From prompt-architecture
Outlines anatomy of effective system prompts including role, context, behavioral rules, output specs, examples, principles, and common mistakes. Useful for AI product prompt design.
npx claudepluginhub owl-listener/ai-design-skills --plugin prompt-architectureThis skill uses the workspace's default tool permissions.
A system prompt is the most important piece of design in an AI product. It defines who the AI is, what it knows, how it behaves, and what it produces. It's the equivalent of a brand guide, interaction spec, and behavioral contract rolled into one document.
Generates production-ready system prompts from user requirements like purpose, domain, output, and constraints. Determines single or multi-prompt architectures and queries for missing details.
Transforms vague prompts into structured ones with roles, task decomposition, output formats, constraints, and quality checks. Useful for inconsistent AI outputs, multi-step reasoning, or safety guardrails.
Designs, optimizes, and tests AI model prompts using techniques like few-shot learning, chain-of-thought, structured output, and role-based prompting. Useful for improving LLM responses via /prompt or related requests.
Share bugs, ideas, or general feedback.
A system prompt is the most important piece of design in an AI product. It defines who the AI is, what it knows, how it behaves, and what it produces. It's the equivalent of a brand guide, interaction spec, and behavioral contract rolled into one document.
A well-structured system prompt has distinct sections, each serving a specific purpose: 1. Identity and Role Who is the AI? What's its purpose? This anchors everything that follows.