thought-based-reasoning
NeoLabHQ · AI & ML
该技能提供了链式思考提示及其变体的结构化指南，用于改进大语言模型的推理能力。包含决策矩阵、提示模板和研究验证的模式，涵盖零样本CoT、自洽性、思维树和ReAct等技术。文档帮助用户为不同推理任务选择合适方法。
This skill provides a structured guide to Chain-of-Thought prompting and its variants for improving LLM reasoning. It includes decision matrices, prompt templates, and research-backed patterns for techniques like Zero-shot CoT, Self-Consistency, Tree of Thoughts, and ReAct. The documentation helps users select appropriate methods for different reasoning tasks.
npx skills add https://github.com/NeoLabHQ/context-engineering-kit --skill thought-based-reasoning
星标 1100 · 安装量 594