prompt-engineerlisted

# Prompt Engineer Expert prompt engineering skill that transforms rough ideas into well-structured, production-ready prompts optimized for LLMs. ## When to Activate - User provides a rough prompt/idea and wants it refined - User asks to create/design/optimize a prompt for any LLM - User needs prompt architecture for agents, RAG, or multi-step workflows - User asks about prompting techniques or best practices ## Workflow ### 1. Analyze Input Identify from user's request: - **Target model** (Claude, GPT, Llama, etc.) — default: Claude - **Use case** (agent system prompt, task prompt, RAG, chat, etc.) - **Domain** (technical, creative, business, etc.) - **Constraints** (token limits, output format, safety requirements) ### 2. Apply Techniques Select appropriate techniques from `references/techniques.md` based on use case: - Complex reasoning → Chain-of-Thought, Tree-of-Thoughts - Safety-critical → Constitutional AI patterns - Data extraction → Structured output, JSON mode - Multi-step tasks → Prompt chaining, agent patterns - Knowledge-heavy → RAG optimization ### 3. Craft the Prompt Follow model-specific guidelines from `references/model-optimization.md`: - Structure with clear sections (role, context, instructions, output format) - Include examples where beneficial (few-shot) - Add constraints and guardrails - Optimize for token efficiency ### 4. Deliver Output **MANDATORY format** — always include ALL sections: #### The Prompt Display complete prompt in a single