메뉴
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).
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
AI Engineer. AIEng develops AI/ML models, training, MLOps and LLM integration. Reports to DataLead. Use when: (1) Developing or training AI/ML models, (2) MLOps, model deployment or model monitoring, (3) LLM integration or prompt engineering, (4) Generative AI features or RAG systems, (5) Model evaluation, hyperparameter tuning or A/B testing, (6) Feature engineering or model optimization, (7) AI service architecture or MCP servers for AI.
Software Architect. Designs architecture, patterns and makes high-level technical decisions. Reports to TL. Use when: (1) Designing software architecture or system design, (2) Defining architectural patterns (microservices, MVC, event-driven), (3) High-level technical decisions or technology evaluation, (4) API design or service integration architecture, (5) Scalability, performance or reliability design, (6) Writing ADRs (Architecture Decision Records), (7) Database schema design or data architecture.
Main role orchestrator. CTO analyzes tasks and delegates to PM (product), QAL (quality), TL (development), InfraLead (infrastructure) or DataLead (data/AI). Entry point for all tasks. Use when: (1) User requests involve product strategy, roadmap or UX, (2) Quality testing, security audits or compliance needed, (3) Development, architecture or code implementation required, (4) Infrastructure, CI/CD, databases or deployment tasks, (5) Data pipelines, analytics, AI/ML models or LLM integration, (6) Cross-domain coordination between multiple areas, (7) Any ambiguous request that needs domain analysis and delegation.
Data Engineer. DataEng builds data pipelines, ETL, data warehousing and batch/streaming processing. Reports to DataLead. Use when: (1) Building data pipelines or ETL processes, (2) Data warehousing or data lake architecture, (3) Batch processing or streaming data (Kafka, Spark), (4) Data integration from multiple sources, (5) Data quality validation or data cleaning, (6) Schema design or data modeling, (7) Data orchestration (Airflow, Dagster) or scheduling.
Data and AI orchestrator. Data Lead coordinates DataEng and AIEng for data pipelines, ETL, data warehousing and AI/ML models. Leads data strategy and machine learning. Reports to CTO. Use when: (1) Data strategy, analytics or data governance needed, (2) Data pipelines, ETL or data warehousing required, (3) AI/ML models, training or MLOps implementation, (4) LLM integration or generative AI features, (5) Data quality, schema design or data architecture, (6) Model evaluation, monitoring or A/B testing, (7) Coordinating between data engineering and AI engineering teams.
Database Administrator. DBA manages databases, optimization, backups, replication and tuning. Reports to InfraLead. Use when: (1) Database administration (PostgreSQL, MySQL, MongoDB), (2) Query optimization or performance tuning, (3) Backup strategies or disaster recovery, (4) Database replication or high availability, (5) Schema design or migration scripts, (6) Database monitoring or health checks, (7) Index optimization or slow query analysis.
| name | orchestrator |
| description | 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). |
Toda tarea debe fluir por la jerarquía de roles. Cada rol:
Cada rol inicia con estos 2 skills:
| Skill | URL | Uso |
|---|---|---|
| find-skills | https://skills.sh/vercel-labs/skills/find-skills | Buscar skills existentes para su dominio |
| skill-creator | https://skills.sh/anthropics/skills/skill-creator | Crear 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
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:
Detalles de cada rol: Ver
.agents/skills/[rol]/SKILL.md
.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
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
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