ai-ml
Build AI/ML Applications with Claude
This workflow bundle provides a comprehensive guide for building production AI applications, from LLM integration to RAG systems and AI agents. It orchestrates multiple specialized skills into a cohesive development process.
Descargar el ZIP de la skill
Subir en Claude
Ve a Configuración → Capacidades → Skills → Subir skill
Activa y empieza a usar
Pruébalo
Usando "ai-ml". Use @ai-product to design AI-powered features
Resultado esperado:
This triggers the ai-product skill to guide you through AI feature design with use case definition, model selection, and architecture planning.
Usando "ai-ml". Use @rag-engineer to design RAG pipeline
Resultado esperado:
The rag-engineer skill provides guidance on designing retrieval-augmented generation pipelines including data pipeline design, embedding model selection, and vector database setup.
Usando "ai-ml". Use @langgraph to create stateful AI workflows
Resultado esperado:
LangGraph integration skill helps create complex, stateful AI workflows with proper state management and workflow orchestration.
Auditoría de seguridad
SeguroStatic analysis flagged 75 potential issues (external_commands, weak_crypto, system_reconnaissance) but all are false positives. The file is a markdown documentation bundle that orchestrates other skills via reference names in code blocks. No actual code execution, shell commands, or cryptographic operations exist. This is safe for publication.
Problemas de riesgo medio (3)
Puntuación de calidad
Lo que puedes crear
Building LLM-powered applications
Follow the phased workflow to design, integrate, and deploy LLM-powered features with proper observability.
Implementing RAG systems
Use the RAG implementation phase to set up vector databases, embedding strategies, and retrieval pipelines.
Creating AI agent systems
Design multi-agent architectures using autonomous agent patterns, CrewAI, and LangGraph integration.
Prueba estos prompts
Use @ai-product to design AI-powered features for my application. Follow the Phase 1 workflow.
Use @rag-engineer to design RAG pipeline, then @vector-database-engineer to set up vector search, and @embedding-strategies to select optimal embeddings.
Use @crewai to build role-based multi-agent system, then @langgraph to create stateful AI workflows.
Use @ml-engineer to build machine learning pipeline and @mlops-engineer to set up MLOps infrastructure.
Mejores prácticas
- Follow the workflow phases in order for comprehensive AI development
- Use the checklist items to ensure all critical components are addressed
- Invoke specialized skills for deep expertise in each area
- Apply quality gates before deploying AI features to production
Evitar
- Skipping workflow phases - each phase builds on previous work
- Ignoring the observability phase - AI systems need monitoring
- Not following security practices - AI features require input validation and rate limiting
- Skipping quality gates - AI features need thorough testing before deployment