
from reprompter
Turn messy prompts into structured, scoreable prompts or multi-agent plans; also reverse-engineer great outputs into reusable prompts.
RePrompter transforms raw or messy user prompts into structured, testable prompts. Supports three modes: Single (clean & score a single prompt), Repromptverse (plan and generate per-agent prompts for multi-agent orchestration), and Reverse (extract a prompt from an exemplar output). Includes templates, interview flows, success-criteria generation, and tooling for execution and evaluation.
Use when you need to improve prompt quality, create multi-agent teams with clear artifact contracts, generate verifiable success criteria, or reverse-engineer high-quality outputs into reproducible prompts. Avoid for simple Q&A or immediate execution-only tasks.
Designed for advanced agent runtimes and developer workflows: Claude Code (tmux/TeamCreate), OpenClaw (sessions_spawn), Codex CLI, and general assistant agents for prompt engineering and orchestration.
This skill has not been reviewed by our automated audit pipeline yet.