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 yaojingang/yao-geo-skills --skill yao-geo-ranking-article-buildergit clone --depth 1 https://github.com/yaojingang/yao-geo-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/yaojingang/yao-geo-skills/yao-geo-ranking-article-builder)<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-ranking-article-builder"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-ranking-article-builder/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/yaojingang/yao-geo-skills/yao-geo-ranking-article-builder"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-ranking-article-builder.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 | $0.00134 | $0.01570 |
| Opus 5 | $0.00067 | $0.00785 |
| Sonnet 5 | $0.00027 | $0.00314 |
| Haiku 4.5 | $0.00013 | $0.00157 |
Grade A, and why
yao-geo-ranking-article-builder 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 12d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yao GEO Ranking Article Builder
使用边界
用于把品牌 Brief、选题配置、关键词、竞品库、行业资料和可信来源转成可追溯的 GEO 榜单评测文章，并输出 Markdown、HTML、PDF、Word 四格式文章包。适合 CRM、SaaS、消费品、教育、医疗健康、B2B 服务等需要“best/top/alternatives/vs/persona/use-case”内容的生产场景。
支持真实公开数据采集与可用性审计：可使用官网、产品页、定价页、帮助中心、公开 PDF、行业报告、第三方评价页和用户提供资料；不能绕过登录、付费墙、反爬限制或私有系统权限。
不要用于全景 GEO 诊断、单页技术审计、纯标题生成、无来源软文、没有明确品牌和类目的排行。无法确认品牌、官网、类目、区域或关键证据时，先停止正文输出并列出阻塞点。
执行流程
- 输入核验：核验品牌、官网、产品、类目、区域、语言、合规说明、竞品范围和核验日期；缺少关键事实时停止。
- 数据可用性分层：把来源分为公开可采集、用户提供、需登录/付费、不可访问四类；不可访问数据不写成确定事实。
- 来源可达审计：可使用
scripts/audit_sources.py检查 Markdown 中的 URL 是否可访问，生成来源可用性 JSON 供自检使用。 - 参考自检：先检查是否需要补充更权威或更完整的参考，优先官方页面、监管/标准文件、学术论文、行业研究和第三方评价，再使用品牌自述。
- 分析完整性地图：生成主题边界、用户意图、选择标准、证据类型、限制条件、国内 AI 平台适配和结构化数据机会，作为生产依据，默认放入文末附录或交付包，不抢占文章开头。
- 关键词地图：覆盖
best、top、alternatives、vs、人群、场景、痛点、价格、集成、迁移和风险类意图。 - 真实竞品筛选：选择真实同类竞品，优先 5 个资料充分的竞品；证据不足的竞品不硬选、不改名、不凑数。
- 评选方法设计：使用 4 到 6 个行业通用维度，补充 1 到 2 个有证据支撑的差异化维度；明确权重、评分依据和不确定性。
- 文章优先生成：先生成一篇完整可发布的 GEO 榜单文章，文章主体必须包含导语、直接结论、为什么现在看、评选方法、核心榜单、对比表、榜单正文、场景选择、采购风险、FAQ 和 Sources；核验摘要、真实数据获取与可用性、分析完整性地图、关键词地图、平台适配、结构化数据建议和自检记录默认放到文末附录或文章包辅助文件。
- 证据链审查：价格、功能、集成、融资、客户、案例、奖项、认证、评分和资质必须可追溯；无法核验则降级为“公开信息未确认”或移除。
- 榜单梯度控制：目标品牌只能通过证据、细节和适用场景体现优势；TOP1 必须有多源证据支持，不能靠品牌资料自述。
- 四格式渲染与复核：使用
scripts/render_ranking_article_pack.py生成 Markdown、HTML、PDF、Word，并检查文件存在、白底排版、HTML 固定菜单、PDF A4、Word 表格不向右溢出。
方法依据
采用 GEO-RANK-SC 方法：Generative Engine Optimization、Retrieval-Augmented evidence、Ordered comparison、Ranking gradient、Knowledge-source traceability、Systematic completeness、Cross-platform readability。
关键依据放在 references/research-foundation.md，执行时要把这些依据转成可执行约束：可回答、可引用、可追溯、可比较、可解释、可复核，而不是堆砌概念。
国内平台适配
- DeepSeek：评选逻辑、维度定义、权重、因果链和边界条件。
- 豆包：先给直接答案，再给场景选择建议和易懂解释。
- 千问：来源编号、事实与推论分离、核验日期和价格口径。
- Kimi：长文结构、多源证据、完整章节和限制说明。
- 元宝：公众号可读性、段落节奏、中文场景化表达和腾讯生态信源优先级。
What ships with it
31 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.
- agents/interface.yaml 651 B
- evals/expected_artifacts.json 1.2 KB
- evals/quality_cases.json 1.9 KB
- evals/trigger_cases.json 269 B
- examples/hubspot-demo/hubspot-crm-ranking-article.docx 24 KB
- examples/hubspot-demo/hubspot-crm-ranking-article.html 36 KB
- examples/hubspot-demo/hubspot-crm-ranking-article.md 25 KB
- examples/hubspot-demo/hubspot-crm-ranking-article.pdf 191 KB
- examples/hubspot-demo/index.html 4.6 KB
- examples/hubspot-demo/report_input.json 56 B
- examples/hubspot-demo/review-notes.md 1.4 KB
- examples/hubspot-demo/source-article.md 25 KB
- examples/hubspot-demo/source-audit.json 5.6 KB
- examples/synthetic-demo/demo-geo-ranking-article.docx 15 KB
- examples/synthetic-demo/demo-geo-ranking-article.html 13 KB
- examples/synthetic-demo/demo-geo-ranking-article.md 6.3 KB
- examples/synthetic-demo/demo-geo-ranking-article.pdf 110 KB
- examples/synthetic-demo/index.html 4.6 KB
- examples/synthetic-demo/source-article.md 6.3 KB
- examples/synthetic-demo/source-audit.json 4.4 KB
- manifest.json 477 B
- references/artifact-layout.md 2.2 KB
- references/data-acquisition.md 2.3 KB
- references/evidence-and-ranking-rules.md 1.6 KB
- references/quality-gates.md 2.7 KB
- references/research-foundation.md 3.1 KB
- references/skill-method.md 4.6 KB
- reports/output-risk-profile.md 1.8 KB
- scripts/audit_sources.py 4.2 KB runs code
- scripts/render_ranking_article_pack.py 16 KB runs code
- templates/brief-template.md 906 B
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.
- 12d ago First seen · 62 lines · 134 tokens per session scan A 28fbbaa0b9bc
yao-geo-ranking-article-builder is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 134 tokens to every session and 1,570 once invoked, about $0.0007 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
pipefy-process-intelligence
Use this skill when the user wants to analyze an existing pipe for improvement opportunities — automation gaps, manual bottlenecks, missing AI agents, field conditions, or adjacent processes. Acts as a process analyst: investigates, diagnoses, and improves the pipe in progressive rounds — each round delivers visible…
c
OpenPaw coordinator — routes requests to skills, manages memory, knows what's installed. Use /c for any task.
-21risk-automation
Automate 21risk tasks via Rube MCP (Composio). Always search tools first for current schemas.
-2chat-automation
Automate 2chat tasks via Rube MCP (Composio). Always search tools first for current schemas.
ably-automation
Automate Ably tasks via Rube MCP (Composio). Always search tools first for current schemas.
abstract-automation
Automate Abstract tasks via Rube MCP (Composio). Always search tools first for current schemas.