clarifying
Shared clarification discipline (grill-style) - one-question-at-a-time interrogation down the decision tree until shared understanding: facts self-researched, each decision put to the user with a recommended answer; standalone sessions end at a consensus summary with three exits (hand off to the main workflow / stop here / write notes to md), no forced deliverable. Referenced by requirement-analysis and quick-fix as their questioning discipline. Use standalone when the user wants an idea, plan or decision grilled into clarity question by question; not for divergent thinking-partner exploration (use exploring), nor for committed delivery work (go straight to requirement-analysis / quick-fix). / 共享澄清纪律(grill 式)——沿决策树一次一题逼近共识:事实自查、每个决策带推荐交用户裁决;独立会话以共识摘要 + 三出口收束(转主流程/就此结束/写入 md),不强制产出。被 requirement-analysis 与 quick-fix 引用作提问纪律。当用户想把一个想法/计划/决定逐题磨清楚时独立使用;发散式的思考陪伴用 exploring;已承诺交付的开发工作直接用 requirement-analysis / quick-fix。
Pinned to revision 095eb40b94ac, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/clarifying/SKILL.md
- skills/clarifying/agents/openai.yaml
- skills/clarifying/evals/evals.json
- skills/clarifying/evals/trigger-evals.json
Every link opens the file at its source, pinned to the revision this page describes.