AGENT SKILL

yao-bayesian-skill

Convert uncertain real-world choices into an auditable Bayesian evidence-to-action report with priors, evidence grading, posterior update, action thresholds, sensitivity checks, multi-turn decision logs, and Markdown plus bilingual HTML output. Do not use for Bayes theorem tutoring, homework, generic brainstorming with no report, or final licensed medical, legal, or financial advice.

License 许可
MIT
最近更新
2026-10-14
Stars
★ 1.3k
Forks
145

01 前言 Front Matter

name
yao-bayesian-skill
description
Convert uncertain real-world choices into an auditable Bayesian evidence-to-action report with priors, evidence grading, posterior update, action thresholds, sensitivity checks, multi-turn decision logs, and Markdown plus bilingual HTML output. Do not use for Bayes theorem tutoring, homework, generic brainstorming with no report, or final licensed medical, legal, or financial advice.

02 资源文件 36

03 SKILL.md 正文

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 markdown plus bilingual html report

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

  1. Use references/intake-contract.md to convert the request into one structured decision brief.
  2. If input is incomplete, read references/multi-turn-dialogue-loop.md; start with a weak prior and ask the minimum next questions.
  3. Use references/evidence-prior-playbook.md to grade evidence and choose the lightest valid update path.
  4. Run references/prior-hygiene-checklist.md; show only the 3-5 principles most relevant to this case.
  5. Maintain the round log: user input, remaining gap, update path, probability change, and decision readiness.
  6. Run scripts/bayesian_decision_report.py for canonical JSON or scripts/generate_report_bundle.py for markdown + html.
  7. Finalize with references/decision-report-contract.md, references/report-export-pipeline.md, and references/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.

Reference Map

  • references/intake-contract.md: request-to-brief conversion
  • references/multi-turn-dialogue-loop.md: incomplete-input handling and iterative questioning
  • references/evidence-prior-playbook.md: evidence tiers, priors, update-path selection
  • references/prior-hygiene-checklist.md: default judgment priors for checking priors, evidence, and action intensity
  • references/decision-report-contract.md: required report sections and schema alignment
  • references/report-export-pipeline.md: automatic HTML/Markdown generation and bilingual HTML rules
  • references/sensitivity-and-safety.md: sensitivity analysis and high-risk disclaimers
  • scripts/bayesian_decision_report.py: canonical V0/V1 calculation
  • scripts/generate_report_bundle.py: Chinese-first Markdown plus bilingual HTML

04 同仓库更多 Skills

yaojingang
yaojingang/yao-open-skills

yao-weread-skill

当用户需要分析微信读书阅读历史、生成读书报告、可视化阅读统计、笔记、书架、词云、热力图、雷达图,或导出精排 HTML 报告时使用。也适用于创建 AI 创业者示例阅读报告。不用于通用图书推荐,或不生成报告的原始微信读书 API 查询。

Skill与智能体开发
★ 1.3k
yaojingang
yaojingang/yao-open-skills

yao-websecurity-skill

Use when auditing an authorized website, SaaS, API, AI app, local code path, GitHub repo, staging URL, or owned runtime for security risks, vulnerability checklist scoring, static review, dynamic review, active validation, or Chinese security reports.

Skill与智能体开发
★ 1.3k
yaojingang
yaojingang/yao-open-skills

yao-tutorial-skill

Create standalone beginner tutorial packages from a topic or supplied references, with adaptive research, course-style outline design, chapter visuals, and Markdown/DOCX/PDF/HTML exports. Use for textbook-like tutorials, course guides, teaching documents, or long beginner guides; not for quick answers, link summaries, pure diagrams, or file conversion.

文档处理资料检索与研究
★ 1.3k
yaojingang
yaojingang/yao-open-skills

yao-positioning-skill

Generate evidence-aware positioning reports for personal IPs, courses, products, services, brands, or companies by combining positioning theory, course-marketing analysis, user intent, competitor research, market demand, and verifiable advantages. Use when users ask for 定位、差异化分析、优势分析、心智定位、品类定位、竞品定位研究、定位报告或再定位建议. Do not use for slogan-only copywriting, generic marketing ideas, standalone market research without a positioning recommendation, or brand knowledge-base construction.

市场营销营销推广资料检索与研究
★ 1.3k
yaojingang
yaojingang/yao-open-skills

yao-open-skills-sync

Manage the yao-open-skills public collection. Use this skill whenever the user wants to evaluate whether a local skill should be open sourced, import a local skill into the yao-open-skills repository, register which skills are already public, track GitHub sync status, or update the collection README and catalog after adding or refreshing a skill.

Skill与智能体开发
★ 1.3k
yaojingang
yaojingang/yao-open-skills

yao-naval-almanack-skill

Improve career choices, service/productization, reusable income/ownership, long-term partnerships, attention allocation, and desire/social-comparison tradeoffs using Naval principles, even without naming Naval. 中文:工作选择、找专长、重复交付产品化、长期合作、忙却无积累、目标取舍、同龄人比较。Also explain, verify, and apply 《纳瓦尔宝典》, Naval Ravikant, or quotes. Use for substantive advice; skip generic planning/editing, coding, arithmetic, vague anxiety, trading, clinical care, and passing name mentions. Honor explicit opt-outs.

★ 1.3k