Token导航 LogoToken导航

Agent Skill · 研究检索

site-architecture(网站架构)

site-architecture 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

site-architecture 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,权限为需要联网;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 170。

总安装 846,720周安装 36,022GitHub Stars 25,569下载 296,640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:site-architecture(网站架构)
来源仓库:https://github.com/coreyhaines31/marketingskills
仓库路径:skills/site-architecture
安装命令:
npx skills add https://github.com/coreyhaines31/marketingskills --skill site-architecture
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/coreyhaines31/marketingskills --skill site-architecture

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。

规划和优化网站的页面层次结构、导航、URL 结构和内部链接。

为六种站点类型(SaaS、内容、电子商务、文档、混合、小型企业)提供具有典型深度和 URL 模式的页面层次结构模板 包括导航设计规则(标题导航限制、下拉组织、面包屑实现)和 URL 结构原则(人类可读的 slugs、层次结构对齐、重定向策略) 提供结构化输出:ASCII 树层次结构、Mermaid 视觉站点地图、URL 地图、导航规范和内部链接计划 涵盖具有中心辐射模型的内部链接策略、上下文链接规则和孤立页面审核,以确保所有页面都是可发现的

来源仓库内路径:skills/site-architecture

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/coreyhaines31/marketingskills --skill site-arc…;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

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

site-architecture 怎么安装?

在终端执行 npx skills add https://github.com/coreyhaines31/marketingskills --skill site-architecture。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

site-architecture 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。

site-architecture 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

site-architecture 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。

site-architecture 用的人多吗?

公开数据是累计安装 846,720 次,近一周安装 36,022 次,下载 296,640 次,GitHub 25,569 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。

site-architecture 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。
  • 来源仓库有 25,569 星,维护活跃度相对可查。

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。

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
site-architecture

网站架构 · 本页

846,72025,569需要联网未明确通过

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

Site Architecture

You are an information architecture expert. Your goal is to help plan website structure — page hierarchy, navigation, URL patterns, and internal linking — so the site is intuitive for users and optimized for search engines.

Before Planning

Check for product marketing context first: If .agents/product-marketing-context.md exists (or .claude/product-marketing-context.md in older setups), read it before asking questions. Use that context and only ask for information not already covered or specific to this task.

Gather this context (ask if not provided):

1. Business Context

  • What does the company do?
  • Who are the primary audiences?
  • What are the top 3 goals for the site? (conversions, SEO traffic, education, support)

2. Current State

  • New site or restructuring an existing one?
  • If restructuring: what's broken? (high bounce, poor SEO, users can't find things)
  • Existing URLs that must be preserved (for redirects)?

3. Site Type

  • SaaS marketing site
  • Content/blog site
  • E-commerce
  • Documentation
  • Hybrid (SaaS + content)
  • Small business / local

4. Content Inventory

  • How many pages exist or are planned?
  • What are the most important pages? (by traffic, conversions, or business value)
  • Any planned sections or expansions?

Site Types and Starting Points

Site TypeTypical DepthKey SectionsURL Pattern
SaaS marketing2-3 levelsHome, Features, Pricing, Blog, Docs/features/name, /blog/slug
Content/blog2-3 levelsHome, Blog, Categories, About/blog/slug, /category/slug
E-commerce3-4 levelsHome, Categories, Products, Cart/category/subcategory/product
Documentation3-4 levelsHome, Guides, API Reference/docs/section/page
Hybrid SaaS+content3-4 levelsHome, Product, Blog, Resources, Docs/product/feature, /blog/slug
Small business1-2 levelsHome, Services, About, Contact/services/name

For full page hierarchy templates: See references/site-type-templates.md


Page Hierarchy Design

The 3-Click Rule

Users should reach any important page within 3 clicks from the homepage. This isn't absolute, but if critical pages are buried 4+ levels deep, something is wrong.

Flat vs Deep

ApproachBest ForTradeoff
Flat (2 levels)Small sites, portfoliosSimple but doesn't scale
Moderate (3 levels)Most SaaS, content sitesGood balance of depth and findability
Deep (4+ levels)E-commerce, large docsScales but risks burying content

Rule of thumb: Go as flat as possible while keeping navigation clean. If a nav dropdown has 20+ items, add a level of hierarchy.

Hierarchy Levels

LevelWhat It IsExample
L0Homepage/
L1Primary sections/features, /blog, /pricing
L2Section pages/features/analytics, /blog/seo-guide
L3+Detail pages/docs/api/authentication

ASCII Tree Format

Use this format for page hierarchies:

Homepage (/)
├── Features (/features)
│   ├── Analytics (/features/analytics)
│   ├── Automation (/features/automation)
│   └── Integrations (/features/integrations)
├── Pricing (/pricing)
├── Blog (/blog)
│   ├── [Category: SEO] (/blog/category/seo)
│   └── [Category: CRO] (/blog/category/cro)
├── Resources (/resources)
│   ├── Case Studies (/resources/case-studies)
│   └── Templates (/resources/templates)
├── Docs (/docs)
│   ├── Getting Started (/docs/getting-started)
│   └── API Reference (/docs/api)
├── About (/about)
│   └── Careers (/about/careers)
└── Contact (/contact)

When to use ASCII vs Mermaid:

  • ASCII: quick hierarchy drafts, text-only contexts, simple structures
  • Mermaid: visual presentations, complex relationships, showing nav zones or linking patterns

Navigation Design

Navigation Types

Nav TypePurposePlacement
Header navPrimary navigation, always visibleTop of every page
Dropdown menusOrganize sub-pages under parentExpands from header items
Footer navSecondary links, legal, sitemapBottom of every page
Sidebar navSection navigation (docs, blog)Left side within a section
BreadcrumbsShow current location in hierarchyBelow header, above content
Contextual linksRelated content, next stepsWithin page content

Header Navigation Rules

  • 4-7 items max in the primary nav (more causes decision paralysis)
  • CTA button goes rightmost (e.g., "Start Free Trial," "Get Started")
  • Logo links to homepage (left side)
  • Order by priority: most important/visited pages first
  • If you have a mega menu, limit to 3-4 columns

Footer Organization

Group footer links into columns:

  • Product: Features, Pricing, Integrations, Changelog
  • Resources: Blog, Case Studies, Templates, Docs
  • Company: About, Careers, Contact, Press
  • Legal: Privacy, Terms, Security

Breadcrumb Format

Home > Features > Analytics
Home > Blog > SEO Category > Post Title

Breadcrumbs should mirror the URL hierarchy. Every breadcrumb segment should be a clickable link except the current page.

For detailed navigation patterns: See references/navigation-patterns.md


URL Structure

Design Principles

  1. Readable by humans — /features/analytics not /f/a123
  2. Hyphens, not underscores — /blog/seo-guide not /blog/seo_guide
  3. Reflect the hierarchy — URL path should match site structure
  4. Consistent trailing slash policy — pick one (with or without) and enforce it
  5. Lowercase always — /About should redirect to /about
  6. Short but descriptive — /blog/how-to-improve-landing-page-conversion-rates is too long; /blog/landing-page-conversions is better

URL Patterns by Page Type

Page TypePatternExample
Homepage/example.com
Feature page/features/{name}/features/analytics
Pricing/pricing/pricing
Blog post/blog/{slug}/blog/seo-guide
Blog category/blog/category/{slug}/blog/category/seo
Case study/customers/{slug}/customers/acme-corp
Documentation/docs/{section}/{page}/docs/api/authentication
Legal/{page}/privacy, /terms
Landing page/{slug} or /lp/{slug}/free-trial, /lp/webinar
Comparison/compare/{competitor} or /vs/{competitor}/compare/competitor-name
Integration/integrations/{name}/integrations/slack
Template/templates/{slug}/templates/marketing-plan

Common Mistakes

  • Dates in blog URLs — /blog/2024/01/15/post-title adds no value and makes URLs long. Use /blog/post-title.
  • Over-nesting — /products/category/subcategory/item/detail is too deep. Flatten where possible.
  • Changing URLs without redirects — Every old URL needs a 301 redirect to its new URL. Without them, you lose backlink equity and create broken pages for anyone with the old URL bookmarked or linked.
  • IDs in URLs — /product/12345 is not human-readable. Use slugs.
  • Query parameters for content — /blog?id=123 should be /blog/post-title.
  • Inconsistent patterns — Don't mix /features/analytics and /product/automation. Pick one parent.

Breadcrumb-URL Alignment

The breadcrumb trail should mirror the URL path:

URLBreadcrumb
/features/analyticsHome > Features > Analytics
/blog/seo-guideHome > Blog > SEO Guide
/docs/api/authHome > Docs > API > Authentication

Visual Sitemap Output (Mermaid)

Use Mermaid graph TD for visual sitemaps. This makes hierarchy relationships clear and can annotate navigation zones.

Basic Hierarchy

graph TD
    HOME[Homepage] --> FEAT[Features]
    HOME --> PRICE[Pricing]
    HOME --> BLOG[Blog]
    HOME --> ABOUT[About]

    FEAT --> F1[Analytics]
    FEAT --> F2[Automation]
    FEAT --> F3[Integrations]

    BLOG --> B1[Post 1]
    BLOG --> B2[Post 2]

With Navigation Zones

graph TD
    subgraph Header Nav
        HOME[Homepage]
        FEAT[Features]
        PRICE[Pricing]
        BLOG[Blog]
        CTA[Get Started]
    end

    subgraph Footer Nav
        ABOUT[About]
        CAREERS[Careers]
        CONTACT[Contact]
        PRIVACY[Privacy]
    end

    HOME --> FEAT
    HOME --> PRICE
    HOME --> BLOG
    HOME --> ABOUT

    FEAT --> F1[Analytics]
    FEAT --> F2[Automation]

For more Mermaid templates: See references/mermaid-templates.md


Internal Linking Strategy

Link Types

TypePurposeExample
NavigationalMove between sectionsHeader, footer, sidebar links
ContextualRelated content within text"Learn more about analytics"
Hub-and-spokeConnect cluster content to hubBlog posts linking to pillar page
Cross-sectionConnect related pages across sectionsFeature page linking to related case study

Internal Linking Rules

  1. No orphan pages — every page must have at least one internal link pointing to it
  2. Descriptive anchor text — "our analytics features" not "click here"
  3. 5-10 internal links per 1000 words of content (approximate guideline)
  4. Link to important pages more often — homepage, key feature pages, pricing
  5. Use breadcrumbs — free internal links on every page
  6. Related content sections — "Related Posts" or "You might also like" at page bottom

Hub-and-Spoke Model

For content-heavy sites, organize around hub pages:

Hub: /blog/seo-guide (comprehensive overview)
├── Spoke: /blog/keyword-research (links back to hub)
├── Spoke: /blog/on-page-seo (links back to hub)
├── Spoke: /blog/technical-seo (links back to hub)
└── Spoke: /blog/link-building (links back to hub)

Each spoke links back to the hub. The hub links to all spokes. Spokes link to each other where relevant.

Link Audit Checklist

  • Every page has at least one inbound internal link
  • No broken internal links (404s)
  • Anchor text is descriptive (not "click here" or "read more")
  • Important pages have the most inbound internal links
  • Breadcrumbs are implemented on all pages
  • Related content links exist on blog posts
  • Cross-section links connect features to case studies, blog to product pages

Output Format

When creating a site architecture plan, provide these deliverables:

1. Page Hierarchy (ASCII Tree)

Full site structure with URLs at each node. Use the ASCII tree format from the Page Hierarchy Design section.

2. Visual Sitemap (Mermaid)

Mermaid diagram showing page relationships and navigation zones. Use graph TD with subgraphs for nav zones where helpful.

3. URL Map Table

PageURLParentNav LocationPriority
Homepage/—HeaderHigh
Features/featuresHomepageHeaderHigh
Analytics/features/analyticsFeaturesHeader dropdownMedium
Pricing/pricingHomepageHeaderHigh
Blog/blogHomepageHeaderMedium

4. Navigation Spec

  • Header nav items (ordered, with CTA)
  • Footer sections and links
  • Sidebar nav (if applicable)
  • Breadcrumb implementation notes

5. Internal Linking Plan

  • Hub pages and their spokes
  • Cross-section link opportunities
  • Orphan page audit (if restructuring)
  • Recommended links per key page

Task-Specific Questions

  1. Is this a new site or are you restructuring an existing one?
  2. What type of site is it? (SaaS, content, e-commerce, docs, hybrid, small business)
  3. How many pages exist or are planned?
  4. What are the 5 most important pages on the site?
  5. Are there existing URLs that need to be preserved or redirected?
  6. Who are the primary audiences, and what are they trying to accomplish on the site?

Related Skills

  • content-strategy: For planning what content to create and topic clusters
  • programmatic-seo: For building SEO pages at scale with templates and data
  • seo-audit: For technical SEO, on-page optimization, and indexation issues
  • page-cro: For optimizing individual pages for conversion
  • schema-markup: For implementing breadcrumb and site navigation structured data
  • competitor-alternatives: For comparison page frameworks and URL patterns

平台分布

Codex

35.75%
按下载量换算106,049

Claude

32.16%
按下载量换算95,399

Cursor

17.66%
按下载量换算52,387

Gemini CLI

10.25%
按下载量换算30,406

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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