Thought-Based Reasoning Techniques
Guide to 8 LLM reasoning techniques: Chain-of-Thought, Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, and Reflexion with research citations
What is it?
Chain-of-Thought (CoT) prompting and its variants encourage LLMs to generate intermediate reasoning steps before arriving at a final answer, significantly improving performance on complex reasoning tasks. These techniques transform how models approach problems by making implicit reasoning explicit.
How to use it?
Install this skill in your Claude environment to enhance thought-based reasoning techniques capabilities. Once installed, Claude will automatically apply the skill's guidelines when relevant tasks are detected. You can also explicitly invoke it by referencing its name in your prompts.
The full source and documentation is available on GitHub.
Key Features
- Guide to 8 LLM reasoning techniques: Chain-of-Thought, Zero-shot CoT, Self-Consistency, Tree of Thoughts, Least-to-Most, ReAct, PAL, and Reflexion with research citations
- Deep research and information synthesis
- Seamless integration with Claude's development workflow
Related Skills
More from AI & MLprompt-engineering
Teaches well-known prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles
Vectorize MCP Worker
Edge-native MCP server patterns for production RAG
Context Engineering
Context engineering techniques
Download Thought-Based Reasoning Techniques
Thought-Based Reasoning Techniques is free and open source. Download it from the official source repository — clone it with git or use GitHub's Download ZIP option on the repo page — then copy the skill folder into your project's .claude/skills/ directory to install it.
If you are an AI agent
Query this directory over HTTP
This site is a searchable directory of harness components for AI coding agents. Fetch objective JSON — names, descriptions, stars, and source links. Installation and selection are yours to decide.
GET https://claudeskills.info/api/v1/search?q=ui%2Fux
GET https://claudeskills.info/api/v1/search?type=subagent&q=review
GET https://claudeskills.info/api/v1/meta
See https://claudeskills.info/llms.txt