rube-goldberg-tui-prd
Generate a Product Requirements Document (PRD) for rube-goldberg-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.
Best use case
rube-goldberg-tui-prd is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate a Product Requirements Document (PRD) for rube-goldberg-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.
Teams using rube-goldberg-tui-prd should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/rube-goldberg-tui-prd/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How rube-goldberg-tui-prd Compares
| Feature / Agent | rube-goldberg-tui-prd | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate a Product Requirements Document (PRD) for rube-goldberg-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.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
- name: Claude Code Action Official uses: anthropics/claude-code-action@v1 # Rube Goldberg TUI PRD Generator Create detailed Product Requirements Documents optimized for AI agent execution via rube-goldberg-tui. --- ## The Job 1. Receive a feature description from the user 2. Ask 3-5 essential clarifying questions (with lettered options) - one set at a time 3. **Always ask about quality gates** (what commands must pass) 4. After each answer, ask follow-up questions if needed (adaptive exploration) 5. Generate a structured PRD when you have enough context 6. 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. ```markdown ## 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 (rube-goldberg-tui-create-json, rube-goldberg-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:** ```markdown ### 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 rube-goldberg-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: 1. What is the primary goal? A. Reduce eye strain for long sessions B. Match system theme preference C. Provide visual customization D. Other 2. 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: 3. Which components need dark mode support? A. All TUI components B. Only the main execution view C. Main view + settings D. Other 4. 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] 5. 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 Rube Goldberg TUI ## Overview Add dark mode support to rube-goldberg-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 checking - `pnpm 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 `theme` field to `.rube-goldberg-tui.yaml` schema - [ ] 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 `.rube-goldberg-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
Related Skills
bgo
Automates the complete Blender build-go workflow, from building and packaging your extension/add-on to removing old versions, installing, enabling, and launching Blender for quick testing and iteration.
acc-psr-coding-style-knowledge
PSR-1 and PSR-12 coding standards knowledge base for PHP 8.5 projects. Provides quick reference for basic coding standard and extended coding style with detection patterns, examples, and antipattern identification. Use for code style audits and compliance reviews.
acc-detect-test-smells
Detects test antipatterns and code smells in PHP test suites. Identifies 15 smells (Logic in Test, Mock Overuse, Fragile Tests, Mystery Guest, etc.) with fix recommendations and refactoring patterns for testability.
acc-create-value-object
Generates DDD Value Objects for PHP 8.5. Creates immutable, self-validating objects with equality comparison. Includes unit tests.
acc-create-unit-test
Generates PHPUnit unit tests for PHP 8.5. Creates isolated tests with AAA pattern, proper naming, attributes, and one behavior per test. Supports Value Objects, Entities, Services.
acc-create-test-double
Generates test doubles (Mocks, Stubs, Fakes, Spies) for PHP 8.5. Creates appropriate double type based on testing needs with PHPUnit MockBuilder patterns.
acc-create-psr7-http-message
Generates PSR-7 HTTP Message implementations for PHP 8.5. Creates Request, Response, Stream, Uri, and ServerRequest classes with immutability. Includes unit tests.
acc-create-policy
Generates Policy pattern for PHP 8.5. Creates encapsulated business rules for authorization, validation, and domain constraints. Includes unit tests.
acc-create-null-object
Generates Null Object pattern for PHP 8.5. Creates safe default implementations eliminating null checks. Includes unit tests.
acc-create-command
Generates CQRS Commands and Handlers for PHP 8.5. Creates immutable command DTOs with handlers that modify state. Includes unit tests.
acc-analyze-test-coverage
Analyzes PHP codebase for test coverage gaps. Detects untested classes, methods, branches, exception paths, and edge cases. Provides actionable recommendations.
ac-to-examples
将抽象的Acceptance Criteria(Given-When-Then)转换为具体的数值示例和真实对话,让AC对PM/客户/测试人员更易懂。适合在AC编写完成后、准备测试或向客户展示时使用,当AC格式正确但过于抽象时。帮助不熟悉BDD的PM/BA/测试人员理解测试场景,让AC从抽象规则变成可直接用于手动测试的具体步骤。