# Ralph Tui Prd

> Genera un Product Requirements Document (PRD) para orquestación de tareas con ralph-tui, con historias de usuario convertibles a issues de beads o prd.json.

Fuente: https://skillsagentes.com/skills/subsy/ralph-tui/ralph-tui-prd
Markdown: https://skillsagentes.com/skills/subsy/ralph-tui/ralph-tui-prd.md

Repositorio: https://github.com/subsy/ralph-tui
Autor: subsy
Licencia: MIT
Actualizado: hace 4 días
Coste de contexto: 69 tok instalada, 2.5k tok al activarse, 2.5k tok con todos los archivos del bundle
Bundle: 1 archivo, 10 KB
Permisos que pide: ninguno declarado

## Instalación

Un skill son archivos markdown: los mismos archivos valen para cualquier agente y lo único que cambia es el directorio de destino, es decir la bandera `--agent`. Añade `-g` para instalarlo en todos los proyectos de la máquina.

```bash
# Claude Code
npx -y skills add subsy/ralph-tui --skill ralph-tui-prd --agent claude-code
# Cursor
npx -y skills add subsy/ralph-tui --skill ralph-tui-prd --agent cursor
# Codex
npx -y skills add subsy/ralph-tui --skill ralph-tui-prd --agent codex
# Gemini CLI
npx -y skills add subsy/ralph-tui --skill ralph-tui-prd --agent gemini
# Windsurf
npx -y skills add subsy/ralph-tui --skill ralph-tui-prd --agent windsurf
# Cline
npx -y skills add subsy/ralph-tui --skill ralph-tui-prd --agent cline
```

## Qué hace

- Guía al agente para hacer preguntas aclaratorias con opciones (1-4 rondas) antes de generar el PRD
- Genera un PRD estructurado con Overview, Goals, Quality Gates, User Stories, Functional Requirements, Non-Goals, etc.
- Envuelve el PRD final en marcadores [PRD]...[/PRD] para que la TUI lo parsee
- Pregunta obligatoriamente por los comandos de quality gates a exigir en cada historia de usuario
- No implementa nada, solo produce el documento de requisitos

## Cuándo usarla

- Cuando el usuario dice 'create a prd', 'write prd for', 'plan this feature', 'requirements for' o 'spec out'
- Cuando se necesita planificar una feature para ejecución automatizada vía ralph-tui

## Qué la activa

- "Crea un PRD para agregar modo oscuro a la TUI"
- "Escribe el PRD para esta funcionalidad"
- "Planifica esta feature antes de implementarla"
- "Especifica los requisitos para el nuevo módulo"

## Antes de instalar

- Pensado para usarse junto a ralph-tui create-prd y herramientas de conversión como ralph-tui-create-json o ralph-tui-create-beads.
- Necesita en el PATH: bun, npm, pnpm

## Archivos

- SKILL.md — 10 KB

## SKILL.md

Reproducido tal cual desde subsy/ralph-tui bajo MIT. Esta sección es el documento original y está en inglés.

# Ralph TUI PRD Generator

Create detailed Product Requirements Documents optimized for AI agent execution via ralph-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.

If you are Claude Code in an interactive session, you may present these questions with the AskUserQuestion tool instead - same questions and options, still one set at a time. When this skill is driven by `ralph-tui create-prd`, the agent runs non-interactively and nothing can answer a tool call, so ask in plain text with lettered options as above.

### 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 (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:**
```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 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:

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 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 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 `.ralph-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 `.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

## Dónde encaja

- Categoría: [Productividad](https://skillsagentes.com/categorias/productividad.md) — Planificación, toma de notas y automatización de flujos personales.
- Creador: [subsy](https://skillsagentes.com/creators/subsy.md) — 0 skills en el directorio
- [Todas las skills](https://skillsagentes.com/skills.md)
- [Ranking de instalaciones](https://skillsagentes.com/ranking.md)

## Otras skills del mismo repositorio

- [Testing Tui Runtime](https://skillsagentes.com/skills/subsy/ralph-tui/testing-tui-runtime.md): Cómo manejar el TUI de ralph-tui (`run`, modo watch, rutas de pausa/salida) de extremo a extremo en una terminal real, con un agente falso y un tracker beads de prueba, sin credenciales de IA.
- [Ralph Tui Create Beads](https://skillsagentes.com/skills/subsy/ralph-tui/ralph-tui-create-beads.md): Convierte PRDs en beads para la ejecución con ralph-tui. Crea un epic con beads hijas por cada historia de usuario cuando quieres usar ralph-tui con beads como fuente de tareas.
- [Ralph Tui Create Json](https://skillsagentes.com/skills/subsy/ralph-tui/ralph-tui-create-json.md): Convierte PRDs al formato prd.json para la ejecución de ralph-tui. Crea archivos JSON de tareas con user stories, criterios de aceptación y dependencias.
- [Ralph Tui Create Beads Rust](https://skillsagentes.com/skills/subsy/ralph-tui/ralph-tui-create-beads-rust.md): Convierte PRDs en beads para la ejecución de ralph-tui usando beads-rust (CLI `br`). Crea un epic con beads hijos para cada historia de usuario.

## Skills relacionadas

- [Spec](https://skillsagentes.com/skills/garrytan/gstack/spec.md): Convierte una intención vaga en un spec preciso y ejecutable en cinco fases, con opción de abrir el issue y lanzar un agente. (gstack)
- [Caveman Help](https://skillsagentes.com/skills/juliusbrussee/caveman/caveman-help.md): Tarjeta de referencia rápida con todos los modos, skills y comandos de caveman. Despliegue de una sola vez, no es un modo persistente.
- [Caveman Stats](https://skillsagentes.com/skills/juliusbrussee/caveman/caveman-stats.md): Muestra el uso real de tokens y el ahorro estimado de la sesión actual, leído directamente del log de sesión de Claude Code, sin estimación del modelo.
- [Caveman](https://skillsagentes.com/skills/juliusbrussee/caveman/caveman.md): Modo de comunicación ultra-comprimido: corta ~65% de los tokens de salida (medido) manteniendo toda la precisión técnica. Soporta niveles lite, full (por defecto), ultra y variantes wenyan.
- [Interview Me](https://skillsagentes.com/skills/addyosmani/agent-skills/interview-me.md): Extrae lo que el usuario realmente quiere, no lo que cree que debería querer, mediante una entrevista de una pregunta a la vez hasta alcanzar ~95% de confianza.

---

Skills Agentes · [Índice de páginas en markdown](https://skillsagentes.com/sitemap.md) · [Inicio](https://skillsagentes.com/index.md)