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 lm203688/aishield --skill chinese-seo-compliancegit clone --depth 1 https://github.com/lm203688/aishieldWrote 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/lm203688/aishield/chinese-seo-compliance)<a href="https://agentmods.dev/skills/lm203688/aishield/chinese-seo-compliance"><img src="https://agentmods.dev/badge/skills/lm203688/aishield/chinese-seo-compliance/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/lm203688/aishield/chinese-seo-compliance"><img src="https://agentmods.dev/badge/skills/lm203688/aishield/chinese-seo-compliance.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 | $0.00088 | $0.01461 |
| Opus 5 | $0.00044 | $0.00731 |
| Sonnet 5 | $0.00018 | $0.00292 |
| Haiku 4.5 | $0.00009 | $0.00146 |
Grade A, and why
chinese-seo-compliance 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
中文站点 SEO / GEO 合规检查
给中文站点做一次可复核的合规体检，覆盖三层：搜索引擎收录合规、中国大陆法规合规、AI Agent 可见性（GEO）。全部检查项都能用只读方式验证，不需要改动线上站点。
何时使用
- 用户说"我的站百度不收录 / 收录掉了 / 索引量下降"
- 用户要上线一个面向中国大陆用户的站点，需要备案与合规声明自查
- 用户希望站点被 ChatGPT、Claude、Perplexity 等 AI 检索到并正确引用
- 用户要做多站点批量体检，需要一份可对比的结论表
工作流程
按顺序做四步，每步产出可核对的事实，不要跳步下结论。
第 1 步：抓取事实（只读）
对目标域名收集以下原始信息，不要凭记忆回答：
| 项目 | 获取方式 |
|---|---|
| DNS 解析与 CDN | 对域名做 A / CNAME 查询 |
| HTTP 状态与跳转链 | 请求首页，记录完整 301/302 链路 |
robots.txt |
读取 /robots.txt |
| 站点地图 | 读取 robots.txt 声明的 sitemap 及 /sitemap.xml |
llms.txt |
读取 /llms.txt |
| Agent Card | 读取 /.well-known/agent-card.json |
| 首页 HTML head | 取 title、description、canonical、hreflang、结构化数据 |
事实缺失时明确写"未获取到"，不要用推测填空。
第 2 步：搜索引擎收录合规
- robots.txt 是否误封中文搜索引擎：
Baiduspider、Sogou web spider、YisouSpider、360Spider是否被Disallow: / - 移动端适配：是否有
viewport，是否响应式或有独立 m 站并做了rel=alternate声明 - 站点地图：是否可访问、条目数是否与实际页面量级一致、
lastmod是否真实更新 - 标题与描述：title 是否 ≤ 30 个汉字、description 是否 ≤ 78 个汉字，是否有大批量重复
- 中文分词友好：核心词是否以完整词组出现在 title 前段，避免关键词堆砌
- canonical：是否自指或指向正确主版本，避免带参 URL 分散权重
- HTTPS 与速度：证书是否有效、首屏是否受阻塞资源拖累
第 3 步：中国大陆法规合规
- ICP 备案号：页脚是否展示，是否与工信部备案信息一致，是否链接到
beian.miit.gov.cn - 公安联网备案：如适用，页脚是否展示公安备案号
- 隐私政策与用户协议：是否可访问，是否说明收集的个人信息范围
- Cookie 与埋点告知：是否有明确告知
- 内容合规：涉及医疗、金融、教育等特殊行业时，是否具备对应资质展示
- 地图与地域表述：涉及地图或地域名称时，需符合中国法律法规的表述要求
法规项只做"是否存在、是否可核验"的事实判断，不替用户下法律结论，建议其咨询专业意见。
第 4 步：AI 可见性（GEO）
这是多数中文站点的空白项，也是当前最大的增量。
llms.txt：是否存在，是否用简明结构说明站点是做什么的、有哪些关键入口/.well-known/agent-card.json：是否声明可被 Agent 调用的能力与端点- robots.txt 对 AI 爬虫的态度：
GPTBot、ClaudeBot、PerplexityBot、Google-Extended是允许还是封禁——要和用户的意图一致，很多站点是"无意中封了" - 结构化数据：是否有 JSON-LD（Organization / Article / FAQPage / BreadcrumbList），字段是否与页面可见内容一致
- 内容可提取性：正文是否服务端渲染，纯前端渲染的内容大多数 AI 爬虫读不到
- 事实密度：页面是否给出可被引用的具体数字、日期、定义，而不是空泛描述
输出格式
产出一张结论表，每行一个检查项：
| 层 | 检查项 | 结论 | 证据 | 建议 |
|---|---|---|---|---|
| 收录 | robots 未封百度 | 通过 | robots.txt 第 3 行 | — |
| 法规 | ICP 备案号展示 | 缺失 | 页脚未见备案号 | 页脚补备案号并链接工信部 |
| GEO | llms.txt | 缺失 | /llms.txt 返回 404 | 新增 llms.txt |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 95 lines · 88 tokens per session scan A 0087836c789f
chinese-seo-compliance is a skill published in the GitHub repository lm203688/aishield (2 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,461 once invoked, about $0.0004 per session on Opus 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.
Other skills, from other repositories
clinical-trial-protocol-skill
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
prior-auth-review-skill
Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization…
epo-patent-analyzer
Automated analysis of patent applications for EPO compliance with Art. 84 EPC (claims clarity/support), Art. 83 EPC (sufficiency of disclosure), and Rules 42-49 EPC (formalities).
prior-art-search
Systematic 7-step methodology for comprehensive patent prior art searches and patentability assessments using BigQuery and CPC classification.
patent-reviewer
Expert system for reviewing utility patent applications against USPTO MPEP guidelines.
mpep-search
Expert system for searching USPTO MPEP, 35 USC statutes, 37 CFR regulations, and post-Jan 2024 updates.