Explorar skills

Model Context Protocol (MCP) integration specialist. Use when creating

Aplicar ciencia del comportamiento y modelos mentales a decisiones de marketing, priorizadas mediante un sistema de puntuación de apalancamiento psicológico y viabilidad.

Medicinal chemistry filters. Apply drug-likeness rules (Lipinski, Veber), PAINS filters, structural alerts, complexity metrics, for compound prioritization and library filtering.

Meta-cognitive reasoning specialist for evidence-based analysis, hypothesis

Use this skill to work with Microsoft Foundry (Azure AI Foundry) and tools from Foundry MCP server: deploy AI models, manage AI agents (create, deploy, invoke, run, troubleshoot Foundry Agents), manage RBAC permissions and role assignments, manage quotas and capacity, create Foundry resources. USE FOR: Microsoft Foundry, AI Foundry, create agent, deploy agent, debug agent, invoke agent, run agent,

Monitors Claude's responses for struggle signals and suggests escalation to deep-thinking agents when complexity exceeds comfortable reasoning capacity.

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

Network architecture, troubleshooting, and infrastructure patterns. Use

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

Reproduce el pipeline completo de análisis de sensibilidad de prellenado para indicadores de 'reward hacking'. Se utiliza para evaluar la susceptibilidad de los puntos de control del modelo a prellenados que provocan exploits, calcular trayectorias basadas en tokens o comparar logprob y el recuento de tokens como predictores de explotabilidad.

Guides users on creating mock implementations for testing with traits, providing test doubles, and avoiding tight coupling to test infrastructure. Activates when users need to test code with external dependencies.

Mobile game development principles. Touch input, battery, performance, app stores.