prompt-engineering-advanced

What problem does it solve?

This Skill helps practitioners craft deterministic, token-efficient prompts and structured reasoning pipelines to produce reliable, repeatable LLM outputs for complex tasks that require multi-step reasoning.

Core Features & Use Cases

• Advanced Reasoning Strategies: Practical guidance for Chain-of-Thought, Tree-of-Thought, Self-Consistency, and ReAct patterns to force or evaluate intermediate reasoning.
• Prompt Structure Frameworks: Copy-ready templates and guidance for RICE and CRISPE frameworks to specify role, instructions, context, and examples for persona-heavy or engineering tasks.
• Context Optimization: Techniques for context compression, delimiters, and reference anchoring to reduce token usage and improve model focus.
• Use Case: Ideal for designing prompts to refactor code, evaluate architectural options, generate technical analyses, or produce multi-path solutions that require evaluation and selection.

Quick Start

Use the prompt-engineering-advanced skill to create a RICE-structured prompt that asks the model to think step-by-step and propose three alternative solutions with pros and cons.