Thought Based Reasoning

This is a structured prompting framework that makes Claude show its work on complex problems. You get six different techniques depending on what you're doing: zero-shot chain of thought for quick reasoning boosts, self-consistency when you need confidence scores, tree of thoughts for puzzles, least-to-most for breaking down dependencies, ReAct for grounding answers in real lookups, and PAL for generating Python to eliminate arithmetic errors. The decision matrix and templates are actually useful, not just theory. ClawFu claims 20-70% accuracy gains on the techniques, which tracks with the academic literature these are pulled from. Worth trying when you catch Claude hedging or making dumb math mistakes.

Install to Claude Code

npx -y skills add guia-matthieu/clawfu-skills --skill thought-based-reasoning --agent claude-code