Skip to main content
NeVibeCode · repository · 11 items

scientific-agent-skills: a set by tondevrel

The tondevrel/scientific-agent-skills repository on GitHub: 11 cards with a description and an install command. They work in Claude Code, Codex, Cursor — 8 platforms in total.

About the repository

GitHub
tondevrel/scientific-agent-skills
Stars
★ 25
Installs across cards
2,548
Licenses
BSD-3-Clause, Apache-2.0, MIT, PSF-2.0
Source updated
2026-02-01
In the catalog since
2026-10-26
xgboost-lightgbm skill xgboost-lightgbm — a skill that gives your agent working patterns for XGBoost and LightGBM: classification, regression, feature importance and hyperparameter tuning on tables. CX Codex +1 501installs matplotlib skill Tells your agent how to build matplotlib figures: line and scatter plots, heatmaps, multi-panel layouts. Useful when the data sits in NumPy or Pandas and the output goes into a paper or report. CX Codex +1 376installs opencv skill Adds an OpenCV reference to your agent: reading and writing images, edge and contour detection, face detection, object tracking in video. CX Codex +1 333installs pyomo skill This skill guides Pyomo-based optimization work in Python. Use it for linear, mixed-integer, and nonlinear models that need an external solver. CX Codex +1 257installs ortools skill Teaches a coding agent to model optimisation problems with Google OR-Tools in Python: CP-SAT models, vehicle routes, linear programs. CX Codex +1 221installs plotly skill Teaches your coding agent to produce interactive Python visualizations with Plotly Express and Graph Objects. Useful for dashboards and data notebooks. CX Codex +1 213installs seaborn skill This skill guides Python statistical plotting with Seaborn and Matplotlib. Use it for EDA, category comparisons, distributions, and relationship analysis. CX Codex +1 167installs numpy skill This skill gives coding agents a NumPy reference for arrays, matrix math, and numerical work in Python. Use it for algorithms, simulations, and scientific tasks. CX Codex +1 124installs scikit-learn skill This skill guides Claude Code through scikit-learn workflows, from preparing tabular data to evaluating a model. Use it for classical machine learning tasks. CX Codex +1 122installs scipy skill A SciPy reference the agent can read: which module handles quadrature, optimisation, interpolation or ODEs, and where the usual calls break. CX Codex +1 121installs xarray skill This skill guides agents through labeled multidimensional data in Python with xarray. Use it for NetCDF, GRIB, Zarr, and Dask-based workloads. CX Codex +1 113installs

More in NeVibeCode

Project sponsors

Companies that keep this analytics open