andrew-shwetzer/thinking-tools

5 stars · Last commit 2026-03-16

A self-improving system of 7 AI skills that chain together to solve hard problems. Built for Claude Code.

README preview

# Thinking Tools

**7 AI skills that chain together, evaluate each other, and improve themselves.**

Built for [Claude Code](https://docs.anthropic.com/en/docs/claude-code). Works with any LLM that supports custom instructions.

Not a prompt collection. This is a thinking **system** with routing, quality gates, and a self-improvement loop.

```
         Input: any hard problem
                    |
               /think (router)
                    |
      +------+------+------+------+
      |      |      |      |      |
   /derive /xray /stress  /otb  /flip
      |      |    -test    |      |
      +------+------+------+------+
                    |
               /taste (scores output 1-10)

View full repository on GitHub →