- Home
- Skills
- Prompt & Skill Engineering
- De idea a proyecto
More screenshots
Works with the AI Agents you already use
De idea a proyecto
Transform software ideas into verifiable OpenSpec specifications and TDD tasks with strict human approval gates.
Free
De idea a proyecto
Example session with this skill installed
Tengo una idea para una API de gestión de inventario. Quiero empezar explorando los requisitos y proponer una especificación OpenSpec inicial sin escribir archivos todavía.
- Read your context and instructions
- Compiled the de idea a
He analizado la propuesta para la API de gestión de inventario en modo EXPLORAR. A continuación, presento el diagnóstico inicial y la propuesta de requisitos para tu revisión antes de generar cualquier artefacto en el repositorio.
Diagnóstico y Propuesta de Requisitos (REQ-INV-001)
| Categoría | Detalle | Estado |
|---|---|---|
| Objetivo | Centralizar el control de existencias, movimientos y alertas de stock mínimo. | Propuesto |
| Actores | Administrador de Almacén, Operario, Sistema de Ventas (API). | Propuesto |
| Stack Detectado | Node.js / TypeScript (basado en package.json raíz). | Identificado |
| OpenSpec | No inicializado. Se requiere opsx init en fase DOCUMENTAR. | Pendiente |
Requisitos Funcionales Iniciales
- RF-01: Registro de productos con SKU único, descripción y categoría.
- RF-02: Actualización de stock mediante incrementos/decrementos atómicos.
- RF-03: Historial de movimientos (trazabilidad de quién y cuándo).
- RF-04: Notificación automática cuando el stock sea inferior al umbral definido.
Restricciones y Supuestos
- Seguridad: Se asume uso de JWT para autenticación de la API.
- Persistencia: Se propone PostgreSQL para garantizar integridad referencial en movimientos.
- Fuera de Alcance: Facturación y pasarelas de pago no incluidas en este MVP.
Next steps
- Aprobar Requisitos: Confirma si los RF-01 a RF-04 cubren el alcance esperado.
- Cambiar a modo DOCUMENTAR: Una vez aprobado, ejecutaré
opsx initpara crear la estructura OpenSpec. - Definir Escenarios: Comenzaremos a redactar los archivos
proposal.mdyspecs/en la carpetaopenspec/.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop shipping code that drifts from its requirements. This skill enforces Spec-Driven Development (SDD) and Test-Driven Development (TDD) by turning raw ideas into verifiable OpenSpec contracts. It bridges the gap between high-level requirements and implementation through explicit human-in-the-loop approval gates.
What it does
- Requirement engineering converts software ideas into structured functional and non-functional requirements.
- Spec-Driven Development generates OpenSpec specifications, architectural designs, and traceability matrices.
- Atomic task planning breaks down features into small, testable units linked to specific requirement IDs.
- TDD orchestration manages the red-green-refactor cycle, ensuring code only exists to satisfy documented specs.
- Automated auditing verifies implementation evidence against the Definition of Done (DoD) before closing tasks.
How it works
- EXPLORE the existing repository to diagnose state, tech stack, and OpenSpec configuration without modifying files.
- DOCUMENT requirements and design artifacts once the project scope and initial constraints are approved.
- IMPLEMENT features using TDD, writing failing tests first and only coding to satisfy the authorized spec.
- VERIFY the increment through non-destructive quality controls, security audits, and traceability checks.
Frameworks & tools
Built for OpenCode v2 environments using OpenSpec CLI (opsx). Supports standard stacks including PHP and Java for enterprise logic, alongside Git-based versioning and Markdown-driven documentation.
Why this beats prompting it yourself
Standard prompting often bypasses documentation for speed, leading to technical debt and loss of context. This skill enforces a "contract-first" workflow with mandatory approval gates, ensuring that every line of code is traceable to a verified requirement.
Use cases
- Initializing a new project with a structured OpenSpec architecture.
- Auditing existing codebases for compliance and documentation gaps.
- Implementing complex features that require high reliability and test coverage.
- Transforming legacy requirements into modern, verifiable implementation plans.
Known limitations
Requires an environment with OpenCode v2 or compatible agents. Does not perform destructive actions or file writes without explicit user authorization in the correct mode.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Prompt & Skill Engineering.
Requires OpenCode v2 environment. No autonomous file writing in EXPLORE mode. Requires OpenSpec CLI (opsx) for full automation. Only English/Spanish support mentioned.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
1 use
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 27 days ago
- Free with an Agensi account
- Accounts
Openspec
- Software
Node.js
Git
Permissions
Allowed Hosts