Joao Maria Arranz Aparicio
Community@informatico-madrid
Analista programador especializado en desarrollo PHP con Symfonony
Agent Skills by Joao Maria Arranz Aparicio
Showing 62 vetted skills indexed across 2 GitHub repositories.
informatico-madridpython-testing-patterns
Apply pytest patterns for unit, integration, and async tests with fixtures and mocks.
informatico-madridhome-assistant-best-practices
Operates intelligently on-premise or in your cloud with Zero-friction deployment, delivering Zero-footprint browsing and Zero-latency interactions.
informatico-madridhomeassistant-dashboard-designer
Refactor Home Assistant Lovelace dashboards with template-driven YAML and MCP validation.
informatico-madridpython-cybersecurity-tool-development
Develop secure Python cybersecurity tools with Pydantic models and modular architecture.
informatico-madridpython-security-scanner
Identifies SQL injection, unsafe deserialization, and hardcoded secrets in Python source files locally.
informatico-madridhomeassistant-ops
Apply bulk, reviewable Home Assistant changes via REST and WebSocket APIs.
informatico-madridhomeassistant-skill
Control Home Assistant devices via REST API using curl and jq.
informatico-madridpython-performance-optimization
Profile and optimize Python code using CPU, memory, and line profilers.
informatico-madride2e-testing-patterns
Provide structured end-to-end testing patterns for Playwright and Cypress.
informatico-madridhomeassistant-config
Validate Home Assistant YAML configurations for syntax, structure, and best practices.
informatico-madriddspy
Develop AI systems with declarative programming and automatic prompt optimization.
informatico-madridopenrlhf-training
Train large language models with RLHF algorithms using Ray and vLLM.
informatico-madridnemo-guardrails
Enforce runtime safety and guardrails for LLM applications using Colang 2.0 DSL.
informatico-madridcrewai-multi-agent
Create and execute multi-agent systems for autonomous AI collaboration.
informatico-madridmoe-training
Train Mixture of Experts models using DeepSpeed and HuggingFace Transformers.
informatico-madridlangsmith-observability
Traces, evaluates, and monitors LLM applications for performance and errors.
informatico-madridnemo-curator
Prepare LLM training data with GPU-accelerated curation tools.
informatico-madridml-paper-writing
Draft machine learning papers with LaTeX templates and verified citations.
informatico-madridprompt-guard
Detect prompt injections and jailbreak attempts in text using a pre-trained classifier.
informatico-madridevaluating-llms-harness
Evaluate LLMs against over 60 academic benchmarks using lm-evaluation-harness.
informatico-madridllama-factory
Fine-tune and deploy LLMs using the LLaMA-Factory framework.
informatico-madridknowledge-distillation
Compress large language models into smaller student models using knowledge distillation.
informatico-madridsimpo-training
Optimize LLMs with reference-free SimPO training using preference datasets.
informatico-madridimplementing-llms-litgpt
Implement and train LLMs using the LitGPT framework.