Find the best CLAUDE.md, AGENTS.md and Claude skills

tondevrelSkill

pytorch-deployment

tondevrel/scientific-agent-skills/skills/pytorch-deployment/SKILL.md

Advanced sub-skill for PyTorch focused on model productionization and deployment. Covers TorchScript (JIT/Tracing), ONNX export, LibTorch (C++ API), and inference optimization (Quantization, Pruning).

tondevrelSkill

pytorch-geometric

tondevrel/scientific-agent-skills/skills/pytorch-geometric/SKILL.MD

Graph Neural Networks (GNN) for learning on graph-structured data. PyTorch Geometric (PyG) extends PyTorch with the MessagePassing framework — the core abstraction for all GNN layers — and provides standard convolutions (GCNConv, GATConv, GraphSAGEConv, GINConv), graph pooling, batching of variable-size graphs, and datasets. Use when: performing node classification (e.g., predicting labels on a citation network), graph classification (e.g., predicting molecular properties), link prediction (e.g., recommending new connections), learning representations on any graph-structured data (social networks, molecules, knowledge graphs, protein structures), implementing custom GNN architectures via the MessagePassing base class, working with heterogeneous graphs (multiple node/edge types), or any task where data has explicit relational structure that CNNs/RNNs cannot capture. Complements networkx (classical graph algorithms) and rdkit (molecular graphs) — PyG adds the deep learning layer on top.

tondevrelSkill

pytorch-research

tondevrel/scientific-agent-skills/skills/pytorch-research/SKILL.md

Advanced sub-skill for PyTorch focused on deep research and production engineering. Covers custom Autograd functions, module hooks, advanced initialization, Distributed Data Parallel (DDP), and performance profiling.

tondevrelSkill

pytorch

tondevrel/scientific-agent-skills/skills/pytorch/SKILL.md

Leading deep learning framework. Provides Tensors and Dynamic Computational Graphs with strong GPU acceleration. Widely used for research, neural networks, and differentiable programming.

tondevrelSkill

qiskit-hardware

tondevrel/scientific-agent-skills/skills/qiskit-hardware/SKILL.md

Advanced sub-skill for Qiskit focused on executing circuits on physical quantum processing units (QPUs). Covers IBM Quantum Runtime, error mitigation techniques (TREX, ZNE), hardware-aware transpilation, and low-level pulse control (OpenPulse).

tondevrelSkill

qiskit

tondevrel/scientific-agent-skills/skills/qiskit/SKILL.md

Comprehensive guide for Qiskit - IBM's quantum computing framework. Use for quantum circuit design, quantum algorithms (VQE, QAOA, Grover, Shor), quantum simulation, noise modeling, quantum machine learning, and quantum chemistry calculations. Essential for quantum computing research and applications.

tondevrelSkill

qutip

tondevrel/scientific-agent-skills/skills/qutip/SKILL.md

Quantum Toolbox in Python. Framework for simulating the dynamics of open quantum systems. Provides data structures for quantum objects (kets, bras, operators) and solvers for master equations, Monte Carlo trajectories, and time-dependent Hamiltonians. Use for quantum dynamics simulation, open quantum systems, master equations, quantum optics, cavity QED, Jaynes-Cummings model, Rabi oscillations, Wigner functions, quantum correlations, entanglement analysis, and quantum control.

Often used withusfiscaldata·deeptools·dnanexus-integration

tondevrelSkill

rasterio

tondevrel/scientific-agent-skills/skills/rasterio/SKILL.MD

Raster geospatial data processing — the Python interface to GDAL for satellite imagery, elevation models, and grid-based geographic analysis. Rasterio reads and writes georeferenced raster formats (GeoTIFF, NetCDF, JP2, PNG, JPEG2000), handles Coordinate Reference Systems (CRS) and reprojection, performs band math (NDVI, NDWI, EVI), clips/masks rasters with vector geometries, resamples grids, and supports memory-efficient windowed I/O for multi-gigabyte files. Use when: working with satellite imagery or aerial photos, processing Digital Elevation Models (DEM/DTM/DSM), computing spectral indices from multispectral data, clipping raster data to polygon boundaries, reprojecting between coordinate systems, performing spatial interpolation on gridded data, analyzing land cover or land use change over time, integrating raster data with vector data (geopandas/shapely), or any task involving georeferenced grid/pixel data as opposed to vector points/lines/polygons.

tondevrelSkill

rdkit

tondevrel/scientific-agent-skills/skills/rdkit/SKILL.md

Open-source cheminformatics and machine learning toolkit for drug discovery, molecular manipulation, and chemical property calculation. RDKit handles SMILES, molecular fingerprints, substructure searching, 3D conformer generation, pharmacophore modeling, and QSAR. Use when working with chemical structures, drug-like properties, molecular similarity, virtual screening, or computational chemistry workflows.

tondevrelSkill

scanpy

tondevrel/scientific-agent-skills/skills/scanpy/SKILL.md

Scalable toolkit for analyzing single-cell gene expression data. Built on top of Anndata, focusing on clustering, trajectory inference, and visualization.

tondevrelSkill

scikit-bio

tondevrel/scientific-agent-skills/skills/scikit-bio/SKILL.md

Library for bioinformatics and community ecology statistics. Provides data structures and algorithms for sequences, alignments, phylogenetics, and diversity analysis. Essential for microbiome research and ecological data science. Use for alpha/beta diversity metrics, ordination (PCoA), phylogenetic trees, sequence manipulation (DNA/RNA/Protein), distance matrices, PERMANOVA, and community ecology analysis.

Often used withusfiscaldata·benchling-integration·etetoolkit

tondevrelSkill

scikit-image

tondevrel/scientific-agent-skills/skills/scikit-image/SKILL.md

A collection of algorithms for image processing in Python. Built on NumPy, SciPy, and Cython. It focuses on scientific image analysis including segmentation, geometric transformations, color space manipulation, analysis, and filtering.

tondevrelSkill

scikit-learn

tondevrel/scientific-agent-skills/skills/scikit-learn/SKILL.md

The industry standard library for machine learning in Python. Provides simple and efficient tools for predictive data analysis, covering classification, regression, clustering, dimensionality reduction, model selection, and preprocessing.

tondevrelSkill

scikit-video

tondevrel/scientific-agent-skills/skills/scikit-video/SKILL.md

Video processing library for scientists. Provides easy access to video files using FFmpeg, motion estimation algorithms, and video quality metrics. Built on NumPy and designed for high-performance research in computer vision and image sequence analysis. Use when working with video files, motion estimation, video quality assessment (VQA), FFmpeg, temporal image data, video codecs, YUV data, or scientific video recordings.

tondevrelSkill

scipy

tondevrel/scientific-agent-skills/skills/scipy/SKILL.md

Comprehensive guide for SciPy - the fundamental library for scientific and technical computing in Python. Use for integration, optimization, interpolation, linear algebra, signal processing, statistics, ODEs, Fourier transforms, and advanced scientific algorithms. Built on NumPy and essential for research and engineering.

tondevrelSkill

seaborn

tondevrel/scientific-agent-skills/skills/seaborn/SKILL.md

A Python data visualization library based on matplotlib. It provides a high-level interface for drawing attractive and informative statistical graphics. Great for exploring relationships between variables and visualizing distributions. Use for statistical data visualization, exploratory data analysis (EDA), relationship plots, distribution plots, categorical comparisons, regression visualization, heatmaps, cluster maps, and creating publication-quality statistical graphics from Pandas DataFrames.

Often used withusfiscaldata·deeptools·torch-geometric

tondevrelSkill

shapely

tondevrel/scientific-agent-skills/skills/shapely/SKILL.md

Manipulation and analysis of planar geometric objects. Based on the widely deployed GEOS library. Provides data structures for points, curves, and surfaces, and standardized algorithms for geometric operations. Use for 2D geometry operations, spatial relationships, set-theoretic operations (intersection, union, difference), point-in-polygon queries, geometric calculations (area, distance, centroid), buffering, simplifying geometries, linear referencing, and cleaning invalid geometries. Essential for GIS operations, spatial analysis, and geometric computations.

tondevrelSkill

simpy

tondevrel/scientific-agent-skills/skills/simpy/SKILL.md

A process-based discrete-event simulation framework. Use for modeling queuing systems, supply chains, manufacturing processes, network simulation, project management, and any system where events occur at specific points in time. Load when working with discrete event simulation, process modeling, resource allocation, virtual time, simpy.Environment, simpy.Resource, or event-driven simulation.

Often used withusfiscaldata·deeptools·torch-geometric

tondevrelSkill

sklearn-advanced

tondevrel/scientific-agent-skills/skills/sklearn-advanced/SKILL.md

Professional sub-skill for scikit-learn focused on robust pipeline architecture, custom estimator development, advanced feature engineering, and rigorous model validation. Covers Target Encoding, Nested Cross-Validation, and Production Deployment.

tondevrelSkill

sklearn-explainability

tondevrel/scientific-agent-skills/skills/sklearn-explainability/SKILL.md

Advanced sub-skill for scikit-learn focused on model interpretability, feature importance, and diagnostic tools. Covers global and local explanations using built-in inspection tools and SHAP/LIME integrations.