ralph-tui-prd
Generate a Product Requirements Document (PRD) for ralph-tui task orchestration. Creates PRDs with user stories that can be converted to beads issues or prd.json for automated execution. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out.
下記のコマンドをコピーしてターミナル(Mac/Linux)または PowerShell(Windows)に貼り付けてください。 ダウンロード → 解凍 → 配置まで全自動。
mkdir -p ~/.claude/skills && cd ~/.claude/skills && curl -L -o ralph-tui-prd.zip https://jpskill.com/download/20880.zip && unzip -o ralph-tui-prd.zip && rm ralph-tui-prd.zip
$d = "$env:USERPROFILE\.claude\skills"; ni -Force -ItemType Directory $d | Out-Null; iwr https://jpskill.com/download/20880.zip -OutFile "$d\ralph-tui-prd.zip"; Expand-Archive "$d\ralph-tui-prd.zip" -DestinationPath $d -Force; ri "$d\ralph-tui-prd.zip"
完了後、Claude Code を再起動 → 普通に「動画プロンプト作って」のように話しかけるだけで自動発動します。
💾 手動でダウンロードしたい(コマンドが難しい人向け)
- 1. 下の青いボタンを押して
ralph-tui-prd.zipをダウンロード - 2. ZIPファイルをダブルクリックで解凍 →
ralph-tui-prdフォルダができる - 3. そのフォルダを
C:\Users\あなたの名前\.claude\skills\(Win)または~/.claude/skills/(Mac)へ移動 - 4. Claude Code を再起動
⚠️ ダウンロード・利用は自己責任でお願いします。当サイトは内容・動作・安全性について責任を負いません。
🎯 このSkillでできること
下記の説明文を読むと、このSkillがあなたに何をしてくれるかが分かります。Claudeにこの分野の依頼をすると、自動で発動します。
📦 インストール方法 (3ステップ)
- 1. 上の「ダウンロード」ボタンを押して .skill ファイルを取得
- 2. ファイル名の拡張子を .skill から .zip に変えて展開(macは自動展開可)
- 3. 展開してできたフォルダを、ホームフォルダの
.claude/skills/に置く- · macOS / Linux:
~/.claude/skills/ - · Windows:
%USERPROFILE%\.claude\skills\
- · macOS / Linux:
Claude Code を再起動すれば完了。「このSkillを使って…」と話しかけなくても、関連する依頼で自動的に呼び出されます。
詳しい使い方ガイドを見る →- 最終更新
- 2026-05-18
- 取得日時
- 2026-05-18
- 同梱ファイル
- 1
📖 Skill本文(日本語訳)
※ 原文(英語/中国語)を Gemini で日本語化したものです。Claude 自身は原文を読みます。誤訳がある場合は原文をご確認ください。
[Skill 名] ralph-tui-prd
Ralph TUI PRDジェネレーター
ralph-tui を介したAIエージェント実行に最適化された、詳細な製品要件定義書(PRD)を作成します。
作業内容
- ユーザーから機能の説明を受け取ります。
- 3〜5個の必須の明確化質問(アルファベット付きの選択肢)を一度に1セットずつ尋ねます。
- 常に品質ゲートについて尋ねます(どのコマンドが合格しなければならないか)。
- 各回答の後、必要に応じて追加の質問をします(適応的な探索)。
- 十分なコンテキストが得られたら、構造化されたPRDを生成します。
- TUI解析のために、PRDを
[PRD]...[/PRD]マーカーで囲んで出力します。
重要: 実装を開始しないでください。PRDを作成するだけです。
ステップ1:明確化質問(反復的)
質問は一度に1セットずつ尋ねます。各回答は、次の質問に影響を与える必要があります。以下の点に焦点を当てます。
- 問題/目標: これは何の問題を解決しますか?
- コア機能: 主要なアクションは何ですか?
- スコープ/境界: 何をしてはいけませんか?
- 成功基準: 完了したことをどのように判断しますか?
- 統合: 既存の機能とどのように適合しますか?
- 品質ゲート: 各ストーリーでどのコマンドが合格しなければなりませんか?(必須)
質問の形式は以下の通りです。
1. この機能の主な目標は何ですか?
A. ユーザーオンボーディング体験の向上
B. ユーザー定着率の向上
C. サポート負担の軽減
D. その他: [具体的に記述してください]
2. ターゲットユーザーは誰ですか?
A. 新規ユーザーのみ
B. 既存ユーザーのみ
C. すべてのユーザー
D. 管理者ユーザーのみ
これにより、ユーザーは「1A, 2C」と応答して迅速な反復が可能になります。
品質ゲートの質問(必須)
常に品質ゲートについて尋ねます。これらはプロジェクト固有のものです。
各ユーザーストーリーでどの品質コマンドが合格しなければなりませんか?
A. pnpm typecheck && pnpm lint
B. npm run typecheck && npm run lint
C. bun run typecheck && bun run lint
D. その他: [コマンドを具体的に記述してください]
UIストーリーの場合、ブラウザ検証を含めるべきですか?
A. はい、dev-browserスキルを使用して視覚的に検証します
B. いいえ、自動テストで十分です
適応的な質問
各応答の後、以下を決定します。
- 追加の質問をする(回答が複雑さを示している場合)
- 新しい側面について尋ねる(現在の領域が明確な場合)
- PRDを生成する(十分なコンテキストがある場合)
通常、2〜4ラウンドの質問が必要です。
ステップ2:PRDの構造
以下のセクションでPRDを生成します。
1. はじめに/概要
機能の簡単な説明と、それが解決する問題。
2. 目標
具体的で測定可能な目標(箇条書き)。
3. 品質ゲート
重要: すべてのユーザーストーリーで合格しなければならないコマンドをリストします。
## 品質ゲート
これらのコマンドは、すべてのユーザーストーリーで合格しなければなりません。
- `pnpm typecheck` - 型チェック
- `pnpm lint` - Linting
UIストーリーの場合、以下も含まれます。
- dev-browserスキルを使用してブラウザで検証する
このセクションは、変換ツール(ralph-tui-create-json、ralph-tui-create-beads)によって抽出され、各ストーリーの受け入れ基準に追加されます。
4. ユーザーストーリー
各ストーリーには以下が必要です。
- タイトル: 短く説明的な名前
- 説明: 「[ユーザー]として、[機能]を[メリット]のために行いたい」
- 受け入れ基準: 「完了」の意味を検証可能なチェックリスト
各ストーリーは、1回の集中的なAIエージェントセッションで実装できるほど小さいものであるべきです。
形式:
### US-001: [タイトル]
**説明:** [ユーザー]として、[機能]を[メリット]のために行いたい。
**受け入れ基準:**
- [ ] 特定の検証可能な基準
- [ ] 別の基準
注: 個々のストーリーの基準に品質ゲートコマンドを含めないでください。それらは品質ゲートセクションで一度定義され、変換中に自動的に適用されます。
重要:
- 受け入れ基準は検証可能でなければならず、曖昧であってはなりません。
- 「正しく動作する」は良くありません。
- 「ボタンは削除前に確認ダイアログを表示する」は良いです。
- 各ストーリーは独立して完了可能であるべきです。
5. 機能要件
特定の機能の番号付きリスト:
- 「FR-1: システムはユーザーが〜できるようにしなければならない」
- 「FR-2: ユーザーがXをクリックすると、システムは〜しなければならない」
明示的かつ曖昧さがないようにしてください。
6. 非目標(スコープ外)
この機能に含まれないもの。スコープ管理にとって重要です。
7. 技術的考慮事項(オプション)
- 既知の制約または依存関係
- 既存システムとの統合ポイント
- パフォーマンス要件
8. 成功指標
成功はどのように測定されますか?
9. 未解決の質問
残っている質問や明確化が必要な領域。
AIエージェント向けに記述する
PRDはralph-tuiを介してAIコーディングエージェントによって実行されます。したがって、以下の点に注意してください。
- 明示的かつ曖昧さがないようにしてください。
- ユーザーストーリーは小さいものにしてください(1回のセッションで完了可能)。
- 受け入れ基準は可能な限り機械で検証可能である必要があります。
- 既知の場合は特定のファイルパスを含めてください。
- プロジェクト内の既存のコードパターンを参照してください。
出力形式
重要: 最終的なPRDをTUI解析用のマーカーで囲んでください。
[PRD]
# PRD: Feature Name
## Overview
...
## Quality Gates
...
## User Stories
...
[/PRD]
ファイル命名: TUIは ./tasks/prd-[feature-name].md に保存します。
会話フローの例
ユーザー: TUIにダークモードを追加するためのPRDを作成してください。
アシスタント: ダークモードのPRD作成をお手伝いします。いくつか質問させてください。
-
主な目標は何ですか? A. 長時間のセッションでの目の疲れを軽減する B. システムのテーマ設定に合わせる C. 視覚的なカスタマイズを提供する D. その他
-
設定は永続化されるべきですか? A. はい、設定ファイルに保存する B. いいえ、セッションのみ C. システム設定に従う
ユーザー: 1A, 2A
アシスタント: 素晴らしいです!あといくつか質問です。
-
どのコンポーネントがダークモードをサポートする必要がありますか? A. すべてのTUIコンポーネント B. メインの実行ビューのみ C. メインビュー + 設定 D. その他
-
各ストーリーでどの品質コマンドが合格しなければなりませんか? A. pnpm typecheck && pnpm lint B. npm run typecheck && npm run lint C. bun run typecheck D. その他: [具体的に記述してください]
-
UIストーリーの場合、ブラウザ検証を含めますか? A. はい、dev-browserスキルを使用します B. いいえ、自動テストで十分です
ユーザー: 3A, 4A, 5A
アシスタント: 完璧です。PRDを生成するのに十分な情報があります。
[PRD]
PRD: ダークモード
(原文がここで切り詰められています)
📜 原文 SKILL.md(Claudeが読む英語/中国語)を展開
Ralph TUI PRD Generator
Create detailed Product Requirements Documents optimized for AI agent execution via ralph-tui.
The Job
- Receive a feature description from the user
- Ask 3-5 essential clarifying questions (with lettered options) - one set at a time
- Always ask about quality gates (what commands must pass)
- After each answer, ask follow-up questions if needed (adaptive exploration)
- Generate a structured PRD when you have enough context
- Output the PRD wrapped in
[PRD]...[/PRD]markers for TUI parsing
Important: Do NOT start implementing. Just create the PRD.
Step 1: Clarifying Questions (Iterative)
Ask questions one set at a time. Each answer should inform your next questions. Focus on:
- Problem/Goal: What problem does this solve?
- Core Functionality: What are the key actions?
- Scope/Boundaries: What should it NOT do?
- Success Criteria: How do we know it's done?
- Integration: How does it fit with existing features?
- Quality Gates: What commands must pass for each story? (REQUIRED)
Format Questions Like This:
1. What is the primary goal of this feature?
A. Improve user onboarding experience
B. Increase user retention
C. Reduce support burden
D. Other: [please specify]
2. Who is the target user?
A. New users only
B. Existing users only
C. All users
D. Admin users only
This lets users respond with "1A, 2C" for quick iteration.
Quality Gates Question (REQUIRED)
Always ask about quality gates - these are project-specific:
What quality commands must pass for each user story?
A. pnpm typecheck && pnpm lint
B. npm run typecheck && npm run lint
C. bun run typecheck && bun run lint
D. Other: [specify your commands]
For UI stories, should we include browser verification?
A. Yes, use dev-browser skill to verify visually
B. No, automated tests are sufficient
Adaptive Questioning
After each response, decide whether to:
- Ask follow-up questions (if answers reveal complexity)
- Ask about a new aspect (if current area is clear)
- Generate the PRD (if you have enough context)
Typically 2-4 rounds of questions are needed.
Step 2: PRD Structure
Generate the PRD with these sections:
1. Introduction/Overview
Brief description of the feature and the problem it solves.
2. Goals
Specific, measurable objectives (bullet list).
3. Quality Gates
CRITICAL: List the commands that must pass for every user story.
## Quality Gates
These commands must pass for every user story:
- `pnpm typecheck` - Type checking
- `pnpm lint` - Linting
For UI stories, also include:
- Verify in browser using dev-browser skill
This section is extracted by conversion tools (ralph-tui-create-json, ralph-tui-create-beads) and appended to each story's acceptance criteria.
4. User Stories
Each story needs:
- Title: Short descriptive name
- Description: "As a [user], I want [feature] so that [benefit]"
- Acceptance Criteria: Verifiable checklist of what "done" means
Each story should be small enough to implement in one focused AI agent session.
Format:
### US-001: [Title]
**Description:** As a [user], I want [feature] so that [benefit].
**Acceptance Criteria:**
- [ ] Specific verifiable criterion
- [ ] Another criterion
Note: Do NOT include quality gate commands in individual story criteria - they are defined once in the Quality Gates section and applied automatically during conversion.
Important:
- Acceptance criteria must be verifiable, not vague
- "Works correctly" is bad
- "Button shows confirmation dialog before deleting" is good
- Each story should be independently completable
5. Functional Requirements
Numbered list of specific functionalities:
- "FR-1: The system must allow users to..."
- "FR-2: When a user clicks X, the system must..."
Be explicit and unambiguous.
6. Non-Goals (Out of Scope)
What this feature will NOT include. Critical for managing scope.
7. Technical Considerations (Optional)
- Known constraints or dependencies
- Integration points with existing systems
- Performance requirements
8. Success Metrics
How will success be measured?
9. Open Questions
Remaining questions or areas needing clarification.
Writing for AI Agents
The PRD will be executed by AI coding agents via ralph-tui. Therefore:
- Be explicit and unambiguous
- User stories should be small (completable in one session)
- Acceptance criteria must be machine-verifiable where possible
- Include specific file paths if you know them
- Reference existing code patterns in the project
Output Format
CRITICAL: Wrap the final PRD in markers for TUI parsing:
[PRD]
# PRD: Feature Name
## Overview
...
## Quality Gates
...
## User Stories
...
[/PRD]
File naming: The TUI will save to ./tasks/prd-[feature-name].md
Example Conversation Flow
User: Create a PRD for adding dark mode to the TUI
Assistant: I'll help you create a PRD for dark mode. Let me ask a few questions:
-
What is the primary goal? A. Reduce eye strain for long sessions B. Match system theme preference C. Provide visual customization D. Other
-
Should the setting persist? A. Yes, save to config file B. No, session only C. Follow system preference
User: 1A, 2A
Assistant: Great! A couple more questions:
-
Which components need dark mode support? A. All TUI components B. Only the main execution view C. Main view + settings D. Other
-
What quality commands must pass for each story? A. pnpm typecheck && pnpm lint B. npm run typecheck && npm run lint C. bun run typecheck D. Other: [specify]
-
For UI stories, include browser verification? A. Yes, use dev-browser skill B. No, automated tests sufficient
User: 3A, 4A, 5A
Assistant: Perfect, I have enough to generate the PRD.
[PRD]
PRD: Dark Mode for Ralph TUI
Overview
Add dark mode support to ralph-tui to reduce eye strain during long orchestration sessions. The feature will apply to all TUI components and persist the user's preference in the config file.
Goals
- Provide a comfortable viewing experience in low-light environments
- Persist theme preference across sessions
- Apply consistent styling to all TUI components
Quality Gates
These commands must pass for every user story:
pnpm typecheck- Type checkingpnpm lint- Linting
For UI stories, also include:
- Verify in browser using dev-browser skill
User Stories
US-001: Add theme configuration
Description: As a user, I want to set my preferred theme (light/dark) so that it persists across sessions.
Acceptance Criteria:
- [ ] Add
themefield to.ralph-tui.yamlschema - [ ] Support values: "light", "dark", "system"
- [ ] Default to "light" for backwards compatibility
US-002: Create dark theme color palette
Description: As a user, I want a soft-contrast dark theme that's easy on the eyes.
Acceptance Criteria:
- [ ] Define dark palette with gray tones (not pure black)
- [ ] Ensure sufficient contrast ratios (WCAG AA)
- [ ] Colors work well for all UI states (selected, hover, disabled)
US-003: Apply theme to TUI components
Description: As a user, I want all TUI components to respect my theme preference.
Acceptance Criteria:
- [ ] Header component uses theme colors
- [ ] Task list uses theme colors
- [ ] Detail panels use theme colors
- [ ] Progress bar uses theme colors
- [ ] Dialogs use theme colors
US-004: Add theme toggle in settings
Description: As a user, I want to toggle themes from within the TUI settings.
Acceptance Criteria:
- [ ] Theme option visible in settings view
- [ ] Changes apply immediately without restart
- [ ] Changes persist to config file
Functional Requirements
- FR-1: Theme setting must be readable from
.ralph-tui.yaml - FR-2: Theme must apply on TUI startup
- FR-3: Theme changes in settings must apply immediately
- FR-4: All text must maintain readability in both themes
Non-Goals
- System theme auto-detection (future enhancement)
- Custom color schemes beyond light/dark
- Per-component theme overrides
Technical Considerations
- Use existing OpenTUI theming capabilities if available
- Consider creating a ThemeContext for React components
- Minimize re-renders when theme changes
Success Metrics
- All components render correctly in dark mode
- No accessibility contrast issues
- Theme persists across sessions
Open Questions
- Should we detect system theme preference automatically in v2? [/PRD]
Checklist
Before outputting the PRD:
- [ ] Asked clarifying questions with lettered options
- [ ] Asked about quality gates (REQUIRED)
- [ ] Asked follow-up questions when needed
- [ ] Quality Gates section included with project-specific commands
- [ ] User stories are small and independently completable
- [ ] User stories do NOT include quality gate commands (they're in the Quality Gates section)
- [ ] Functional requirements are numbered and unambiguous
- [ ] Non-goals section defines clear boundaries
- [ ] PRD is wrapped in
[PRD]...[/PRD]markers