guia-matthieu avatar

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.

skills.sh installs
308
GitHub stars
150
last updated
Aug 21, 2026

Install

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

Installs into .claude/skills of the current project.

Files

Thought-Based Reasoning

Overview

Core principle: Making reasoning explicit improves accuracy 20-70% on complex tasks.

Instead of jumping to answers, decompose problems into steps. This catches errors, enables backtracking, and produces verifiable reasoning.

When to Use

digraph decide {
  "Problem type?" [shape=diamond];
  "Direct answer worked?" [shape=diamond];
  "Need confidence?" [shape=diamond];
  "Use direct prompting" [shape=box];
  "Use Zero-shot CoT" [shape=box];
  "Use Self-Consistency" [shape=box];
  "Use technique from table" [shape=box];

  "Problem type?" -> "Direct answer worked?" [label="simple"];
  "Problem type?" -> "Use technique from table" [label="math/logic/creative"];
  "Direct answer worked?" -> "Use direct prompting" [label="yes"];
  "Direct answer worked?" -> "Need confidence?" [label="no"];
  "Need confidence?" -> "Use Self-Consistency" [label="yes, high stakes"];
  "Need confidence?" -> "Use Zero-shot CoT" [label="no, just need better"];
}

Sponsors

Details

Repository
github.com/guia-matthieu/clawfu-skills
First seen
Jun 3, 2026

More from guia-matthieu/clawfu-skills

All 96

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs