Open-sourcing a Demand Assessment Skill — the underlying model is based on Li Jiao Shou’s Demand Triangle Model, and it works well. In short, a reliable demand usually consists of three core elements: lack of fulfillment, target object, and consumer capability. GitHub link at the end.

Basic logic:

1. Input a product, and it will diagnose across dimensions such as the demand triangle, user motivation, willingness to pay, competitive landscape, risk/cost, and output reports in multiple formats (HTML, Word, PDF, etc.).
2. Core purpose: determine whether the product’s demand is valid, where the biggest gaps are, and what to validate next.
3. Whether you are planning a product, a specific feature, or analyzing a comparable mature product, this skill will scrape relevant data, combine it with related models, and provide a detailed analysis and evaluation.

The image shows a sample reference report.

GitHub link: https://github.com/yaojingang/yao-open-skills/tree/main/skills/yao-demand-skill…

yaojingang/yao-open-skills

Source: https://github.com/yaojingang/yao-open-skills

Yao Open Skills

A curated collection of production-ready AI skills for research, decision, business, learning, and document generation

OpenYao continues the methodology line of YAO = Yielding AI Outcomes. The focus is not on piling up more prompt text, but on turning effective methods, workflows, evaluations, aesthetic constraints, and execution boundaries into reusable AI assets that ultimately produce real, deliverable results.

Yao Open Skills is a growing collection of AI-native skills designed for real-world work: turning uncertain decisions into reports, turning business questions into structured analysis, and turning topics or reference packets into polished tutorial documents.

This directory serves two purposes:

• Acts as a local working area for the GitHub open-source collection.
• Acts as a local sync management center, recording which Skills have been included in the collection, their current public status, and whether the description page has been updated.
• Acts as a release entry point for subsequent version iterations — after each confirmed update, it syncs and pushes to GitHub.

Navigation

• OpenYao Philosophy
• Recommended Entry Points
• Published Skill Guides
• Featured Published Skills
• Skill Catalog
• Publishing Rules
• Naming Conventions
• Repository Design

OpenYao Philosophy

yao-open-skills aims to make public not a collection of “scattered prompts,” but a more stable view of AI assets:

• Skills should serve real task outcomes, not just conversation processes.
• Skills should be reusable, maintainable, and evaluable, not one-off tricks.
• Skills should be able to be solidified into team assets, not remain in personal memory or chat logs.
• The open-source collection should emphasize method quality, clear boundaries, and continuous evolution, not quantity stacking.

In other words, OpenYao pushes the YAO methodology further into a public knowledge base: turning skills worth sharing from local-only assets into a public capability set that can be discovered, referenced, improved, and reused.

Featured Skill Lines

This section showcases the capability lines that OpenYao plans to build long-term. The naming style will remain functional and verb-driven, avoiding fragmentation in the naming system.

Skill Doctor
Diagnose and fix issues in skills automatically.

Skill Optimizer
Improve performance, structure, and effectiveness.

Skill Ranker
Evaluate and rank skills based on real impact.

These names represent product directions; they are not necessarily already included as independent skills in the repository. The current repository maintains a clear distinction between “published capabilities” and “planned capability lines.”

Recommended Entry Points

If you want to understand the meta-methods behind OpenYao, start with yao-meta-skill (https://github.com/yaojingang/yao-meta-skill).
This is the meta-skill project in the YAO methodology line, designed to further solidify workflows, prompts, notes, and execution experience into skill assets that can be created, evaluated, governed, and packaged.

The relationship between these two repositories can be simply understood as:

• yao-meta-skill (https://github.com/yaojingang/yao-meta-skill): Defines how to systematically create, evaluate, govern, and package skills.
• yao-open-skills (https://github.com/yaojingang/yao-open-skills): Houses the skill outcomes already worth sharing publicly.

If you think of yao-meta-skill as the “meta-method engine,” then yao-open-skills is more like the “public product showcase layer.”

Repository Goals

• Organize scattered local skills into a stable public collection.
• Retain clear source, inclusion path, sync status, and license information for each public skill.
• Use unified rules to filter skills, avoiding pushing private data, output artifacts, and experimental garbage to the public repository.
• Build a continuously evolving public asset library for truly valuable skills under the YAO methodology.

Public Inclusion Criteria

• Clear topic: Others should know what problem a skill solves just by seeing its name and description.
• Reusable: It should not depend on private context on your local machine to run.
• Cleanable: It should be possible to remove sensitive information, cache, outputs, account traces, and internal documentation.
• Maintainable: You are willing to continue fixing, iterating, and explaining it.

For detailed rules, see:

• docs/repository-design.md
• docs/naming-conventions.md
• docs/publishing-rules.md

Directory Structure

yao-open-skills/
├── README.md
├── docs/
├── registry/
├── scripts/
└── skills/

• docs/: Repository design, publishing rules, sync conventions.
• registry/: Skill registry, the source of truth for local and public status.
• scripts/: Helper scripts to update the registry and README.
• skills/: Copies of skills actually included in the public collection.

Published Skill Guides

• Skill Guides Index
• Yao Open Skills Sync
• Yao Bayesian Skill
• Yao Business Skill
• Yao Copyright Skill
• Yao Crux Skill
• Yao Demand Skill
• Yao Game Theory Skill
• Yao Kelly Skill
• Yao Tutorial Skill
• Yao WeRead Skill
• Yao Websecurity Skill

Featured Published Skills

Yao Crux Skill

yao-crux-skill is a skill for diagnosing primary and secondary contradictions in complex real-world problems.

It first determines whether the user’s current situation is clear enough, then organizes visible problems, invisible root variables, primary contradictions, secondary contradictions, primary aspects, recommended actions, and outcome probabilities into a reviewable diagnostic report.

Its public version now has these standout features:

• First performs a situation clarity check; if information is insufficient, it prioritizes follow-up questions rather than rushing to conclusions.
• Uses decisiveness, driving force, and stage relevance to explain primary contradiction judgments, then cross-validates with primary/secondary contradictions, first principles, Bayesian evidence updating, and Occam’s razor.
• Distinguishes internal changeable structures from external hard conditions, and how external factors work through internal ones.
• Clearly separates primary contradiction (the most critical bottleneck) from secondary contradiction (not the main focus now, but keep an eye on it).
• When the primary contradiction is clear enough, more aggressively allocates 50%-70% of high-leverage resources to the main attack line.
• Every conclusion includes reversal conditions, review timing, and signals that the next-stage primary contradiction may shift.
• The report includes an analysis flowchart, a photo-style iceberg model, a contradiction candidate matrix, a resource allocation chart, and a dynamic stage transition diagram.
• Default output: Markdown + HTML + DOCX + PDF + report JSON.
• The public repository contains three fictional business examples and downloadable reference materials; real cases and private inputs are not included in the repository.

If you want to quickly understand this skill, we recommend viewing in this order:

1. Public documentation
2. Chinese directory description
3. English README
4. Skill entry point
5. Follow-up and situation clarity
6. Theoretical anchors and rules
7. Primary/secondary contradiction judgment model
8. Report export pipeline
9. Fictional example reports
10. Downloadable reference materials

Yao WeRead Skill

yao-weread-skill is a skill for generating personal reading visualization reports from WeRead (微信读书) data.

It organizes reading duration, reading rhythm, bookshelf assets, content preferences, and note semantics from the past two years into a directly openable HTML report. Rather than simply counting reading minutes, it focuses more on “how you read, what you read, and which books prompted your thoughts.”

Its public version now has these standout features:

• Default generation of 26 chart modules, covering monthly reading, weekly rhythm, cumulative reading, longest-read books, category radar, author/publisher preferences, bookshelf composition, note types, progress scatter, word clouds, and note timelines.
• Supports real WeRead account reports as well as AI entrepreneur sample profiles that require no account.
• Uses a combination of /readdata/detail, /shelf/sync, /user/notebooks, /book/bookmarklist, and /review/list/mine for a complete data view.
• The word cloud prioritizes high-signal domain-specific words and filters common Chinese segmentation fragments.
• The HTML report adopts a warm paper texture, ink-blue accents, and compact evidence cards, suitable for local browsing, screenshots, and archiving.
• API keys are read only from environment variables; real reports are not included in the public repository by default.

If you want to quickly understand this skill, we recommend viewing in this order:

1. Public documentation
2. Directory description
3. Skill entry point
4. Chart catalog
5. Data contract
6. Generation script
7. AI entrepreneur sample report

Yao Websecurity Skill

yao-websecurity-skill is a skill for security audits of authorized websites, SaaS, APIs, AI applications, local code directories, and GitHub repositories.

It does not simply call a scanner; instead, it first understands the system’s code, routes, authentication, data model, deployment configuration, dependencies, and AI/LLM integration, then selects the truly relevant checks from the V001-V275 vulnerability ontology, and finally outputs a reviewable security scorecard and audit report.

Its public version now has these standout features:

• Built-in 275 website security checks covering access control, authentication sessions, APIs, XSS, CSRF, SSRF, file upload, dependencies, containers, CI/CD, database, cache, AI/RAG/LLM, and other risk domains.
• Supports multiple review modes: static, dynamic-safe, dynamic-active, online-authorized, and hybrid.
• Local code and GitHub repositories must first be copied or cloned to a fresh temporary directory; building, running, testing, and report generation all happen inside the isolated workspace.
• Dynamic active testing is controlled by authorization switches; blind SSRF/OOB, brute force, file changes, database writes, and resource stress tests are only allowed by default in isolated temporary deployments.
• Reports default to Chinese; outputs include Excel + HTML + Markdown + PDF + sanitized JSON.
• HTML supports Chinese/English toggle and sticky top navigation; Excel uses Chinese status labels, Chinese explanations, and an engineering-friendly scoring table.
• Before rendering, it sanitizes local absolute paths, cookies, Bearer tokens, API keys, passwords, private keys, and long token-like strings.

If you want to quickly understand this skill, we recommend viewing in this order:

1. Public documentation
2. Skill entry point
3. Directory description
4. Review modes
5. Report contract
6. Vulnerability ontology
7. Report script
8. Fictional example report

Yao Tutorial Skill

yao-tutorial-skill is a production-oriented skill that goes “from topic or reference packet to complete tutorial output.”

It does not simply help you write a explanatory article; instead, it organizes the input topic, user-provided materials, authoritative sources, papers, GitHub practices, and case evidence into a deliverable tutorial package: first normalizing the requirements, then conducting research and evidence gathering, then generating a beginner-friendly chapter outline, and finally outputting Markdown + Word + PDF + HTML with accompanying visuals.

Its public version now has these standout features:

• Supports inputting just a topic, or a set of materials, links, papers, repositories, or drafts.
• Prioritizes the user’s provided materials as the core; supplements with external authoritative sources only when materials are insufficient.
• Written for beginners: titles convey user benefits, outlines speak in plain language, chapter structures are accessible and executable.
• Public outputs do not show internal evidence markers like [U1] or [X1], nor do they include phrases like “based on the original text.”
• Each chapter must have a corresponding visual illustration.
• Illustrations are first generated as HTML canvases, then screenshots are embedded into the tutorial content.
• The HTML report supports a centered content container, left-side table of contents, date, chapter jumping, and a clean reading layout.
• Word/PDF outputs have headers and footers removed by default to avoid interference from export paths, page numbers, and browser print information.
• Built-in validation scripts check for chapters, illustrations, references, export files, and local path leaks.

If you want to quickly understand this skill, we recommend viewing in this order:

1. Public documentation
2. Skill entry point
3. Input adaptation rules
4. Tutorial writing rules
5. Visual canvas rules
6. Export and validation script

Yao Bayesian Skill

yao-bayesian-skill is the most complete type of “evidence-to-action” skill in the current public collection.

Its focus is not on explaining Bayes’ theorem, but on compressing a real-world uncertain problem into a decision workflow that is executable, reviewable, and continuously iterable.

Its public version now has these standout features:

• Supports starting from incomplete input, giving a weak prior and preliminary judgment.
• Supports multiple rounds of follow-up, continuously updating the prior, posterior, and decision readiness.
• Built-in Bayesian prior checks: picks the 3 to 5 most relevant principles from 20 life judgment principles.
• Records which pieces of information changed the judgment in each conversation round.
• The report first presents conclusions readable by ordinary users, then shows technical details.
• Default output: Markdown + bilingual HTML.
• The HTML supports Chinese/English toggle, sticky navigation, printing, and saving as PDF directly in the browser.

If you want to quickly understand this skill, we recommend viewing in this order:

1. Public documentation
2. Skill entry point
3. Detailed case input
4. Export script
5. Example reports directory

Yao Game Theory Skill

yao-gametheory-skill is a game theory strategic report skill for competition, negotiation, alliances, channels, platforms, and competitor counterattacks.

It suits any scenario where “our actions will provoke a reaction from opponents”: price wars, channel conflicts, competitor counterattacks, platform ecosystems, funding negotiations, M&A bidding, market entry, alliance cooperation, and regulatory communication.

It does not treat game theory as a stack of textbook concepts; instead, it converts CEO questions into players, strategies, payoffs, timing, signals, commitments, and equilibrium checks, focusing on:

• How opponents might respond.
• Whether our commitment actions are credible.
• Which strategy remains more stable even after the opponent’s reaction.

Its design principle: first identify players, strategies, payoffs, constraints, and action timing; then route to an appropriate combination of game frameworks; finally convert the model into a strategic report that management can use directly.

Its public version now has these standout features:

• Built-in framework catalog and AI application router, covering Nash equilibrium, Prisoner’s Dilemma, zero-sum, coordination, Hawk-Dove, Stag Hunt, entry deterrence, Stackelberg, Bertrand/Cournot, signaling, repeated games, auctions, alliances, and mechanism design.
• Combines frameworks by scenario rather than mechanically applying concepts; for example, a price war combines Bertrand, Prisoner’s Dilemma, repeated games, and credible commitments.
• New real historical behavior correction layer: adjusts opponent rationality probability using past threat fulfillment rates, free-tier investments, channel attack history, and empirical references, avoiding overestimation of opponent time consistency.
• Supports starting from incomplete strategic input, building a weak model that can be updated.
• Clear routing for price wars, channel conflicts, platform ecosystems, M&A bidding, funding negotiations, competitor free versions, and regulatory communication.
• The report front-loads recommended actions, opponent reaction map, payoff matrix, historical behavior correction, commitment credibility, strategy readiness, and sensitivity checks.
• Supports re-running the report by incorporating new opponent actions into the original case.
• Default output: Markdown + HTML + Word + PDF + canonical JSON.
• Word/PDF wide tables are handled with landscape pages, real tables, fixed widths, and safe line breaks.

If you want to quickly understand this skill, we recommend viewing in this order:

1. Directory description
2. Public documentation
3. Skill entry point
4. Framework catalog and AI router
5. Price war example input
6. Export script
7. Example reports directory

Workflow

1. You provide a local Skill path.
2. Determine whether the Skill is suitable for public release according to rules.
3. Clean sensitive files and irrelevant artifacts, then copy to skills/<name>/.
4. Write or update the registry entry in registry/skills.json.
5. Run the README rendering script to refresh the collection description page.
6. If you want to publish, push the repository to GitHub’s yao-open-skills.

GitHub Publishing Conventions

• The GitHub repository name is fixed as yao-open-skills.
• After completing local collection changes, first update registry/skills.json and the README, then perform Git commit and push.
• Only after the push is actually completed can the Skill be marked as published, and last_synced_at is written.
• If the local source Skill changes later but GitHub has not been updated yet, the corresponding record should be marked as needs-update.

Local Skill Management

This repository includes a built-in management Skill:

• skills/yao-open-skills-sync/SKILL.md

Its responsibilities are:

• Receive the local Skill path you provide.
• Determine if it is suitable for public release.
• Import it into yao-open-skills according to collection rules.
• Maintain the registry and README directory page.
• Record whether this Skill has been synced to GitHub and the corresponding online path.

Skill Catalog

Future Conventions

• registry/skills.json is the source of truth.
• The table of contents in the README is generated by a script, not manually maintained.
• Any newly included Skill must first pass the publishing rules, then update the registry and README.
• Any changes intended for public release should be pushed to the GitHub remote repository after cleanup.