yaojingang/yao-open-skills is a public collection of reusable AI skills for research, decision-making, business analysis, learning, and document creation. It serves people who want repeatable, maintainable AI workflows instead of isolated prompts, and catalogued add-ons are published skills from this collection.
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-open-skills --skill yao-bayesian-skillgit clone --depth 1 https://github.com/yaojingang/yao-open-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-open-skills/yao-bayesian-skill)<a href="https://agentmods.dev/skills/yaojingang/yao-open-skills/yao-bayesian-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-bayesian-skill/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-open-skills/yao-bayesian-skill"><img src="https://agentmods.dev/badge/skills/yaojingang/yao-open-skills/yao-bayesian-skill.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 | $0.00078 | $0.00776 |
| Opus 5 | $0.00039 | $0.00388 |
| Sonnet 5 | $0.00016 | $0.00155 |
| Haiku 4.5 | $0.00008 | $0.00078 |
Grade A, and why
yao-bayesian-skill 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Yao Bayesian Skill
Use This Skill For
- structure a vague choice into hypothesis, time horizon, success metric, and actions
- set a prior, grade evidence, update posterior, compare action thresholds, and recommend next information
- start from incomplete input with a weak prior, then improve the judgment through multi-turn questioning
- export one synchronized Chinese-first
markdownplus bilingualhtmlreport
Do Not Route Here
- Bayes theorem tutoring or homework-only calculations
- broad research or brainstorming with no explicit decision report
- final professional medical, legal, or investment advice
Default Workflow
- Use
references/intake-contract.mdto convert the request into one structured decision brief. - If input is incomplete, read
references/multi-turn-dialogue-loop.md; start with a weak prior and ask the minimum next questions. - Use
references/evidence-prior-playbook.mdto grade evidence and choose the lightest valid update path. - Run
references/prior-hygiene-checklist.md; show only the 3-5 principles most relevant to this case. - Maintain the round log: user input, remaining gap, update path, probability change, and decision readiness.
- Run
scripts/bayesian_decision_report.pyfor canonical JSON orscripts/generate_report_bundle.pyformarkdown + html. - Finalize with
references/decision-report-contract.md,references/report-export-pipeline.md, andreferences/sensitivity-and-safety.md.
Iteration And Implementation Constraints
When extending this skill: state assumptions before coding, keep the smallest valid workflow, touch only files required by the request, and define user-visible success checks before editing. Typical checks: incomplete input yields a weak prior plus follow-up questions; each round is logged; the report explains belief changes; HTML/Markdown still render the intended guidance.
Output Contract
- Produce a decision report, not a formula dump; mark numbers as observed, estimated, or assumed.
- Put the plain-language conclusion and action recommendation before technical sections.
- Include weak evidence, dependence risk, sensitivity, prior-hygiene checks, and high-risk disclaimers when relevant.
- For multi-turn use, log prior, posterior, readiness, gaps, and formula/update path for each round.
- Reports default to Simplified Chinese; HTML also supports Chinese/English switching, sticky navigation, collapsible advanced sections, and top-right
Print/Save as PDF. - Printing or saving HTML as PDF should expand folded sections first.
What ships with it
36 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 930 B
- evals/semantic_config.json 3.8 KB
- evals/trigger_cases.json 1.1 KB
- input/bayesian_decision_request.template.json 11 KB
- input/detailed_growth_case.json 16 KB
- input/geo_overseas_service_case.json 17 KB
- input/sanya_travel_case.json 6.8 KB
- input/sanya_travel_real_case.json 11 KB
- manifest.json 585 B
- references/decision-report-contract.md 1.8 KB
- references/evidence-prior-playbook.md 2.4 KB
- references/intake-contract.md 1.9 KB
- references/multi-turn-dialogue-loop.md 2.2 KB
- references/prior-hygiene-checklist.md 5.0 KB
- references/report-export-pipeline.md 3.4 KB
- references/sensitivity-and-safety.md 1.6 KB
- reports/detailed-growth-case.html 90 KB
- reports/detailed-growth-case.md 11 KB
- reports/detailed-growth-case.pdf 1087 KB
- reports/example-decision-report.html 82 KB
- reports/example-decision-report.md 9.3 KB
- reports/example-decision-report.pdf 1000 KB
- reports/geo-overseas-service-case.html 89 KB
- reports/geo-overseas-service-case.md 12 KB
- reports/geo-overseas-service-case.pdf 1111 KB
- reports/README.md 1.2 KB
- reports/sanya-travel-case.html 69 KB
- reports/sanya-travel-case.md 8.4 KB
- reports/sanya-travel-case.pdf 843 KB
- reports/sanya-travel-real-report.html 74 KB
- reports/sanya-travel-real-report.md 10 KB
- reports/sanya-travel-real-report.pdf 905 KB
- scripts/bayesian_decision_report.py 52 KB runs code
- scripts/generate_report_bundle.py 69 KB runs code
- templates/report-theme.css 17 KB
- templates/report.schema.json 2.4 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 · 55 lines · 78 tokens per session scan A db2028191464
yao-bayesian-skill is a skill published in the GitHub repository yaojingang/yao-open-skills (1,314 stars, last pushed 15d ago), licensed MIT. It adds 78 tokens to every session and 776 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…