# Ask Questions If Underspecified

> Clarify requirements before implementing. Use when serious doubts arise.

- Skill: `diegosouzapw/ask-questions-if-underspecified-2` (Agent Skill, multi-file: 5 files)
- Install (CLI): `npx skillmds@latest add diegosouzapw/ask-questions-if-underspecified-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/diegosouzapw/ask-questions-if-underspecified-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector CAUTION)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools, Productivity
- Author: diegosouzapw (https://skillmd.com/u/diegosouzapw)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/diegosouzapw/ask-questions-if-underspecified-2

---


# Ask Questions If Underspecified

## Goal

Ask the minimum set of clarifying questions needed to avoid wrong work; do not start implementing until the must-have questions are answered (or the user explicitly approves proceeding with stated assumptions).

## Workflow

### 1) Decide whether the request is underspecified

Treat a request as underspecified if after exploring how to perform the work, some or all of the following are not clear:
- Define the objective (what should change vs stay the same)
- Define "done" (acceptance criteria, examples, edge cases)
- Define scope (which files/components/users are in/out)
- Define constraints (compatibility, performance, style, deps, time)
- Identify environment (language/runtime versions, OS, build/test runner)
- Clarify safety/reversibility (data migration, rollout/rollback, risk)

If multiple plausible interpretations exist, assume it is underspecified.

### 2) Ask must-have questions first (keep it small)

Ask 1-5 questions in the first pass. Prefer questions that eliminate whole branches of work.

Use the `question` tool to present structured choices:
- Offer multiple-choice options with clear labels
- Mark recommended defaults with "(Recommended)" in the label
- Use `multiple: true` when the user can select several options
- The user can always select "Other" for custom input

### 3) Pause before acting

Until must-have answers arrive:
- Do not run commands, edit files, or produce a detailed plan that depends on unknowns
- Do perform a clearly labeled, low-risk discovery step only if it does not commit you to a direction (e.g., inspect repo structure, read relevant config files)

If the user explicitly asks you to proceed without answers:
- State your assumptions as a short numbered list
- Ask for confirmation; proceed only after they confirm or correct them

### 4) Confirm interpretation, then proceed

Once you have answers, restate the requirements in 1-3 sentences (including key constraints and what success looks like), then start work.

## Anti-patterns

- Don't ask questions you can answer with a quick, low-risk discovery read (e.g., configs, existing patterns, docs).
- Don't ask open-ended questions if a tight multiple-choice or yes/no would eliminate ambiguity faster.