Master prompt engineering: chain-of-thought, few-shot learning, system prompts, structured output, tool use, and prompt optimization for different models.
When to use this skill
- Designing a system prompt
- Using chain-of-thought prompting
- Getting structured output from an LLM
Core concepts
This skill provides guidance on llm prompting best practices, patterns, and common pitfalls. It is designed to be loaded on demand when a relevant task is detected.
Installation
curl -LO https://opencode-skills.example/downloads/ai-ml/llm-prompting.zip
unzip llm-prompting.zip -d ~/.config/opencode/skills/Restart OpenCode — the skill loads automatically.
When it triggers
- designing a system prompt
- using chain-of-thought prompting
- getting structured output from an LLM