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-1031/gingiris-skills --skill gr-geo-citegit clone --depth 1 https://github.com/Gingiris-1031/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-1031/gingiris-skills/gr-geo-cite)<a href="https://agentmods.dev/skills/gingiris-1031/gingiris-skills/gr-geo-cite"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-geo-cite/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/gingiris-1031/gingiris-skills/gr-geo-cite"><img src="https://agentmods.dev/badge/skills/gingiris-1031/gingiris-skills/gr-geo-cite.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00188 | $0.04024 |
| Opus 5 | $0.00094 | $0.02012 |
| Sonnet 5 | $0.00038 | $0.00805 |
| Haiku 4.5 | $0.00019 | $0.00402 |
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 10d 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 — 290 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚠️ 2C 产品的 GEO 调整
本 skill 默认 B2B/开源场景。2C 消费品 / 教育 / 应用 做 GEO 时按下表调整：
| 维度 | 默认 | 2C 建议 |
|---|---|---|
| 固定查询选题 | 产品类目词 | 用户真实提问句（"2026 托福口语怎么练" 而非 "best X tool"） |
| Citable Stats 来源 | 行业/产品数据 | 权威机构/官方（考试局/政府/平台财报），YMYL 品类准确性是命门 |
| FAQ 问题 | "Why is X best" | 考生/用户真实搜索句 |
| 被引用后动作 | "As cited by" 角标 | 同左 + 强化作者资质（YMYL E-E-A-T，Google：Trust 是核心） |
完整 2C 指南 + 公开数据来源见 → gingiris-seo-geo/references/2c-adaptation.md
gr-geo-cite — GEO 引用追踪
核心理念
目标 = 当前基线 + 滚动目标：不设固定 deadline 数字（旧"6 月底 0→3+"已过期）。每周对照 memory seo_tracker_baseline.md 里的最新引用基线，滚动目标 = 本周引用数 ≥ 上周，破零后转为"稳定引用的固定查询数 +1/月"。
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
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 四件套（2026-06-24 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） - 模板见本文下方「llms.txt v2 模板」节
2. FAQ Schema（JSON-LD）
- FAQPage JSON-LD，5–8 题（不少于 5 题，AI 爬虫抽取阈值）
- 在 top 5 博客页的
<head>里嵌入 - 问题必须是用户真实搜索句，不是营销话术（"Why is X the best?" ❌ → "How do I X?" ✅）
- 模板在 Jekyll
_layouts/default.html
3. Citable Statistics 表
- 硬数据 + 来源 URL（每行必须有数字 + 来源）
- 放在 H1 下方第一屏（AI 爬虫爬前 1000 字权重最高）
- 5–10 行，TL;DR 段必须是完整句
- 模板：见
gr-blog-post的 seo_geo_playbook_2026 参考
4. Bing IndexNow + AI 友好格式（2026 新增）
- 内容更新后立即 Bing IndexNow 推送（让大模型比 Google 爬虫更快 discover/index）
- AI 友好格式：一句话直接答 + 对比表格 + FAQ（三件套缺一不可）
- GA4 AI 来源流量监控：配置 ChatGPT/Perplexity/Claude referral channel grouping
- 最后更新日期：每次更新后显示（AI 爬虫 freshness 信号）
每周引用追踪工作流
Step 1：固定查询集（两组，随周检一起跑）
这些是用户真实会问 AI 的问题：
gingiris 组（检测 gingiris.tools / dev.to/iris1031）：
G1: "What's the best Product Hunt launch playbook for 2026?"
G2: "How do indie founders get GitHub stars?"
G3: "What are the best social listening tools for startups?"
What ships with it
7 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.
- gr-geo-cite/scripts/citability-scorer.py 12 KB runs code
- gr-geo-cite/scripts/llms-txt-gen.py 5.2 KB runs code
- gr-geo-cite/scripts/weekly-cite-check.py 6.1 KB runs code
- gr-geo-cite/SKILL.md 13 KB
- scripts/citability-scorer.py 12 KB runs code
- scripts/llms-txt-gen.py 5.2 KB runs code
- scripts/weekly-cite-check.py 6.1 KB runs code
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.
- 10d ago First seen · 290 lines · 188 tokens per session scan A 334dcb701db4
gr-geo-cite is a skill published in the GitHub repository Gingiris-1031/gingiris-skills (79 stars, last pushed 5d ago), licensed MIT. It adds 188 tokens to every session and 4,024 once invoked, about $0.0009 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
synthesis-explore
Synthesis EXPLORE stage for the Diffmode growth-tactics pipeline (fuses the blind-combination draw + emergent-mechanism derivation — formerly two separate synthesis steps — into ONE structural-check-only stage). Reads the per-run growth-factors.json (LIGHT vector DB) + synthesis-constraints.json + founder-input +…
growth-factors-mining
Builds a per-run LIGHT growth-vector database for the Diffmode growth-tactics pipeline by mining public growth case studies fresh, every run, and distilling each into atomic "growth factors" (transferable mechanisms). Clean-room — NEVER reads the proprietary tacticsDB. Outputs growth-factors.json (20-40 vectors spread…
diagnostics-intake
Fast founder-input capture for the Diffmode growth-tactics pipeline (the diagnostics stage). Produces WS/01-diagnostics/founder-input.md in the exact schema the enrichment + synthesis stages read. Two modes — (A) URL mode researches a product's website (homepage/pricing/about) plus a web-research pass to prefill the…
lite-constraints
Generates synthesis-constraints.json for the Diffmode growth-tactics pipeline by reasoning in-context over the per-run growth-factors.json (LIGHT vector DB) + founder context — the clean-room, no-Python replacement for the proprietary Python constraints generator. Emits the white-space pairs, mandatory…
conversion-audit
Use this skill to run a scored 53-point conversion audit covering customer focus, narrative, copy, design, calls to action, and proof. Trigger it when a landing, sales, product, or ad destination page needs diagnosis, pre-launch review, or prioritized conversion fixes.
channel-discovery
Use this skill to identify and score acquisition channels by audience fit, speed, cost, effort, and learning value, then recommend the top three. Trigger it when choosing where to reach a defined audience, planning go-to-market, or replacing an underperforming channel.