Ask Questions If Underspecified
SkillMediaUse this skill when scope ambiguity blocks progress in any SOP step (PRD, TDD, design, task decomposition). Produces a tight set of clarifying questions (max 5) that, once answered, unblock the next step. Avoids the failure mode where Agents proceed on assumption and produce wrong work. Chinese trigger examples: "需求不清", "需要澄清", "提问澄清", "范围不明", "信息不足要澄清", "ask the user". Do NOT use for exploration (use research), do NOT use to delay obvious work. Success = ≤ 5 questions, each decision-shaping, each tied to a specific PRD section.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the Ask Questions If Underspecified skill
What this skill tells your AI
The instructions your AI receives, as published by charliehzm/medharness in .claude/skills/ask-questions-if-underspecified/SKILL.md and read by ahel’s review.
The "stop and clarify" gate. Many AI Coding failures trace back to "Agent assumed X, X was wrong, 4 hours wasted." This skill catches that early.
Core principle
Only ask decision-shaping questions. If the answer changes nothing about what gets built, don't ask.
Question taxonomy
For each candidate question, classify:
| Type | Ask? | Example |
|---|---|---|
| Decision-shaping | YES | "Should L4 PHI be stored encrypted at rest or only redacted?" |
| Preference | Only if 2 acceptable paths | "Frontend React or Vue?" |
| Trivia | NO | "What color is the button?" (decide and move on) |
| Compliance-touching | ALWAYS | Anything touching tier / model / audit |
Workflow
- List unknowns surfaced from the upstream artifact (PRD / TDD / design).
- Classify each per the taxonomy.
- Keep at most 5 of type decision-shaping or compliance-touching.
- Phrase each question so the answer is bounded (multiple-choice or numeric).
- Format with AskUserQuestion tool when available; otherwise inline.
- Never ask "is this OK" / "should I proceed" — those are not clarifications.
Output
A list of ≤ 5 questions, each with:
- Header (≤ 12 chars chip label)
- Why it matters (one line)
- 2-4 mutually exclusive options (or "numeric input")
- Recommended default
Common failure modes
- Question dump — asking 15 questions exhausts the user. Cap at 5; everything else is your call.
- Open-ended phrasing — "What do you think about X?" produces non-actionable answers. Always bound.
- Asking after committing — questions came too late, work already started. Run this skill earlier in the SOP.
Signals
- GitHub stars
- 86
- Forks
- 8
- Last commit
- Jun 2026
Advanced
- Catalog kind
- skill
- Gateway key
ask-questions-if-underspecified- Source
- github.com/charliehzm/medharness