Validates completed work against defined acceptance criteria. Use after completing a task that has specific success criteria defined in issues, specs, or task descriptions.
日本語の概要は準備中です。原文の説明を表示しています。
ash1794/vibe-engineering1642026年10月8日 更新
無料GitHub で公開
vibe-requirements-validator
Validates PRD, user stories, or feature requirements against SMART criteria. Use when reviewing requirements to catch vagueness before it causes expensive rework.
含まれるファイル（1）
- SKILL.md2.2 KB
SKILL.md（原文）
インストールする前に、エージェントに与えられる指示の中身を確認できます。
vibe-requirements-validator
Vague requirements cause expensive rework. Catch them early.
When to Use This Skill
- Reviewing a PRD or feature spec before implementation
- Writing acceptance criteria for user stories
- When you notice requirements like "make it fast" or "improve UX"
- Before estimating effort for a feature
When NOT to Use This Skill
- Internal technical tasks with clear scope
- Bug fixes (the bug IS the requirement)
- When requirements are already validated and approved
SMART Criteria
Score each requirement 1-5 on:
- Specific — Is it clear what exactly needs to be built? (Not "improve performance" but "reduce P95 latency to <200ms")
- Measurable — Can you objectively verify it's done? (Not "users like it" but "NPS score >40")
- Achievable — Can it be built with available resources and constraints?
- Relevant — Does it align with project goals and user needs?
- Time-bound — Is there a clear scope boundary? (Not "eventually" but "in v1.0")
Steps
-
List all requirements from the document
-
Score each on SMART (1-5 per dimension)
-
Flag issues:
- Score < 3 on any dimension → needs revision
- Measurability < 3 → most common failure, flag prominently
- Near-duplicates → consolidate
- Positioning statements masquerading as requirements → remove
-
Report:
Output Format
Requirements Validation: [Document Name]
Total Requirements: X Passing (avg >= 3.5): Y (Z%) Flagged: W
| ID | Requirement | S | M | A | R | T | Avg | Issue |
|---|---|---|---|---|---|---|---|---|
| FR-1 | "..." | 4 | 2 | 5 | 4 | 3 | 3.6 | Low measurability |
Top Issues
- Measurability crisis — X requirements have M < 3
- Near-duplicates — [list pairs]
- Not requirements — [positioning statements]
Recommended Revisions
| ID | Current | Suggested |
|---|---|---|
| FR-3 | "Improve load time" | "Reduce initial page load to <2s on 3G" |
レビュー
まだレビューはありません。使ってみた感想をお寄せください。
同じリポジトリのスキル
概要と使いどころ
Generates edge case, failure mode, and spec-driven test cases. Covers boundary values, nil inputs, concurrency, resource exhaustion, malformed data, and requirement-linked traceability tests. Use after happy-path tests exist and before claiming coverage is complete, when requirements lack tests, or before a security review.
日本語の概要は準備中です。原文の説明を表示しています。
ash1794/vibe-engineering1642026年10月8日 更新
Catches shortcuts and reward hacking — weakening or deleting tests to make them pass, hard-coding expected outputs, silently dropping requirements, or claiming work is done without running it. Use before declaring a task complete and whenever a test or requirement feels like it's in the way.
日本語の概要は準備中です。原文の説明を表示しています。
ash1794/vibe-engineering1642026年10月8日 更新
Safely integrates commits from parallel agent branches using sequential cherry-pick. Use after parallel work completes in isolated branches or worktrees.
日本語の概要は準備中です。原文の説明を表示しています。
ash1794/vibe-engineering1642026年10月8日 更新
Audits tests for concurrency safety — race conditions, shared mock state, cleanup ordering. Use when writing tests that involve goroutines, async operations, or shared mutable state.
日本語の概要は準備中です。原文の説明を表示しています。
ash1794/vibe-engineering1642026年10月8日 更新
Enforces tiered test coverage standards with three dimensions — line coverage by tier, spec-to-test traceability, and spec-to-code implementation mapping. Use before claiming code is complete.
日本語の概要は準備中です。原文の説明を表示しています。
ash1794/vibe-engineering1642026年10月8日 更新