ワンクリックで
spec
Interview the user one question at a time, walking the decision tree, to clarify a feature proposal before implementation
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。
メニュー
Interview the user one question at a time, walking the decision tree, to clarify a feature proposal before implementation
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
A method for organizing a prototype that illustrates an agentic, spec-driven PR review—the type a person employs to determine if a merge is acceptable without scrutinizing each alteration. Applicable when a user intends to create, outline, or develop a review interface, a review dashboard, a PR-review process, or a "verdict screen" for an agent-generated modification set, particularly one generated by a specification-driven development (SDD) workflow. Triggers encompass: "review flow", "PR review prototype", "review UI", "how should I present this review", "verdict-first review", "visualize the PR", or asking how a developer should review an agent's output. This is a METHOD skill — it tells you how to think about and lay out the prototype; it does not lock you to a single output format. Do NOT use for performing the code review itself (finding bugs, judging the author) — that is a different skill.
Reviews a pull request in two stages — first interrogating the author to verify they understand and can defend every decision in their own submission (catching AI-generated code forwarded without comprehension), then performing a structural design review of intent fidelity, abstractions, coupling, and failure behavior. The comprehension gate must pass before the design review runs. Use when reviewing a feature PR, vetting incoming code for author ownership, screening for AI slop, or running a deep structural review beyond what CI and linters cover.
Translate the spec into a complete, traceable set of acceptance criteria in EARS form
Capture feature-level design decisions and the technical constraints that follow, traceable to acceptance criteria
Stress-test the spec pipeline outputs against each other and the codebase before implementation begins
Generate an implementation task list from validated spec artifacts
| name | spec |
| description | Interview the user one question at a time, walking the decision tree, to clarify a feature proposal before implementation |
Walk down the decision tree, surfacing ambiguities, missing info, implicit assumptions, and edge cases through one-at-a-time questioning until the spec is implementable.
Pipeline position: proposal → spec → criteria → rules → review → plan
You prepare requirements for implementation by an AI coding agent.
Feature request: @file:spec/proposal.md
Scan the proposal and identify ambiguities, missing info, implicit assumptions, edge cases, and decision dependencies. Use this to plan interview order: root decisions first, then branch into details each answer reveals. Draft candidate behaviors to verify.
If the @file:spec/proposal.md does not exist, ask for the input and save it into that file.
Only ask if the answer changes at least one of:
If none, decide it yourself and record under "Resolved ambiguities" or "Explicit assumptions" with the rationale. Trivial questions waste turns and erode trust in the interview.
The criteria step depends on this section as its primary handoff. Treat it as a contract.
Complete only when ALL hold:
A clean spec has ZERO open questions. Before writing, do a final verification pass. If any item fails, return to the interview loop.
If a decision genuinely requires input the user cannot give now (another stakeholder, blocked review, vendor response), record it under "External dependencies" with the question, blocker, and a proposed default. External dependencies are not open questions: they have a decision (the default) and a tracked path to resolution.
Write to spec/spec.md: