Deep Learning

Manage team-wide Windsurf settings and AI policies. Activate when users mention "team settings", "organization config", "team policies", "shared settings", or "team standardization". Handles team configuration management. Use when working with windsurf team settings functionality. Trigger with phrases like "windsurf team settings", "windsurf settings", "windsurf".

Comprehensive guide for initializing or reorganizing agent memory. Load this skill when running /init, when the user asks you to set up your memory, or when you need guidance on creating effective memory blocks.

Run omicverse's CellPhoneDB v5 wrapper on annotated single-cell data to infer ligand-receptor networks and produce CellChat-style visualisations.

Optimize deep learning models using Adam, SGD, and learning rate scheduling to improve accuracy and reduce training time. Use when asked to "optimize deep learning model" or "improve model performance".

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Transforms workflow to use Manus-style persistent markdown files for planning, progress tracking, and knowledge storage. Use when starting complex tasks, multi-step projects, research tasks, or when the user mentions planning, organizing work, tracking progress, or wants structured output.

Package expertise into discoverable, reusable capabilities that extend Claude's functionality. Use when creating new Skills, understanding how Skills work, or organizing existing capabilities.

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform melody-conditioned music generation.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Accelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.

Transforms conversations and discussions into structured documentation pages in Notion. Captures insights, decisions, and knowledge from chat context, formats appropriately, and saves to wikis or databases with proper organization and linking for easy discovery.

Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural architecture search, MLOps automation, and production ML deployment. Build scalable ML pipelines with comprehensive monitoring and experiment tracking.

Enterprise Machine Learning specialist with TensorFlow 2.20.0, PyTorch 2.9.0, Scikit-learn 1.7.2 expertise. Master AutoML, neural architecture search, MLOps automation, and production ML deployment. Build scalable ML pipelines with comprehensive monitoring and experiment tracking.

Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx). Specialized in neural network architectures, system diagrams, and flowcharts. Generates SVG/EPS in figures/ folder with automated quality verification.

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill structure, progressive disclosure, or skill development best practices for Claude Code plugins.

Write consistent, maintainable CSS following the project's methodology (Tailwind, BEM, utility classes, CSS modules) with design system adherence and performance optimization. Use this skill when writing or modifying styles, CSS files, utility classes, CSS-in-JS, styled components, or any styling code. Apply when working with .css, .scss, .module.css files, Tailwind utility classes, styled-components, CSS modules, design tokens (colors, spacing, typography), framework-specific styling approaches, optimizing CSS for production, implementing CSS purging or tree-shaking, or avoiding style overrides. Use for any task involving visual styling, layout styling, design system implementation, or CSS organization.