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-effect-monitorgit 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-effect-monitor)<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-effect-monitor"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-effect-monitor/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-effect-monitor"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-effect-monitor.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 | $0.00067 | $0.01777 |
| Opus 5 | $0.00034 | $0.00889 |
| Sonnet 5 | $0.00013 | $0.00355 |
| Haiku 4.5 | $0.00007 | $0.00178 |
Grade A, and why
yao-geo-effect-monitor 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yao GEO Effect Monitor
When To Use
- 为 GEO 长期运营建立 AI 答案监测、引用源追踪、品牌表述纠偏和效果归因闭环。
- 面向客户月报、内容迭代、页面优化、外部信源建设或品牌事实纠偏输出后端监测方案。
- 覆盖国内平台:DeepSeek、豆包、千问、Kimi、元宝,并为每个平台建立独立采样口径。
- 默认交付
Word、PDF、HTML、Markdown四格式报告,要求白底、表格边框、对齐、换行和页面溢出可控。
Do Not Use
- 一次性 GEO 战略诊断,优先用
yao-geo-panorama-audit。 - 只做 CRM 字段、表单和转化追踪,不需要 AI 答案监测,优先用
yao-geo-tracking。 - 需要绕过平台限制、批量滥采、模拟真人登录或违反服务条款。
- 只需要内容生产或文章改写,不需要监测闭环。
Required Inputs
最少输入:品牌名、目标平台、监测目标或报告周期。可选输入包括意图拓词 Prompt 库、竞品名、目标页面、内容清单、基线数据、发布日期、更新记录、CRM 或转化数据、外部信源清单、历史 AI 答案样本、设备、账号、地区、联网状态和合规限制。
Required Reading
references/research-basis.mdreferences/monitoring-method.mdreferences/cn-platform-sampling.mdreferences/data-acquisition.mdreferences/metrics-attribution.mdreferences/correction-loop.mdreferences/dashboard-data-model.mdreferences/report-completeness-model.mdreferences/artifact-layout.mdreferences/quality-gates.md
Workflow
- 统一监测对象:品牌名、别名、产品名、竞品名、官网域名、公众号、文档站、媒体稿、社区和视频号。
- 做权威参考扫描:先收集官网、官方文档、投资者/监管/标准资料、研究论文和可信第三方来源,建立来源账本,再进入分析。
- 做公司测试场景发现:从公开事实提炼产品线、客户场景、AI/新功能、价格边界、集成生态、中文资料可得性和竞品/替代品,再映射到 Prompt 组。
- 建立 Prompt 库:按
推荐、比较、替代、价格、风险、品牌验证、场景问法七组组织,每组保留核心问法、长尾问法、对照问法和追问问法。 - 建立五平台独立采样口径:DeepSeek 记录结论稳定性和证据链;豆包记录口语问答和图文输出;千问记录引用源和追问;Kimi 记录深度研究与长文引用;元宝记录微信生态来源和公众号内容表现。
- 选择数据接入模式:按
合成回放、人工真实样本、授权 API/连接器、浏览器辅助合规采样、CRM/转化数据导入分级,先确认权限、频率、证据和隐私边界。 - 执行采样并记录环境:平台、时间、设备、账号状态、地区、联网状态、Prompt 版本、答案原文、引用链接、截图、导出文件、接口日志或其他可审计证据。
- 做真实数据可用性判定:没有原始答案、截图/导出、采样环境和来源记录时,不得把结果标成真实采样;只能标成合成样例、推断或待复核。
- 按六层模型分析:覆盖可见性、事实性、证据性、稳定性、竞争性和治理/归因,不允许只输出单维度指标。
- 计算指标:品牌出现率、候选率、推荐率、排序、竞品出现率、负面表述率、描述准确率、事实错误率、引用召回率、引用准确率、引用类型覆盖、答案稳定性。
- 做引用源追踪:区分官网、公众号、媒体、百科、社区、视频号、文档站、评测站、聚合页和竞品页面,并判断引用是否支持对应说法。
- 做谨慎归因:设置基线窗口、观察窗口、处理 Prompt、对照 Prompt、竞品对照和外部事件记录;默认使用
观察相关,只有证据充分才提高归因置信度。 - 生成纠偏闭环:把错误事实、缺失证据、弱页面、负面表达和引用缺口映射到知识库、内容改造、页面设计、外部发布或销售口径。
- 输出系统、详细、完整的报告:必须包含来源账本、数据接入声明、分析边界、指标体系、平台差异、引用质量、风险治理、纠偏路线图、仪表盘/API 和附录。
What ships with it
35 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 1.3 KB
- evals/expected_artifacts.json 2.2 KB
- evals/failure_cases.md 540 B
- evals/rubric.md 1.2 KB
- evals/trigger_cases.json 1.7 KB
- examples/hubspot-cn-signal-monitor/html-head.html 3.7 KB
- examples/hubspot-cn-signal-monitor/hubspot-cn-effect-monitor.docx 19 KB
- examples/hubspot-cn-signal-monitor/hubspot-cn-effect-monitor.html 31 KB
- examples/hubspot-cn-signal-monitor/hubspot-cn-effect-monitor.md 15 KB
- examples/hubspot-cn-signal-monitor/hubspot-cn-effect-monitor.pdf 542 KB
- examples/hubspot-cn-signal-monitor/quality-report.json 1.5 KB
- examples/hubspot-cn-signal-monitor/report_input.json 413 B
- examples/README.md 687 B
- examples/synthetic-demo/html-head.html 3.7 KB
- examples/synthetic-demo/quality-report.json 1.2 KB
- examples/synthetic-demo/README.md 387 B
- examples/synthetic-demo/report_input.json 214 B
- examples/synthetic-demo/xinglan-effect-monitor-demo.docx 19 KB
- examples/synthetic-demo/xinglan-effect-monitor-demo.html 29 KB
- examples/synthetic-demo/xinglan-effect-monitor-demo.md 13 KB
- examples/synthetic-demo/xinglan-effect-monitor-demo.pdf 531 KB
- manifest.json 409 B
- references/artifact-layout.md 1.6 KB
- references/cn-platform-sampling.md 1.1 KB
- references/correction-loop.md 1.0 KB
- references/dashboard-data-model.md 1.1 KB
- references/data-acquisition.md 3.6 KB
- references/metrics-attribution.md 1.7 KB
- references/monitoring-method.md 2.4 KB
- references/quality-gates.md 1.9 KB
- references/report-completeness-model.md 3.0 KB
- references/research-basis.md 3.1 KB
- reports/artifact-design-profile.md 423 B
- reports/output-risk-profile.md 504 B
- templates/brief-template.md 1.6 KB
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 · 98 lines · 67 tokens per session scan A c9ecdbad8c1a
yao-geo-effect-monitor is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,777 once invoked, about $0.0003 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.