agentleFS
FullFranFullFran/Agent-skills-POC/.agents/skills/architecture-decision-record/SKILL.md

architecture-decision-record

Skill1 starsChanged 10 months agoMITView on GitHub

Help the team document and maintain Architecture Decision Records (ADRs).

13 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Architecture Decision Record (ADR) Skill

Esta skill permite al agente ayudar al equipo a documentar decisiones técnicas importantes para mantener un rastro histórico de la arquitectura.

Cuándo usar

  • Al elegir una nueva base de datos o framework.
  • Al cambiar un patrón de diseño global (ej: pasar de REST a GraphQL).
  • Al establecer convenciones de código obligatorias.

Estructura del ADR

Los archivos deben guardarse en docs/adr/NNNN-nombre-descriptivo.md con:

  1. Título: Breve y claro.
  2. Estatus: Propuesto, Aceptado, Superado o Rechazado.
  3. Contexto: ¿Cuál es el problema y qué opciones hay?
  4. Decisión: ¿Qué se ha elegido y por qué?
  5. Consecuencias: ¿Qué ganamos y qué perdemos con esto?

Proceso

  1. Ayuda al usuario a articular la decisión.
  2. Genera el markdown siguiendo la plantilla.
  3. Asegúrate de que el número sea correlativo al último ADR en docs/adr/.
  4. Ejecuta npm run sync si la decisión afecta al framework de agentes.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.