Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add jrr996shujin-png/openclaw-seo-aeo-skills --skill site-architecturegit clone --depth 1 https://github.com/jrr996shujin-png/openclaw-seo-aeo-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/jrr996shujin-png/openclaw-seo-aeo-skills/site-architecture)<a href="https://agentmods.dev/skills/jrr996shujin-png/openclaw-seo-aeo-skills/site-architecture"><img src="https://agentmods.dev/badge/skills/jrr996shujin-png/openclaw-seo-aeo-skills/site-architecture/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/jrr996shujin-png/openclaw-seo-aeo-skills/site-architecture"><img src="https://agentmods.dev/badge/skills/jrr996shujin-png/openclaw-seo-aeo-skills/site-architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00083 | $0.01336 |
| Opus 5.5 | $0.00033 | $0.00534 |
| Sonnet 5.5 | $0.00017 | $0.00267 |
| Haiku 4.5 | $0.00008 | $0.00134 |
Grade A, and why
seo-site-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
站内架构诊断模块
本模块负责检查网站的内部链接结构和页面可达性,满分 10 分。站内架构就像一栋建筑的动线——好的动线让每个房间都容易到达,好的站内架构让每个页面都容易被搜索引擎发现。
检查项
1. 内部链接健康度(5 分)
检查方法:
- 从目标页面提取所有内部链接(同域名下的链接)
- 分析:
- 内部链接总数
- 唯一内部链接数(去重)
- 链接锚文本质量:
- 描述性锚文本("查看我们的 SEO 服务" ✅)
- 通用锚文本("点击这里""了解更多" ⚠️)
- 裸 URL 锚文本(❌)
- 空锚文本或纯图片链接无 alt(❌)
- 导航链接 vs 正文内链接的比例
- 是否有指向自身的链接(自链接)
- 检查链接分布:
- 是否集中在导航/页脚(模板链接)
- 正文中是否有上下文相关的内链(更有价值)
- 是否有"相关文章""推荐阅读"等模块
评分:
- 5 分:内链丰富(> 10 个唯一内链)+ 锚文本描述性强 + 正文有上下文内链
- 3 分:内链数量尚可但锚文本质量一般,或多为模板链接
- 1 分:内链很少或锚文本质量差
- 0 分:几乎无内部链接(孤岛页面)
输出格式:
状态:✅/⚠️/❌
内部链接总数:X 个(唯一:Y 个)
链接来源分布:
- 导航/页头:X 个
- 正文内链:X 个
- 侧边栏/推荐:X 个
- 页脚:X 个
锚文本质量:
| 类型 | 数量 | 占比 | 示例 |
|------|------|------|------|
| 描述性 | X | X% | "SEO 优化指南" |
| 通用性 | X | X% | "点击这里" |
| 裸 URL | X | X% | "https://..." |
| 空/无文本 | X | X% | [图片链接] |
上下文内链:有/无(X 处)
相关推荐模块:有/无
修复建议:(具体建议)
2. 核心页面点击深度(5 分)
点击深度指从首页到达目标页面所需的最少点击次数。搜索引擎和 AI 引擎通常认为深度越浅的页面越重要,3 次点击内可达是理想状态。
检查方法:
- 如果诊断的是首页:
- 提取首页所有链接
- 对关键页面(由链接的位置和文本判断重要性)追踪深度
- 列出首页直达的页面(深度 1)
- 抽样检查深度 2 的页面
- 如果诊断的是具体页面:
- 从首页出发,检查是否能在 3 次点击内到达
- 检查面包屑导航(
<nav>中带有 BreadcrumbList 特征的结构) - 推断页面在网站层级中的位置
- 通用检查:
- 面包屑导航是否存在
- 面包屑层级数(反映网站深度)
- 面包屑是否有 Schema 标记
- URL 路径深度(斜杠数量作为参考信号)
评分:
- 5 分:关键页面 ≤ 3 次点击可达 + 面包屑导航完善 + URL 结构清晰
- 3 分:大部分页面可达但缺少面包屑或有些页面过深
- 1 分:页面深度过深(> 4 次点击)或缺少面包屑导航
- 0 分:无法确定页面可达性,且无面包屑、URL 结构混乱
输出格式:
状态:✅/⚠️/❌
URL 路径深度:X 层(/segment1/segment2/.../pageX)
面包屑导航:有/无
面包屑层级:首页 > [类别] > [子类别] > [当前页]
面包屑 Schema:有/无
从首页点击深度:约 X 次(推断)
网站层级概览(基于链接分析):
深度 0(首页):1 页
深度 1:~X 页(导航直达)
深度 2:~X 页
深度 3+:~X 页
修复建议:(具体建议,如添加面包屑、调整导航结构等)
汇总输出
## 站内架构 — 得分 X/10
| 检查项 | 得分 | 状态 |
|--------|------|------|
| 内部链接健康度 | X/5 | ✅/⚠️/❌ |
| 核心页面点击深度 | X/5 | ✅/⚠️/❌ |
关键发现:(1-2 句总结)
架构优化建议:(改善内容发现和爬取效率的关键建议)
优先修复:(最重要的 1-2 项)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 118 lines · 83 tokens per session scan A 1d2e154de7cf
seo-site-architecture is a skill published in the GitHub repository jrr996shujin-png/openclaw-seo-aeo-skills (13 stars, last pushed 8mo ago), licensed MIT. It adds 83 tokens to every session and 1,336 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
seo-site-architecture compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| seo-site-architecturejrr996shujin-png/openclaw-seo-aeo-skills | Skill | 13 | 8mo ago | MIT | A | 83 | Claude Code, Codex |
| ansvisor-aeo-coach-standaloneansvisor/ansvisor | Skill | 232 | yesterday | MIT | A | 148 | Claude Code, Codex |
| ansvisor-aeo-coachansvisor/ansvisor | Skill | 232 | yesterday | MIT | A | 241 | Claude Code, Codex |
| aeroCanonry/canonry | Skill | 198 | yesterday | MIT | A | 93 | Claude Code |
| canonryCanonry/canonry | Skill | 198 | yesterday | MIT | A | 64 | Claude Code |
| promptsansvisor/ansvisor | Skill | 232 | yesterday | MIT | A | 25 | Claude Code, Codex |
| fanoutansvisor/ansvisor | Skill | 232 | yesterday | MIT | A | 23 | Claude Code, Codex |