prompt-design

# Prompt Design Turn a behavioral contract into the smallest production prompt stack that can express it. Return a pinned candidate and development cases; route behavioral claims to evaluation. ## Ownership - Use this skill for the instructions and context assembly shipped inside an LLM, RAG, or tool-using application: system and developer prompts, tool descriptions, examples, output schemas, memory summaries, and retrieved-context wrappers. - Use [product-loop](../product-loop/SKILL.md) first when the desired product behavior is unsettled, [technical-research](../technical-research/SKILL.md) for current provider or model semantics, and [threat-model](../threat-model/SKILL.md) when sensitive data or untrusted content crosses a trust boundary. - Use [agent-skills](../agent-skills/SKILL.md) to author a reusable `SKILL.md` package. Use [agent-project](../agent-project/SKILL.md) for repository-level agent instructions and configuration. - Use [agent-evaluation](../agent-evaluation/SKILL.md) to compare the frozen candidate against a baseline with repeated model runs. Prompt design prepares evidence and hypotheses; it does not prove behavior. ## Authority and Safety - Design is local and read-only by default. Do not call paid models, use credentials or customer data, change production prompts, publish provider prompt objects, or mutate external systems without explicit authorization for that boundary and cost. - Prompts are not security boundaries. Enforce authentication, auth...