agentleFS
Sign inStart free
javalenciacaijavalenciacai/develop-skills/SKILL.md

orchestrator

Skill0 starsChanged 9 months agoMITView on GitHub

Sistema de orquestación de roles para agentes de IA. Cada rol delega a sus subordinados y usa skills de skills.sh. Skills base para todos los roles - find-skills (buscar) y skill-creator (crear).

80 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use worker, reviewer and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • stotihvSkill

    worker

    Execute beads autonomously within a track. Handles bead-to-bead context persistence via Agent Mail, uses preferred tools from AGENTS.md, and reports progress to orchestrator.

    Also in 3 projects that use this

  • MicrosoftSkill

    reviewer

    ASP.NET Core ハンドブックの記事をレビューする。Use when: 記事をレビューする、ドキュメントを校正する、コードレビューする、PRをレビューする。技術ドキュメントのレビュー、品質チェック、校正。

    Also in 4 projects that use this

  • am-willSkill

    planner

    Create comprehensive, phased implementation plans with sprints and atomic tasks. Use when user says: "make a plan", "create a plan", "plan this out", "plan the implementation", "help me plan", "design a plan", "draft a plan", "write a plan", "outline the steps", "break this down into tasks", "what's the plan for", or any similar planning request. Also triggers on explicit "/planner" or "/plan" commands.

    Also in 4 projects that use this

  • yakatotechSkill

    advisor

    Provide improvement suggestions and advice on work content. Use for document review, efficiency suggestions, and best practices

    Also in 3 projects that use this

  • AWSSkill

    planning

    Discovers user intent and generates a structured, step-by-step plan for model customization workflows. This skill must always be activated alongside any other skill when the user's request relates to model customization — including fine-tuning, training, building, customizing, reviewing data, or getting advice on approach, regardless of domain. Do not skip this skill even if the immediate ask is narrow (e.g., reviewing data format or a single workflow step), because planning discovers the full scope of work needed. Also activate when the user wants to resume, continue, or modify an existing plan.

    Also in 3 projects that use this

  • OpenAISkill

    observability

    Vercel Observability expert guidance — Drains (logs, traces, speed insights, web analytics), Web Analytics, Speed Insights, runtime logs, custom events, OpenTelemetry integration, and monitoring dashboards. Use when instrumenting, debugging, or optimizing application performance and user experience on Vercel.

    Also in 3 projects that use this

The file

Create a free account to mount
Files
SKILL.md

Sistema de Orquestación para Agentes de IA

Regla Principal

Toda tarea debe fluir por la jerarquía de roles. Cada rol:

  1. Recibe tarea de su superior
  2. Ejecuta usando sus skills O delega a subordinados
  3. Reporta resultado hacia arriba

Skills Base (Todos los Roles)

Cada rol inicia con estos 2 skills:

SkillURLUso
find-skillshttps://skills.sh/vercel-labs/skills/find-skillsBuscar skills existentes para su dominio
skill-creatorhttps://skills.sh/anthropics/skills/skill-creatorCrear skills nuevos cuando no existen
# Instalar skills base
npx skills add vercel-labs/skills --skill find-skills
npx skills add anthropics/skills --skill skill-creator

Jerarquía de Roles

graph TD
    CTO[CTO<br/>Chief Technology Officer]
    
    PM[PM<br/>Product Manager]
    QAL[QAL<br/>QA Lead]
    TL[TL<br/>Tech Lead]
    InfraLead[InfraLead<br/>Infrastructure Lead]
    DataLead[DataLead<br/>Data Lead]
    
    PO[PO<br/>Product Owner]
    UX[UX<br/>UX Designer]
    QA[QA<br/>Quality Assurance]
    SecOps[SecOps<br/>Security Operations]
    Architect[Architect<br/>Software Architect]
    Dev[Dev<br/>Developer]
    DevOps[DevOps<br/>DevOps Engineer]
    DBA[DBA<br/>Database Administrator]
    DataEng[DataEng<br/>Data Engineer]
    AIEng[AIEng<br/>AI Engineer]
    
    CTO --> PM
    CTO --> QAL
    CTO --> TL
    CTO --> InfraLead
    CTO --> DataLead
    
    PM --> PO
    PM --> UX
    
    QAL --> QA
    QAL --> SecOps
    
    TL --> Architect
    TL --> Dev
    
    InfraLead --> DevOps
    InfraLead --> DBA
    
    DataLead --> DataEng
    DataLead --> AIEng
    
    classDef nivel1 fill:#ff6b6b,stroke:#c92a2a,color:#fff
    classDef nivel2 fill:#4dabf7,stroke:#1971c2,color:#fff
    classDef nivel3 fill:#51cf66,stroke:#2f9e44,color:#fff
    
    class CTO nivel1
    class PM,QAL,TL,InfraLead,DataLead nivel2
    class PO,UX,QA,SecOps,Architect,Dev,DevOps,DBA,DataEng,AIEng nivel3

Leyenda:

  • 🔴 Nivel 1 (Directivo): CTO
  • 🔵 Nivel 2 (Suborquestadores): PM, QAL, TL, InfraLead, DataLead
  • 🟢 Nivel 3 (Ejecutores): 10 roles especializados

Resumen de Roles

Nivel 1: Directivo

  • CTO: Orquestador principal → Delega a PM, QAL, TL, InfraLead, DataLead

Nivel 2: Suborquestadores

  • PM: Gestión de producto → Delega a PO, UX
  • QAL: Estrategia de calidad → Delega a QA, SecOps
  • TL: Liderazgo técnico → Delega a Architect, Dev
  • InfraLead: Infraestructura → Delega a DevOps, DBA
  • DataLead: Datos e IA → Delega a DataEng, AIEng

Nivel 3: Ejecutores

  • PO: Requisitos y backlog
  • UX: Diseño de interfaces
  • QA: Testing funcional
  • SecOps: Seguridad
  • Architect: Arquitectura de software
  • Dev: Implementación de código
  • DevOps: CI/CD e infraestructura
  • DBA: Gestión de BD
  • DataEng: Pipelines de datos
  • AIEng: Modelos de IA/ML

Detalles de cada rol: Ver .agents/skills/[rol]/SKILL.md

Ubicación de Skills por Rol

.agents/skills/
├── cto/SKILL.md
├── pm/SKILL.md
├── qal/SKILL.md
├── tl/SKILL.md
├── infralead/SKILL.md
├── datalead/SKILL.md
├── po/SKILL.md
├── ux/SKILL.md
├── qa/SKILL.md
├── secops/SKILL.md
├── architect/SKILL.md
├── dev/SKILL.md
├── devops/SKILL.md
├── dba/SKILL.md
├── dataeng/SKILL.md
└── aieng/SKILL.md

Flujo de Orquestación

1. Usuario → CTO (recibe tarea)
2. CTO analiza → Delega según dominio:
   - Producto/UX → PM
   - Calidad/Seguridad → QAL
   - Desarrollo/Arquitectura → TL
   - Infraestructura/BD → InfraLead
   - Datos/IA → DataLead
3. Suborquestador → Delega a ejecutor(es)
4. Ejecutor:
   a. ¿Tiene skill? → Ejecuta
   b. ¿No tiene? → find-skills (busca)
   c. ¿No existe? → skill-creator (crea)
5. Ejecutor → Reporta a suborquestador
6. Suborquestador → Reporta a CTO
7. CTO → Responde al usuario

Ejemplo: "Crear API REST para usuarios"

CTO analiza → Requiere desarrollo + infra + datos
CTO delega a:
  - TL: Diseño y código
  - InfraLead: BD y deployment
  - DataLead: Analytics (opcional)

TL → Delega:
  - Architect: Diseña estructura de API REST
  - Dev: Implementa endpoints y lógica

InfraLead → Delega:
  - DBA: Diseña esquema de BD
  - DevOps: Configura CI/CD y deployment

Cada ejecutor:
  1. Busca skill (ej: Dev busca "express-api")
  2. Si no existe → skill-creator
  3. Ejecuta y reporta a su líder

Flujo de reporte:
Dev → TL → CTO
Architect → TL → CTO
DBA → InfraLead → CTO
DevOps → InfraLead → CTO
CTO consolida → Usuario

Referencias

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.

Check your setup, free