yaojingang/yao-open-skills

OpenYao public skills collection: reusable AI assets for decision-making, business analysis, tutorials, research evidence gathering, and document generation.

Yao Open Skills

What it is – A curated, open‑source collection of AI Skills (structured prompt‑plus‑code workflows) that turn real‑world tasks—decision analysis, business modelling, security auditing, tutorial generation, reading‑report visualisation, etc.—into reproducible, evaluable artefacts. Each Skill lives in its own folder with a SKILL.md entry point, source scripts, reference material and ready‑to‑export reports (Markdown, HTML, DOCX, PDF, JSON, …).

Why it matters – Rather than a loose dump of prompts, the project treats a Skill as a first‑class software asset: reusable, maintainable, and assessable. This aligns with the broader YAO (Yielding AI Outcomes) methodology that emphasises delivering concrete, deliverable results instead of endless chat interactions.

Key components

  • skills/ – the actual Skill implementations (e.g., Bayesian decision‑making, game‑theory strategy, web‑security audit, WeRead reading‑report, tutorial authoring, etc.).
  • registry/skills.json – the single source of truth listing every Skill, its public status, and sync metadata.
  • docs/ – design docs, publishing rules, naming conventions and repository‑level guidelines.
  • scripts/ – helper scripts for updating the registry, rendering the README and the GitHub‑Pages navigation page.
  • index.html + assets/ – a static HTML catalogue generated from the registry for easy browsing.

Highlighted Skills

Skill What it does Output formats
Yao Crux Diagnoses complex problems by identifying primary/secondary contradictions, assesses resource allocation, and produces a full decision report. Markdown, HTML, DOCX, PDF, JSON
Yao Bayesian Turns uncertain questions into a Bayesian decision workflow with prior/likelihood/posterior updates and a readable report. Markdown, bilingual HTML
Yao Websecurity Audits websites, SaaS, APIs or codebases against a 275‑item vulnerability ontology, generating a security scorecard. Excel, HTML, Markdown, PDF, sanitized JSON
Yao WeRead Visualises a user’s WeRead (WeChat Reading) data – reading cadence, book‑shelf composition, note semantics, word‑clouds, etc. Stand‑alone HTML report
Yao Tutorial Converts a topic or source bundle into a full beginner‑friendly tutorial package with outlines, illustrations and multi‑format export. Markdown, Word, PDF, HTML
Yao Game Theory Produces strategic game‑theory reports for pricing wars, negotiations, platform battles, etc., with payoff matrices and credibility checks. Markdown, HTML, Word, PDF, JSON

Typical workflow

  1. Provide a local Skill directory.
  2. The built‑in Yao Open Skills Sync Skill checks if it meets the open‑source criteria (no private data, clean artefacts, reproducible).
  3. If approved, the Skill is copied into skills/<slug>/ and an entry is added to registry/skills.json.
  4. Run python3 scripts/render_collection_pages.py to refresh the README table and the GitHub‑Pages HTML catalogue.
  5. Push to GitHub – the Skill is now publicly discoverable.

Getting started

# Clone the repo
git clone https://github.com/yaojingang/yao-open-skills.git
cd yao-open-skills

# Install any Python dependencies (the repo uses only the standard library for its scripts)
# Explore a Skill, e.g. the Bayesian decision workflow
cd skills/yao-bayesian-skill
cat SKILL.md   # entry point and usage instructions
python3 scripts/generate_report_bundle.py  # run the Skill

Who should use it

  • Researchers and analysts who need repeatable AI‑augmented decision pipelines.
  • Product or strategy teams looking for structured, evidence‑based reports.
  • Security engineers wanting a templated audit workflow that can be version‑controlled.
  • Content creators who want to automate tutorial or reading‑report generation.
  • Anyone interested in the YAO methodology for turning prompts into maintainable software assets.

License – The repository follows the open‑source publishing rules outlined in docs/publishing-rules.md; each Skill includes its own licence information (typically MIT or Apache‑2.0), ensuring the collection can be freely reused and extended.

All details are taken directly from the repository’s README and linked documentation; no external assumptions have been added.

Related

  • Project
    chujianyun/skills

    A Chinese‑language repo that bundles dozens of reusable “Agent Skills” – small, documented plugins for Claude Code and similar LLM‑agent platforms. Skills cover wiki look‑ups, prompt optimisation, career assessments, diagram generation, document interpretation, audio‑to‑text, image watermarking, web‑scraping, and service run‑books. They are organized under `skills/`, registered in `config/skills.json`, and installed via Claude Code’s marketplace, an installer agent, or the `openskills` CLI.

  • Project
    anbeime/skill

    Skill Store is a curated, automatically synced catalog of AI‑agent “skills” (JSON‑described plugins) covering document handling, content creation, video production, e‑commerce automation, and more. It pulls 182 official skills from the community‑maintained awesome‑agent‑skills repo every 24 h and adds 63 hand‑picked Chinese‑language skills. The repo provides Python scripts to update, export, and validate the skill definitions, plus a web UI for browsing. Ideal for developers building LLM‑orchestrated agents who want ready‑made, reusable capabilities.

  • Project
    joeseesun/qiaomu-meta-skill

    A meta-skill that transforms prompts and workflows into researched, evaluated, and securely published AI agent skill packages.

  • Project
    zjunlp/SkillNet

    SkillNet is an open‑source platform that lets you discover, generate, evaluate, analyse and route reusable AI‑agent skills. It offers a public catalogue (500 K+ GitHub‑hosted skills), a Python SDK/CLI with six operations (search, download, create, evaluate, analyze, route), a local web UI, and integration points for agents via an MCP server. The system builds a graph of skill relationships and uses LLM‑powered routing (Claude/Codex) to pick the best skills for a task, providing safety/maintainability scores and reasoning.

  • Project
    davidondrej/skills

    A curated set of prompt‑based skill definitions for AI coding, research, and ops agents, organized by workflow type and ready to be loaded into Cloudroom or similar agent runtimes.