Poser des questions si requis vague

VérifiéSûr

Clarifier les exigences avant d'implémenter. Poser des questions ciblées pour éviter un travail incorrect. À utiliser uniquement sur invocation explicite.

Spar Skills Guide Bot
DeveloppementIntermédiaire
2031/07/2026
Claude CodeCursorWindsurfCopilotCodex
#requirements-clarification#question-asking#underspecified-requests#agent-workflow#discovery

Recommandé pour

Notre avis

Guide l'assistant IA pour poser un minimum de questions ciblées avant de démarrer une tâche lorsque la demande est sous-spécifiée, et pour marquer une pause jusqu'à ce que les informations essentielles soient fournies.

Points forts

  • Se concentre sur les questions indispensables pour éviter un travail inutile.
  • Propose des formats à choix multiples et des réponses rapides comme `defaults`.
  • Évite de sur-solliciter l'utilisateur en recommandant une découverte préalable à faible risque.
  • Sépare clairement le nécessaire du facultatif pour réduire la friction.

Limites

  • Peut ajouter de la lenteur si l'utilisateur attend une action immédiate.
  • Dépend du jugement de l'assistant pour identifier correctement les ambiguïtés.
  • N'est efficace que si l'utilisateur répond réellement aux questions.
Quand l'utiliser

À utiliser quand une demande manque d'objectifs clairs, de périmètre, de contraintes ou de critères d'acceptation, et que l'utilisateur demande explicitement des clarifications.

Quand l'éviter

Ne pas utiliser pour des tâches bien spécifiées ou lorsque l'utilisateur souhaite une exécution immédiate en acceptant des hypothèses.

Analyse de sécurité

Sûr
Score qualité88/100

This skill only defines conversational workflow for requirement clarification; it does not instruct the agent to execute any commands, access files, or perform any potentially destructive actions. There are no references to external tools or data exfiltration.

Aucun point d'attention détecté

Exemples

Explicit clarification request
Before you start coding, this task seems underspecified. Use your ask-questions skill to ask me up to 5 clarifying questions with multiple-choice options and defaults.
Define done and scope
Please clarify what 'done' means for this feature and which files are in scope. Ask me the must-have questions from your ask-questions-if-underspecified skill, and I'll reply with 'defaults' if I don't care.
Invoke the skill explicitly
The user story below is vague. Trigger your ask-questions-if-underspecified skill and pause until I answer, but keep the questions scannable and offer a 'not sure' option.

Skill file:


name: ask-questions-if-underspecified description: Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.

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.

Make questions easy to answer:

  • Optimize for scannability (short, numbered questions; avoid paragraphs)
  • Offer multiple-choice options when possible
  • Suggest reasonable defaults when appropriate (mark them clearly as the default/recommended choice; **bold the recommended choice in the list, or if you present options in a code block, put a bold "Recommended" line immediately above the block and also tag defaults inside the block)
  • Include a fast-path response (e.g., reply defaults to accept all recommended/default choices)
  • Include a low-friction "not sure" option when helpful (e.g., "Not sure - use default")
  • Separate "Need to know" from "Nice to know" if that reduces friction
  • Structure options so the user can respond with compact decisions (e.g., 1b 2a 3c); restate the chosen options in plain language to confirm

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.

Question templates

  • "Before I start, I need: (1) ..., (2) ..., (3) .... If you don't care about (2), I will assume ...."
  • "Which of these should it be? A) ... B) ... C) ... (pick one)"
  • "What would you consider 'done'? For example: ..."
  • "Any constraints I must follow (versions, performance, style, deps)? If none, I will target the existing project defaults."
  • Use numbered questions with lettered options and a clear reply format
1) Scope?
a) Minimal change (default)
b) Refactor while touching the area
c) Not sure - use default
2) Compatibility target?
a) Current project defaults (default)
b) Also support older versions: <specify>
c) Not sure - use default

Reply with: defaults (or 1a 2a)

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
Skills similaires