TaiXu WuZhuan is a cognitive methodology skill pack for AI agents that turns divergent thinking, convergent analysis, empirical validation, adversarial review, and value recovery into an executable pipeline.

Stars

86

7-day growth

No data

Forks

19

Open issues

0

License

No data

Last updated

2026-07-09

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It operationalizes a five-stage cognitive framework (diverge-converge-verify-review-recover) into independent, composable AI skills, with a pipeline orchestrator and an external argument scrutiny skill (Socrates), all grounded in first principles and Bayesian reasoning.

Who it is for

  • AI agent users (Claude Code, Qoder, Aone Copilot) building complex cognitive workflows
  • Engineers and product managers evaluating technical or architectural decisions
  • Investors or analysts performing structured due diligence
  • Content creators needing systematic idea generation and critique

Use cases

  • Assessing a product or technical proposal end-to-end (diverge, converge, verify, review, recover)
  • Making architectural decisions by uncovering blind spots and rescuing discarded options
  • Validating third-party analyses or industry reports via Socrates external review
  • Iterating on creative work (writing, design) with structured cognitive checks

Strengths

  • Each skill is independent and can be used standalone or chained; pipeline supports checkpoints and selective steps
  • Empirically demonstrated with a real case: 68 ideas → 10 findings → data-driven validation → reversal of a 'do not release' verdict
  • Built on dual frameworks (deterministic vs. non-deterministic) with clear philosophical grounding (first principles, bounded Bayesian, phase transition)
  • Includes a dedicated external-argument scrutiny skill (Socrates) that complements the internal-review Feynman skill

Considerations

  • Requires an AI agent platform that supports the SKILL.md specification (Claude Code, Qoder, Aone Copilot); not a standalone tool
  • Single-agent attention tunnel effect is acknowledged as a current limitation; future plans involve multi-agent parallelization
  • Installation requires manual copying of skill files and a Bash environment for some validations

README quick start

安装

Description

我的核心技能包,分享给大家。

Related repositories

Similar projects matched by category, topics, and programming language.

react
Featured
react GitHub avatar

react

React is a JavaScript library for building user interfaces with declarative, component-based, and cross-platform design.

Web DevelopmentFrontend Frameworks
246,741
tandpfun
Featured
tandpfun GitHub avatar

wardrobe

A GPT‑image powered app that extracts individual garment cutouts from photos, organizes them into a digital wardrobe, and generates modeled outfit previews.

JavaScript
1,570
mshumer
Featured
mshumer GitHub avatar

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents
1,234