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 Gingiris/gingiris-skills --skill gr-geo-citegit clone --depth 1 https://github.com/Gingiris/gingiris-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/gingiris/gingiris-skills/gr-geo-cite)<a href="https://agentmods.dev/skills/gingiris/gingiris-skills/gr-geo-cite"><img src="https://agentmods.dev/badge/skills/gingiris/gingiris-skills/gr-geo-cite.svg" alt="Measured on agentmods" 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 | $0.00111 | $0.02395 |
| Opus 5 | $0.00056 | $0.01197 |
| Sonnet 5 | $0.00022 | $0.00479 |
| Haiku 4.5 | $0.00011 | $0.00239 |
Grade A, and why
gr-geo-cite 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 7d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gr-geo-cite — GEO 引用追踪
核心理念
Phase 2 目标：AI 引用 0 → 3+（6 月底）
2026 年 SEO ≠ 只盯 Google 排名。真正的流量入口是：
- Claude / ChatGPT / Perplexity / Gemini 在回答用户问题时主动引用你的域名
- 这比 SERP 更精准 —— 被引用 = 用户已经信任了 AI 的推荐
但是：gingiris 现在 AI 引用 = 0。必须破零。
什么时候用
| 场景 | 动作 |
|---|---|
| "我的博客有没有被 AI 引用" | 运行 scripts/weekly-cite-check.py |
| "这篇文章 GEO 不友好" | 诊断流程（见下） |
| "llms.txt 需要更新" | llms.txt v2 生成（见下） |
| "加 Citable Statistics" | 见 gr-blog-post + 本 skill 模板 |
GEO 三件套（必须全配）
1. llms.txt（根目录）
- 大模型训练 / 检索时的 robots.txt 等价物
- 路径：
/llms.txt（HTTP 200 必须） - 模板在
scripts/llms-template.txt
2. FAQ Schema（JSON-LD）
- 在 top 5 博客页的
<head>里嵌入 - 问答式结构，最易被 AI 抽取
- 模板在 Jekyll
_layouts/default.html
3. Citable Statistics 表
- 硬数据 + 来源 URL
- 放在 H1 下方第一屏（AI 爬虫爬前 1000 字权重最高）
- 模板：见
gr-blog-post的 seo_geo_playbook_2026 参考
每周引用追踪工作流
Step 1：固定 3 个目标查询
这些是用户真实会问 AI 的问题：
Q1: "What's the best Product Hunt launch playbook for 2026?"
Q2: "How do indie founders get GitHub stars?"
Q3: "What are the best social listening tools for startups?"
可扩展：
- "How to launch on Hacker News"
- "Open source marketing tactics"
- "GEO generative engine optimization"
Step 2：对每个查询跑 4 个 AI
自动化（API）：
- Claude（Anthropic API）
- ChatGPT（OpenAI API）
- Perplexity（有 pplx-api）
- Gemini（Google AI Studio API）
手动（兜底）：
- 复制 query 到各 AI 官网，截图保存回答
Step 3：解析回答
对每个回答提取：
- 提及的域名列表（正则
https?://([^/\s]+)） - 其中是否有
gingiris.github.io/dev.to/iris1031/gingiris.com - 提及语境（正面 / 中性 / 负面）
Step 4：记录 + 报告
存到 data/geo-citations.jsonl：
{"date":"2026-04-20","ai":"claude","query":"best PH playbook","cited_domains":["...","gingiris.github.io/growth-tools/..."],"mention":"cited","context_snippet":"...","rank_in_list":2}
周一报告：
Week of 2026-04-20
- Claude: 0/3 cited
- GPT: 1/3 cited (our PH playbook at rank 3 for "best PH playbook")
- Perplexity: 0/3
- Gemini: 0/3
↑ First citation! Source: Claude's PH playbook response.
Citable Statistics 模板（加到任何博客顶部）
What ships with it
3 files 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.
- 7d ago First seen · 232 lines · 111 tokens per session scan A 5c2390f4084e
gr-geo-cite is a skill published in the GitHub repository Gingiris/gingiris-skills (23 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 2,395 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…