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-brand-graphgit 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-brand-graph)<a href="https://agentmods.dev/skills/yaojingang/yao-geo-skills/yao-geo-brand-graph"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-brand-graph/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-brand-graph"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-geo-skills/yao-geo-brand-graph.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 | $0.00761 |
| Opus 5 | $0.00034 | $0.00380 |
| Sonnet 5 | $0.00013 | $0.00152 |
| Haiku 4.5 | $0.00007 | $0.00076 |
Grade A, and why
yao-geo-brand-graph 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.
What it actually says
Yao GEO Brand Graph
执行流程
- 按
references/skill-method.md建立来源账本，区分官网、官方文档、投资者关系、客户案例、第三方资料和待确认素材。 - 按
references/real-data-acquisition.md对来源 URL 做自动连通核验；能访问的来源进入真实数据样本，受限来源进入人工复核。 - 按 mention -> candidate -> canonical entity 做实体消歧。
- 按
references/entity-schema.md抽取品牌、产品、服务、功能、技术、行业、用户、场景、客户、案例、证据、地点、时间。 - 按
references/evidence-policy.md抽取有方向的关系边，每条关系必须有证据 ID。 - 先做完整性自检：权威参考、来源覆盖、真实数据来源核验、实体覆盖、关系证据、Schema 一致性、内容资产对齐、国内 AI 平台监测闭环和隐私授权缺口。
- 输出实体清单、关系清单、可信等级、消歧表、Mermaid、JSON-LD、RDF 三元组、国内 AI 平台测试场景和补强建议。
排版质量门
- Word 必须使用横向页面、真实 w:tbl 表格、固定 dxa 表宽，禁止自动表宽撑出页面。
- Word 表格网格总宽必须小于正文宽度，并保留右侧安全边距。
- URL、英文实体 ID、英文产品名和长英文短语必须在单元格内主动断行。
- HTML/PDF 按 kami paper long-doc 风格排版：暖米纸底、ivory 内容面、油墨蓝点缀、暖灰边框、serif 标题、紧凑长文档节奏。
- HTML 可视化报告必须有固定跟随的目录菜单；PDF 打印版可隐藏菜单以保持正文排版。
- 报告必须包含系统化分析模块，不能只输出基础实体表和图谱图。
工具入口
scripts/render_yao_geo_brand_graph.py：从结构化report_input.json生成 Word、PDF、HTML、Markdown 和quality-report.json。scripts/collect_source_validation.py：读取来源账本，自动采样 URL 可达性、页面标题和核验时间，并可写回source_validation。examples/hubspot-domestic-ai-test/report_input.json：HubSpot 国内 AI 平台测试样例输入。templates/brief-template.md：项目输入简报模板。evals/expected_artifacts.json：必要文件和示例交付检查清单。reports/output-risk-profile.md与reports/artifact-design-profile.md：输出风险和排版设计约束。
What ships with it
24 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 923 B
- evals/expected_artifacts.json 903 B
- evals/failure_cases.md 126 B
- evals/rubric.md 156 B
- evals/trigger_cases.json 85 B
- examples/hubspot-domestic-ai-test/hubspot-domestic-ai-yao-geo-brand-graph.docx 26 KB
- examples/hubspot-domestic-ai-test/hubspot-domestic-ai-yao-geo-brand-graph.html 57 KB
- examples/hubspot-domestic-ai-test/hubspot-domestic-ai-yao-geo-brand-graph.md 42 KB
- examples/hubspot-domestic-ai-test/hubspot-domestic-ai-yao-geo-brand-graph.pdf 361 KB
- examples/hubspot-domestic-ai-test/quality-report.json 1.6 KB
- examples/hubspot-domestic-ai-test/report_input.json 68 KB
- examples/hubspot-domestic-ai-test/source-validation.generated.json 7.4 KB
- manifest.json 741 B
- references/entity-schema.md 1.4 KB
- references/evidence-policy.md 1.1 KB
- references/quality-gates.md 1.4 KB
- references/real-data-acquisition.md 2.0 KB
- references/research-backed-framework.md 2.1 KB
- references/skill-method.md 3.2 KB
- reports/artifact-design-profile.md 399 B
- reports/output-risk-profile.md 204 B
- scripts/collect_source_validation.py 5.3 KB runs code
- scripts/render_yao_geo_brand_graph.py 35 KB runs code
- templates/brief-template.md 315 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 · 43 lines · 67 tokens per session scan A c0a025c9ab15
yao-geo-brand-graph 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 761 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
ai-ml-api-automation
Automate AI ML API tasks via Rube MCP (Composio). Always search tools first for current schemas.
vs-crawler
Crawl websites (news, blogs, papers, GitHub, product docs, RSS feeds) into a fixed-schema JSONL file, then create a dataset and a searchable application in Viking AI Search. Supports one-time crawl and scheduled recurring crawl with automatic incremental sync.
vs-search-tuning
Use when a user asks an agent to evaluate or tune text search similarity for an existing Viking AI Search application and dataset.
bailian-cli
A command-line hub for Alibaba Cloud Bailian and DashScope resources. It covers applications, models, knowledge bases, usage, authentication, files, MCP services, pipelines, and installing or updating related agent skills.
bailian-kb
A command-line manager for Alibaba Cloud Bailian knowledge bases, which are collections of documents prepared for search and question answering. It handles the stored documents, search services, text chunks, and data-centre files rather than everyday searches.
bailian-finetune
A command-line workflow for fine-tuning your own Alibaba Cloud Bailian models using text, audio, or image data. It validates and uploads training data, creates a training job, tracks it, exports a selected result, and can deploy the model as a service.