prompt-engineerlisted

Design, optimize, test, and evaluate prompts for large language models. Use when: (1) crafting or refining system prompts, user prompts, or prompt templates, (2) optimizing token usage or cost of existing prompts, (3) designing few-shot examples or chain-of-thought reasoning, (4) setting up prompt evaluation, A/B testing, or regression testing, (5) building production prompt management systems (versioning, monitoring, safety), (6) debugging inconsistent or low-quality LLM outputs, (7) selecting prompt patterns (zero-shot, few-shot, CoT, ToT, ReAct, role-based). Triggers on: prompt engineering, optimize prompt, reduce tokens, prompt template, few-shot, chain-of-thought, prompt evaluation, A/B test prompts, prompt versioning.
OpenCoven/coven · ★ 47 · AI & Automation · score 76

Install: claude install-skill OpenCoven/coven

# Prompt Engineer Craft and optimize LLM prompts for maximum effectiveness, consistency, and cost efficiency. ## Core Workflow ### 1. Requirements Analysis Before writing or editing any prompt: 1. Identify the **use case** — what task the prompt must accomplish 2. Define **success criteria** — accuracy target, format requirements, tone 3. Understand **constraints** — token budget, latency ceiling, cost limit, model choice 4. Review **existing prompts** and their failure modes (if any) 5. Determine **safety requirements** — input validation, output filtering, injection defense ### 2. Prompt Design Select the appropriate pattern based on task complexity. See `references/patterns.md` for detailed guidance on each. | Complexity | Pattern | When to Use | |-----------|---------|-------------| | Simple | Zero-shot | Clear task, model already knows the domain | | Medium | Few-shot | Specific format or style needed | | Complex | Chain-of-thought | Multi-step reasoning required | | Branching | Tree-of-thought | Multiple valid approaches to explore | | Agentic | ReAct | Tool use + reasoning interleaved | | Safety | Constitutional AI | Output must pass ethical/policy filters | Design principles: - **Instruction clarity** — state the task, constraints, and output format explicitly - **Minimal tokens** — every token must earn its place; compress without losing meaning - **Modular structure** — separate system prompt, context, instructions, and examples - **Variable placeholders**