メニュー
Prevents the agent from making assumptions by forcing structured clarifying questions before acting. Use when the user wants thorough spec-gathering, disambiguation, or wants the agent to ask before assuming. Applies to any task type.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Propose a Conventional Commit message for the staged changes, then commit only after confirmation.
Creates an implementation plan from a PRD or a task description. Researches codebase context, clarifies ambiguities, and outputs a phased plan with vertical slices and acceptance criteria. Use when the user wants to plan a feature, break down a PRD, create an implementation plan, or mentions "tracer bullets".
Creates a PRD through structured clarification, codebase exploration, and module design, then saves it as a local Markdown file. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
Dispatches multiple subagents in parallel for 2+ confirmed-independent, each-substantial failures or investigation targets that share no state or sequential dependency. Use when the work splits cleanly and each part is big enough to justify a separate agent.
Decides how to integrate a finished branch — merge, pull request, keep, or discard — once tests pass. Use when implementation work on a branch is complete and you need to decide what happens to it next.
Acts on code-review feedback (from a human, a PR comment, or an AI reviewer) by verifying each item against the codebase before implementing, and asking when items are unclear. Use when receiving code review comments, PR feedback, or suggestions from another reviewer — before implementing any of them.
| name | clarify |
| description | Prevents the agent from making assumptions by forcing structured clarifying questions before acting. Use when the user wants thorough spec-gathering, disambiguation, or wants the agent to ask before assuming. Applies to any task type. |
Never assume — always ask. Before acting on any task, identify ambiguities and unknowns, then resolve them through structured questions. Walk down each branch of the decision tree, resolving dependencies between decisions one-by-one. Use this skill when clarification is the task itself or when thorough spec-gathering is needed — create-plan and write-prd embed a lighter clarification pass scoped to their own work.
Ask questions in rounds, each round drilling deeper based on prior answers. Stop as soon as the decision tree is resolved, even after a single round — do not pad with extra rounds. Continue only while unresolved branches remain.
Identify what is ambiguous or underspecified in the user's request. Ask the biggest unknowns first.
Based on prior answers, ask follow-up questions on remaining gaps, edge cases, or conflicting constraints. Confirm critical decisions before proceeding. Once no unresolved branches remain, stop.
Update the current plan or document with every decision made, then proceed with the task.
Follow the canonical clarification question rules: explore before asking, always recommend, context before question, structured over free-text, max 5 questions per round, stop when resolved, and the declined-answer fallback.
