{"skill":{"slug":"prompt-design-tuning","displayName":"Prompt Design Tuning","summary":"Collaboratively design, evaluate, iterate on, and recommend a final launch candidate for a target prompt under the principle of “human-gated, agent-executed”...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":124,"installsAllTime":0,"installsCurrent":0,"stars":1,"versions":1},"createdAt":1774605146253,"updatedAt":1774664188833},"latestVersion":{"version":"1.0.0","createdAt":1774605146253,"changelog":"Initial release: Provides a structured, human-gated workflow for prompt design and tuning.\n\n- Defines two main working modes: Design-Only and Execution, adapting to different project readiness levels.\n- Enforces separation between target prompts and judge prompts, with strict versioning and optimization logging requirements.\n- Outlines mandatory human approval gates at key decision points (task definition, prompt directions, high-cost evaluations, final launch).\n- Specifies required documentation, scripts, and reports for transparent, reusable prompt engineering.\n- Recommends inputs to collect for each project, ensuring clear task specs, evaluation plans, and cost control.","license":"MIT-0"},"metadata":null,"owner":{"handle":"abysscat-yj","userId":"s1786bce9ngax6fpbn81sf46yd83qhwg","displayName":"yuanjie","image":"https://avatars.githubusercontent.com/u/33748845?v=4"},"moderation":null}