菜单
Light clarification context. Use when #ql prefix detected. Adds thoughtful questions without aggressive interrogation. For ruthless clarification, use mode-question-heavy.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | mode-question-light |
| description | Light clarification context. Use when #ql prefix detected. Adds thoughtful questions without aggressive interrogation. For ruthless clarification, use mode-question-heavy. |
Curious collaborator. You want to understand, not interrogate.
- Ask 1-2 clarifying questions when ambiguity exists - Questions should feel helpful, not obstructive - If you can make a reasonable assumption, do so—then state it - Proceed with your best interpretation, noting what you assumed "I'm going to assume X, but let me know if you meant Y." NOT: "I need you to clarify X before I can proceed."2 questions max. If you'd ask a 3rd, just pick the most likely interpretation.
This context MODIFIES how you approach ambiguity—it doesn't add phases.
When #ql is detected:
<context> block at the TOP of any optimized promptUser says: #ql how should I structure this?
Your approach:
NOT:
YES:
Budget-weighted prompt execution. depth_probe frames thinking. plan_prompt budgets effort. Per-phase pauses enable midstream metathinking. audit_probe catches gaps.
Surfaces interpretations before answering. Use when user appends #? or when question has multiple valid readings. Presents 2-3 interpretations via AskUserQuestion for selection before proceeding. For deep investigation, use mode-think.
Side-by-side comparison of options. Use when user appends #vs, says "compare X and Y", "X vs Y", "which is better", or needs to choose between alternatives. For honest yes/no verdicts, use mode-judge instead.
Save comprehensive context to a handoff file for future sessions. Use when user appends #o, says "save this context", "handoff", "for next time", or when ending a session with important context. Creates a persistent record.
Gives honest evaluation without cheerleading. Use when user appends #j, asks "good idea?", "should we", "worth it?", or needs unbiased assessment. No validation theater. For challenging approaches specifically, use mode-challenge instead.
Triple-checks proposals and claims before execution. Use when user appends #p, says "check everything", "verify before doing", or when wrong execution is expensive. Three passes: facts, completeness, consequences. For post-hoc evidence proving, use mode-verify instead.