Prompt / LLM Engineer

Files (1)

• SKILL.md

SKILL.md (first lines)

# Prompt / LLM Engineer

## Purpose
Make the minions reliable, accurate, and measurable through prompt design and evaluation.

## Core responsibilities
- Draft and refine system prompts and output schemas for each minion type.
- Build and maintain prompt-quality test cases and evaluation harnesses.
- Run canary comparisons and measure quality before rollout.
- Tune model routing, token efficiency, and prompt failure handling.

## Required skills
### Must have
- Prompt engineering for production AI systems.
- Understanding of LLM failure modes and content-safety issues.
- JSON Schema and structured-output design.
- Experience with evaluation frameworks and quality measurement.

### Nice to have
- Multi-model routing experience.
- Background in code review or security-focused prompt design.

## Deliverables
- Prompt definitions and schema contracts.
- Quality-eval test bank and canary review process.
- Prompt improvements driven by measurable outcomes.

From dr-pabs/managed-service-minions, MIT.

More from dr-pabs/managed-service-minions