Install
Quick install
npx skills add https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/customaize-agent/skills/thought-based-reasoningnpx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques" --agent claude-codenpx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques" --agent cursornpx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques" --agent codexnpx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques" --agent opencodenpx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques" --agent github-copilotnpx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques" --agent windsurfMore install options
Shorthand — useful for multi-skill repos:
npx skills add NeoLabHQ/context-engineering-kit --skill "Thought-Based Reasoning Techniques"Manual — clone the repo and drop the folder into your agent's skills directory:
git clone https://github.com/NeoLabHQ/context-engineering-kit.gitcp -r context-engineering-kit/plugins/customaize-agent/skills/thought-based-reasoning ~/.claude/skills/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 workflowView on GitHub
GitHub Stats
StarsForksLast UpdateAuthorNeoLabHQLicenseGPL-3.0Version1.0.0Categories
AI & MLDeveloper ToolsTags
chain-of-thoughtreasoningprompt-engineeringresearchllm-techniquesFeatures
Related Skills
More from AI & MLprompt-engineering
Teaches well-known prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles433NeoLabHQDeveloper ToolsAI & ML00
Vectorize MCP Worker
Edge-native MCP server patterns for production RAG12dannwaneriDeveloper ToolsAI & ML00
Context Engineering
Context engineering techniques8.3kmuratcankoylanDeveloper ToolsAI & ML00
---
Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/customaize-agent/skills/thought-based-reasoning
Author: NeoLabHQ
License: https://www.gnu.org/licenses/gpl-3.0.html
GitHub Stars: 433
Tags: chain-of-thought, reasoning, prompt-engineering, research, llm-techniques
SKILL.md source
--- name: Thought-Based Reasoning Techniques description: 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 --- # 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 workflowView on GitHub ### GitHub Stats StarsForksLast UpdateAuthorNeoLabHQLicenseGPL-3.0Version1.0.0 ### Categories AI & MLDeveloper Tools ### Tags chain-of-thoughtreasoningprompt-engineeringresearchllm-techniques ### Features ## Related Skills More from AI & ML ### prompt-engineering Teaches well-known prompt engineering techniques and patterns, including Anthropic best practices and agent persuasion principles 433NeoLabHQDeveloper ToolsAI & ML00 ### Vectorize MCP Worker Edge-native MCP server patterns for production RAG 12dannwaneriDeveloper ToolsAI & ML00 ### Context Engineering Context engineering techniques 8.3kmuratcankoylanDeveloper ToolsAI & ML00 --- **Source**: https://github.com/NeoLabHQ/context-engineering-kit/tree/master/plugins/customaize-agent/skills/thought-based-reasoning **Author**: NeoLabHQ **License**: https://www.gnu.org/licenses/gpl-3.0.html **GitHub Stars**: 433 **Tags**: chain-of-thought, reasoning, prompt-engineering, research, llm-techniques
Related skills 6
Firecrawl / firecrawl-build-scrape
Integrate Firecrawl `/scrape` for single-page extraction from product code
Firecrawl / firecrawl-build-onboarding
Set up Firecrawl credentials and SDK in a project for the first integration
Hugging Face / hugging-face-paper-publisher
Publish papers on HF Hub with model/dataset links
Firecrawl / firecrawl-build
Integrate Firecrawl into application code for web search, scraping, extraction, and browser interaction
Firecrawl / firecrawl-build-interact
Multi-step Firecrawl browser flows: clicks, form fills, pagination, and auth-aware navigation
Firecrawl / firecrawl-build-search
Integrate Firecrawl `/search` for query-first discovery with optional content hydration