ワンクリックで
refine-requirement
Updates an existing product requirement document based on user feedback. Triggered by: nvst refine requirement.
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
Updates an existing product requirement document based on user feedback. Triggered by: nvst refine requirement.
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
Fixes one issue from the iteration issues list by reproducing, diagnosing, and resolving it. Invoked by: bun nvst fix issue.
Refines .agents/PROJECT_CONTEXT.md via editor mode or challenge mode. Challenge mode validates the document against the actual codebase and detects compliance issues. Triggered by: nvst refine project-context.
Leads a structured ideation interview to surface feature/project ideas and update ROADMAP.md with new candidates.
Creates or updates .agents/PROJECT_CONTEXT.md with project conventions, tech stack, code standards, testing strategy, and product architecture. Triggered by: nvst create project-context.
Drive interactive approval of the prototype by updating project context and roadmap artifacts after a completed iteration.
Load the refactor plan from it_{iteration}_audit.json and invoke the agent to apply code changes.
| name | refine-requirement |
| description | Updates an existing product requirement document based on user feedback. Triggered by: nvst refine requirement. |
| user-invocable | true |
Update it_{current_iteration}_product-requirement-document.md in place based on user feedback. The file must already exist; this skill does not create it from scratch.
Do NOT start implementing. Only update the document.
Two modes available — the agent asks at the start:
- Editor mode — apply specific changes requested by the user.
- Challenger mode — act as an independent critical reviewer: challenge assumptions, question scope, find gaps, and propose improvements. The user accepts or rejects each suggestion before anything is written.
Use Chain of Draft (CoD) for all internal reasoning steps performed while executing this skill.
.agents/state.json exists. If it does, read it to obtain requirement_definition.file (e.g. it_000001_product-requirement-document.md). If it does not exist, ask the user to provide the required information:
it_000037_product-requirement-document.md).agents/flow/{file}.define-requirement.state.json — requirement_definition.status stays "in_progress".Act as a second agent reviewing the document with fresh eyes. Do not apply any change without explicit user approval.
Challenge areas — examine each (in order):
FR-N that contradicts another or contradicts an acceptance criterion.Challenger output format — one observation at a time:
CRITICAL: Present findings one at a time. After delivering one finding, stop and wait for the user to respond before moving on. Do not queue or batch findings.
For each finding, format it as:
Challenge [N/total]: <area name>
Finding: <what the issue is>
Suggestion: <proposed change>
Accept / Reject / Discuss?
Ask only what is needed to understand the requested change.
1. What would you like to change or add?
A. Replace or rewrite a user story
B. Add a new user story (must be MVP-justified)
C. Remove a user story
D. Tighten acceptance criteria
E. Update goals or non-goals
F. Other: [describe]
2. If adding a user story — is it strictly necessary for the MVP?
[Open answer — skip if not adding stories]
3. Anything else to update in this pass?
[Open answer — skip if none]
US-NNN and FR-N entries only if a story is removed; otherwise keep existing IDs stable.define-requirement).Before saving:
US-NNN and FR-N numbering is consistent.agents/flow/it_{current_iteration}_product-requirement-document.mdstate.json not modified (status stays "in_progress")