Loading...
Loading...
Found 7,518 Skills
Systematic debugging frameworks for finding and fixing bugs - includes root cause analysis, defense-in-depth validation, and verification protocols
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.
SEO fundamentals, E-E-A-T, Core Web Vitals, and Google algorithm principles.
Use when building NestJS applications requiring modular architecture, dependency injection, or TypeScript backend development. Invoke for modules, controllers, services, DTOs, guards, interceptors, TypeORM/Prisma.
Execute implementation tasks from design documents using markdown checkboxes. Use when (1) implementing features from feature-design-assistant output, (2) resuming interrupted work, (3) batch executing tasks. Triggers on 'start implementation', 'run tasks', 'resume'.
Statistical visualization. Scatter, box, violin, heatmaps, pair plots, regression, correlation matrices, KDE, faceted plots, for exploratory analysis and publication figures.
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
Use when building MCP servers or clients that connect AI systems with external tools and data sources. Invoke for MCP protocol compliance, TypeScript/Python SDKs, resource providers, tool functions.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Designs user experiences, creates wireframes, defines user flows, ensures accessibility. Trigger keywords - UX design, wireframe, user flow, accessibility, WCAG, mobile-first, responsive, UI design, user journey, interface design, user experience, design system, component design, interaction design
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output library