具体建议]
2. [具体建议]
3. [具体建议]
## 建议更新的 llms.txt
[如果需要重大改进,则提供完整的重写后的 llms.txt 文件内容]
输出完整的 llms.txt 文件内容,准备保存到网站的根目录。同时输出一个简短的 GEO-LLMSTXT-GENERATION.md 报告,说明:
https:// URL,切勿使用相对路径。https://yourdomain.com/llms.txt 访问且没有重定向。每周安装次数
71
代码仓库
GitHub 星标数
3.7K
首次出现时间
2026年2月27日
安全审计
安装于
codex70
opencode70
kimi-cli68
gemini-cli68
amp68
cline68
This skill handles everything related to the llms.txt standard -- an emerging convention (proposed by Jeremy Howard in September 2024, gaining adoption through 2025-2026) that allows websites to provide structured guidance to AI systems about their content, structure, and key information. It is analogous to robots.txt (which tells crawlers what NOT to access) but instead tells AI systems what IS most useful to understand about the site.
AI language models face a fundamental challenge when processing websites: they must determine which pages are most important, what the site is about, and how content is organized -- typically by crawling many pages and inferring structure. llms.txt solves this by providing an explicit, machine-readable (and human-readable) summary.
Benefits of having a well-crafted llms.txt:
The file MUST be located at the root of the domain:
https://example.com/llms.txt
The file uses Markdown formatting with specific conventions:
# [Site Name]
> [One-sentence description of what the site/business does. Keep under 200 characters.]
## Docs
- [Page Title](https://example.com/page-url): Concise description of what this page covers and why it matters.
- [Another Page](https://example.com/another-page): Description of content.
## Optional
- [Less Critical Page](https://example.com/optional-page): Description.
1. Title (Required)
# Site Name
#).2. Description (Required)
> Brief description of the site/business
>).3. Main Sections (Required -- at least one)
Use H2 headings (##) to organize pages by category. Common section names:
| Section Name | Purpose | Example Content |
|---|---|---|
## Docs | Primary documentation or key pages | Product pages, service descriptions, core content |
## Optional | Secondary pages worth knowing about | Blog posts, supplementary resources |
## API | API documentation | API reference, authentication guides |
## Blog | Blog or news content | Recent/popular articles |
## Products |
4. Page Entries (Required)
Each entry follows the format:
- [Page Title](URL): Description of page content
Rules for page entries:
5. Key Facts Section (Recommended)
## Key Facts
- Founded in [year] by [founder(s)]
- Headquarters: [City, Country]
- [X] customers/users in [Y] countries
- Key products: [Product A], [Product B], [Product C]
- Industry: [Industry classification]
This section provides quick reference data that AI systems frequently need to answer user queries about your business.
6. Contact Section (Recommended)
## Contact
- Website: https://example.com
- Email: hello@example.com
- Support: support@example.com
- Phone: +1-555-123-4567
- Address: 123 Main St, City, State, ZIP, Country
In addition to llms.txt, sites can provide /llms-full.txt -- an extended version with more detail.
Differences from llms.txt:
| Feature | llms.txt | llms-full.txt |
|---|---|---|
| Length | Concise (50-150 lines) | Comprehensive (150-500+ lines) |
| Page entries | 10-30 key pages | 30-100+ pages |
| Descriptions | 10-30 words per entry | 30-100 words per entry, may include key facts from each page |
| Audience | Quick AI comprehension | Deep AI analysis |
| Sections | 3-6 sections | 8-15 sections |
| Key facts | Business-level facts | Page-level facts and data points |
Both files can coexist. AI systems check for llms.txt first, then may optionally load llms-full.txt for deeper understanding.
When checking an existing llms.txt file:
[domain]/llms.txt.[domain]/llms-full.txt.Check each structural element:
| Element | Check | Severity if Missing |
|---|---|---|
| H1 Title | Present, matches business name | Critical |
| Blockquote description | Present, under 200 chars, factual | High |
| At least one H2 section | Present | Critical |
| Page entries with URLs | At least 5 entries present | High |
| URLs are absolute | All URLs use full https:// paths | High |
| URLs are valid | All URLs return 200 status | Medium |
| Descriptions present | Every entry has a description after the colon | Medium |
| Key Facts section | Present with business information | Medium |
| Contact section | Present with at least email | Low |
Rate the llms.txt on these dimensions:
Completeness (0-100):
Accuracy (0-100):
Usefulness (0-100):
Overall llms.txt Score = (Completeness * 0.40) + (Accuracy * 0.35) + (Usefulness * 0.25)
When creating a new llms.txt file from scratch:
<title>, <meta property="og:site_name">, or H1)/sitemap.xml to discover all public pages.Categorize all discovered pages and select the most important ones:
Always Include:
Include if High Quality:
Skip:
For each selected page:
Good description examples:
Explains the three pricing tiers (Free, Pro, Enterprise) with feature comparison and annual/monthly costs.Details the company's founding in 2018, team of 45 employees, and office locations in Austin and London.Covers integration setup for Slack, Salesforce, and HubSpot with step-by-step guides and API endpoints.Bad description examples:
Our amazing pricing page! (marketing language, no specifics)Learn more about our company. (too vague)Click here for details. (not descriptive)Gather key business facts from the site:
Construct the llms.txt following this template:
# [Site Name]
> [One clear sentence: what the business does, who it serves, and its primary value proposition. Under 200 characters.]
## Docs
- [Most Important Page](https://example.com/page): Description covering the key content on this page.
- [Second Page](https://example.com/page-2): Description of this page's content and value.
- [Third Page](https://example.com/page-3): What users and AI systems will find here.
## Products
- [Product A](https://example.com/product-a): Core features, target users, and pricing model for Product A.
- [Product B](https://example.com/product-b): What Product B does and how it differs from Product A.
## Resources
- [Guide Title](https://example.com/guide): Comprehensive guide covering [topic] with [X] sections and practical examples.
- [Blog Post](https://example.com/blog/post): Analysis of [topic] with original data from [source].
## Key Facts
- Founded in [year] by [name(s)]
- Headquartered in [City, Country]
- [Specific metric: e.g., "Serves 10,000+ businesses in 40 countries"]
- [Key differentiator: e.g., "Only platform offering real-time X and Y integration"]
- Industry: [Classification]
## Contact
- Website: https://example.com
- Email: [primary contact email]
- Support: [support URL or email]
Before outputting:
Generate GEO-LLMSTXT-ANALYSIS.md:
# llms.txt Analysis: [Domain]
**Analysis Date:** [Date]
**llms.txt Status:** [Found at URL / Not Found / Error]
**llms-full.txt Status:** [Found / Not Found]
---
## Overall llms.txt Score: [X]/100
| Dimension | Score |
|---|---|
| Completeness | [X]/100 |
| Accuracy | [X]/100 |
| Usefulness | [X]/100 |
---
## Format Validation
| Element | Status | Notes |
|---|---|---|
| H1 Title | [Pass/Fail] | [Notes] |
| Description blockquote | [Pass/Fail] | [Notes] |
| H2 Sections | [Pass/Fail] | [X sections found] |
| Page entries | [Pass/Fail] | [X entries found] |
| URL validity | [Pass/Fail] | [X broken URLs] |
| Entry descriptions | [Pass/Fail] | [X missing descriptions] |
| Key Facts | [Pass/Fail] | [Notes] |
| Contact section | [Pass/Fail] | [Notes] |
---
## Missing Pages
These important pages were found on the site but not in llms.txt:
1. [Page Title](URL) -- [Why it should be included]
2. [Page Title](URL) -- [Why it should be included]
## Improvement Recommendations
1. [Specific recommendation]
2. [Specific recommendation]
3. [Specific recommendation]
## Suggested Updated llms.txt
[Complete rewritten llms.txt file if significant improvements are needed]
Output the complete llms.txt file content, ready to be saved to the site's root directory. Also output a brief GEO-LLMSTXT-GENERATION.md report explaining:
https:// URL, never relative paths.https://yourdomain.com/llms.txt with no redirects.Weekly Installs
71
Repository
GitHub Stars
3.7K
First Seen
Feb 27, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykWarn
Installed on
codex70
opencode70
kimi-cli68
gemini-cli68
amp68
cline68
超能力技能使用指南:AI助手技能调用优先级与工作流程详解
52,100 周安装
| Product catalog |
| Product pages, pricing |
## Services | Service offerings | Service descriptions, process pages |
## About | Company information | About page, team, mission |
## Resources | Educational/reference content | Guides, tutorials, whitepapers |
## Legal | Legal documents | Terms of service, privacy policy |
## Contact | Contact information | Contact page, support channels |
| Reasonable length | 30-200 lines | Low |
| No broken Markdown | Proper formatting throughout | Medium |