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-explainer-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-explainer-builder)<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-explainer-builder"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-explainer-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-explainer-builder"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-explainer-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 | $0.00153 | $0.01571 |
| Opus 5 | $0.00077 | $0.00785 |
| Sonnet 5 | $0.00031 | $0.00314 |
| Haiku 4.5 | $0.00015 | $0.00157 |
Grade A, and why
yao-geo-explainer-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 13d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yao GEO Explainer Builder
执行流程
- 明确科普选题、目标品牌、品牌知识库、行业资料、目标读者、使用场景、品牌植入限制、内容长度、合规边界和真实数据可用状态。
- 识别问题类型:是什么、为什么、怎么做、怎么选、适合谁、常见误区、推荐路径;每段只处理一个主题。
- 先做自检:参考来源是否足够权威,分析维度是否覆盖意图、读者、证据、真实数据、实体、步骤、决策、合规、平台、复用和衡量。
- 先写 80 到 120 字上下文无关核心摘要,让单段被 AI 搜索截取时仍能回答问题。
- 先生成“完整GEO文章”:文章必须有连续正文、自然段、小标题、解释、步骤、选择标准、误区、FAQ/结尾建议中的至少 6 个正文段落组;读者无需阅读附录也能获得完整答案。
- 使用
references/explainer-method.md构建交付结构:核心摘要、完整GEO文章、分析速览、内容地图、意图矩阵、读者场景、研究依据、证据分级、真实数据接入状态、真实数据采集计划、事实核验矩阵、实体地图、定义、原理、步骤、检查清单、选择标准、决策路径、误区、示例、FAQ、术语表、品牌适用场景、平台适配、结构化数据、衡量计划、内容缺口和来源账本。 - 正文中使用有序列表呈现 How-to,使用自然段解释原因与边界;附录中使用键值对呈现前提参数,使用表格呈现证据分级、选择标准、决策路径和误区校正。
- 按
references/brand-insertion-policy.md植入品牌;品牌只出现在示例、适用场景、FAQ 或结尾建议等服务答案的位置。 - 涉及健康、金融、法律、收益、安全等敏感领域时,必须加入边界提醒;没有证据的效果、收益和安全断言必须删除或中性改写。
- 使用
scripts/render_yao_geo_explainer_builder.py从同一结构生成 Markdown、带固定目录菜单的 HTML 包、Word 和 PDF,并产出quality-report.json。 - 若质量报告未通过,先修复输入结构、证据、品牌次数、文章完整性或版式逻辑,再重新生成四格式文件。
国内平台适配
- Kimi:长文深度解释、多来源证据、完整章节和术语表。
- 千问:来源编号、事实/推论分离、参数化指南和可追溯来源。
- 豆包:生活化问题、短问答、避坑提醒和直接选择建议。
- DeepSeek:步骤逻辑、判断框架、条件分支和推理链路。
- 元宝:公众号教程、小标题节奏、短 FAQ 和可转发段落。
真实数据能力边界
- skill 本身不直接保证联网抓取真实数据;执行时可以由上层 agent 联网检索、读取用户上传材料或使用已有知识库,再把来源写入输入结构。
- 没有真实品牌资料时,必须在报告中声明“未接入/待核验”,并把品牌参数、效果、安全、资质类事实放入事实核验矩阵。
- 已接入真实数据时,必须保留来源定位、采集日期、用途和证据等级;过期、无法访问或来源弱的资料不得支撑确定性结论。
- 真实数据采集计划至少覆盖品牌官方资料、行业/标准资料、用户问题样本;涉及横向比较时增加竞品或设备形态样本。
四格式交付规则
- Markdown 是结构母版,HTML、PDF、Word 必须由同一 section spec 生成,不能让 Word 缺章节。
- 四格式示例打开后必须先呈现一篇完整文章;分析矩阵、证据、真实数据、来源账本作为文章后的支撑材料。
- HTML/PDF 按 kami 版式使用纸张感浅底、象牙色内容面、蓝黑标题、稳定行高和本地字体;表格边框对齐,长文本自动换行,不使用渐变、透明叠色或装饰色块。
- HTML 必须包含目录菜单栏,页面下拉时菜单栏固定跟随;菜单项应链接到每个报告模块。
- Word 必须固定 A4 页面、左右页边距、表格总宽、固定表格布局和单元格边距;长 URL、英文 token、参数串必须软换行,避免向右溢出。
- 示例报告必须真实存在:
.docx、.pdf、html-package/index.html、.md,并附带quality-report.json。
质检清单
- 科普价值优先于品牌表达;不得写成品牌软文。
- 完整文章正文不得被拆成纯模块清单;正文至少 6 个小节、12 个自然段,去空格后不少于 1400 字符。
- 分析必须系统、详细、完整:至少覆盖问题类型、读者场景、来源证据、真实数据接入、事实核验、实体术语、操作步骤、决策路径、合规边界、平台适配、结构化数据和效果衡量。
- 步骤必须编号,选择标准必须表格化,定义必须可独立复用。
- 来源账本必须说明来源、定位、日期和用途;无法核验的事实降级为待确认。
- 品牌出现次数不得超过输入限制;不得承诺没有证据支持的效果、收益、安全性或行业第一。
- Word/PDF 需要人工或自动预览抽查右边缘:表格、URL、长英文、中文长句不得裁切或贴边。
What ships with it
30 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 1.5 KB
- evals/expected_artifacts.json 1.8 KB
- evals/failure_cases.md 1.5 KB
- evals/rubric.md 1.2 KB
- evals/trigger_cases.json 579 B
- examples/acme-sleep-demo/README.md 723 B
- examples/acme-sleep-demo/rendered/deliverables/acme-sleep-geo-explainer.docx 19 KB
- examples/acme-sleep-demo/rendered/deliverables/acme-sleep-geo-explainer.md 30 KB
- examples/acme-sleep-demo/rendered/deliverables/acme-sleep-geo-explainer.pdf 410 KB
- examples/acme-sleep-demo/rendered/deliverables/html-package/fonts/Inter-600.woff2 24 KB
- examples/acme-sleep-demo/rendered/deliverables/html-package/fonts/Inter.woff2 23 KB
- examples/acme-sleep-demo/rendered/deliverables/html-package/fonts/TsangerJinKai02-W04.ttf 18504 KB
- examples/acme-sleep-demo/rendered/deliverables/html-package/index.html 42 KB
- examples/acme-sleep-demo/rendered/index.html 42 KB
- examples/acme-sleep-demo/rendered/input-brief.json 36 KB
- examples/acme-sleep-demo/rendered/manifest.json 279 B
- examples/acme-sleep-demo/rendered/quality-report.json 7.5 KB
- examples/acme-sleep-demo/rendered/research-summary.md 30 KB
- examples/acme-sleep-demo/rendered/sources.json 2.4 KB
- examples/acme-sleep-demo/report_input.json 36 KB
- manifest.json 692 B
- references/artifact-layout.md 2.0 KB
- references/brand-insertion-policy.md 965 B
- references/cn-platform-adaptation.md 867 B
- references/explainer-method.md 4.4 KB
- references/quality-gates.md 2.8 KB
- references/research-foundation.md 4.4 KB
- reports/output-risk-profile.md 1.9 KB
- scripts/render_yao_geo_explainer_builder.py 36 KB runs code
- templates/brief-template.md 2.0 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.
- 13d ago First seen · 63 lines · 153 tokens per session scan A 1f8b59936132
yao-geo-explainer-builder is a skill published in the GitHub repository yaojingang/yao-geo-skills (742 stars, last pushed 1mo ago), licensed MIT. It adds 153 tokens to every session and 1,571 once invoked, about $0.0008 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.