research▌

### Scientific Critical Thinking - name: "scientific-critical-thinking" - description: "Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias)..." - allowed-tools: "Read Write Edit"

### Scientific Schematics - name: "scientific-schematics" - description: "Create publication-quality scientific diagrams using Nano Banana 2 AI with smart iterative refinement. Uses Gemini 3.1 Pro Preview for quality review. Only regenerates if quality is below threshold fo..." - allowed-tools: "Read Write Edit Bash"

### Scientific Slides - name: "scientific-slides" - description: "Build slide decks and presentations for research talks. Use this for making PowerPoint slides, conference presentations, seminar talks, research presentations, thesis defense slides, or any scientific..." - allowed-tools: "Read Write Edit Bash"

### Scientific Visualization - name: "scientific-visualization" - description: "Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journ..."

### Scikit Survival - name: "scikit-survival" - description: "Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitt..."

### Timesfm Forecasting - name: "timesfm-forecasting" - description: "Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/Dat..." - allowed-tools: "Read Write Edit Bash"

### Torchdrug - name: "torchdrug" - description: "PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model de..."

### Stable Baselines3 - name: "stable-baselines3" - description: "Production-ready reinforcement learning algorithms (PPO, SAC, DQN, TD3, DDPG, A2C) with scikit-learn-like API. Use for standard RL experiments, quick prototyping, and well-documented algorithm impleme..." - allowed-tools: "Read Write Edit Bash"

### Shap - name: "shap" - description: "Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP p..."

### Torch Geometric - name: "torch-geometric" - description: "PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when w..."