From prompt-architecture
Designs reusable, parameterized prompt templates for consistent LLM outputs. Covers anatomy, variables, patterns, composition, quality criteria, and artefacts.
How this skill is triggered — by the user, by Claude, or both
Slash command
/prompt-architecture:template-designThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
A prompt template is a reusable prompt structure with variable slots that get filled at runtime. Templates create consistency across similar tasks and make prompt management scalable.
A prompt template is a reusable prompt structure with variable slots that get filled at runtime. Templates create consistency across similar tasks and make prompt management scalable.
A template has:
Each variable should be:
{user_query} not {input1}Complex prompts can be built from smaller templates:
npx claudepluginhub owl-listener/ai-design-skills --plugin prompt-architectureCreates structured, reusable prompt templates for reliable LLM outputs in production systems using chain-of-thought and few-shot examples.
Creates .prompt files for LLM operations in Output SDK workflows, with YAML frontmatter for provider config and Liquid.js templating for dynamic content.
Designs reusable text, image, and video prompts with focus on clarity, control, cost, and reproducibility. Use when prompt quality is central to a feature or flow.