Explore skills

Comprehensive guide for Pixi package manager - Python environment management, CUDA/GPU support, PyPI integration, Docker/Pixi-Pack deployment, and best practices for ML research

Use when implementing features, refactors, or multi-file changes. Orchestrated plan-then-execute with subagent dispatch and regression checkpoints.

Паттерн Schema-Guided Reasoning (SGR) для решения задач на базе LLM с использованием structured output, constrained decoding, Pydantic моделей. Используй когда нужно: структурированный вывод, JSON schema, воспроизводимость рассуждений, тестируемость промежуточных шагов, направленное рассуждение модели, response_format, parse().

Enforces Karpathy's 4 LLM-coding principles (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven Execution). Auto-fires whenever the user requests writing, editing, refactoring, fixing, or adding code. Blocks drive-by refactoring, over-engineering, and speculative changes; demands clarification before implementation, minimum code, surgical edits, and conversion of tasks into verif

Full-stack implementation agent that writes complete, production-ready code following an approved architecture and schema. Triggers on: write the code, implement features, build the app, code the MVP, generate codebase.

Application security agent that audits code for OWASP Top 10 vulnerabilities, hardcoded secrets, and common security flaws. Triggers on: security audit, vulnerability scan, OWASP check, security review, penetration test, hardening.

Comprehensive SEO content strategy including keyword research, content cluster architecture, technical SEO audit, on-page optimization guidelines, 90-day content calendar, link building strategy, and success metrics for sustainable organic growth

Optimize user onboarding to reduce time-to-value and increase activation rates. Design clear paths to the "aha moment" through checklists, product tours, educational content, and personalized flows. Generate actionable HTML reports with funnel analysis, email sequences, and A/B testing plans.

Building professional CLIs with Typer and Rich - type-safe argument parsing, progress bars, model visualization, Hydra integration, RichHandler logging, and multi-process handling for ML workflows

Profile ML training performance to identify bottlenecks (data loading, compute, memory usage) and optimize GPU utilization. Use when training is slow, GPU utilization is low, or experiencing memory issues.

Initialize a new ML research project using the ML Research template with PyTorch Lightning, Hydra, and modern Python tooling. Use when starting a new ML project from scratch.

Complete guide for PyTorch Geometric (PyG) - graph neural networks, message passing, large-scale distributed graph learning, Lightning integration, and heterogeneous graphs