Development skills

Browse reusable Agent Skills, each with a clear purpose and practical guidance.

tensorflow-guide

TensorFlow best practices for tf.function, GPU memory, and deployment

2.87k repo starsObserved in 4 repos
Development

causal-inference-mixtape

This skill should be used when the user asks to "implement a DiD regression", "write a causal inference pipeline", "set up an event study", "implement instrumental variables", "run a regression discontinuity design", "build a synthetic control model", "implement propensity score matching", "write parallel trends test", "implement Bacon decomposition", or needs code templates for causal inference methods in Python, R, or Stata. Based on Scott Cunningham's Causal Inference: The Mixtape.

2.87k repo starsObserved in 3 repos
Development

code-exec-skills

7 code execution skills. Trigger: running code, interactive notebooks, Jupyter, Colab, sandboxed execution. Design: execution environment guides with setup instructions and best practices.

2.87k repo starsObserved in 3 repos
Development

execute

Executes all registered notebooks, strips noisy cell metadata, and syncs Jupytext pairs. Use when asked to re-run notebooks or refresh outputs.

2.87k repo starsObserved in 3 repos
Development

geopandas

Spatial data: GeoDataFrames, spatial joins, CRS/projections, choropleth/interactive maps, spatial autocorrelation, PySAL. Use for geographic data, spatial files (Shapefile, GeoPackage, GeoParquet), or spatial stats. For charts without GIS use plotly.

2.87k repo starsObserved in 3 repos
Development

marimo

Reactive Python notebook system. Cell reactivity, UI elements (sliders, dropdowns, tables), SQL cells, plotting, app deployment. Use when assembling Stage 9 notebooks, building data apps, or converting Jupyter to marimo .py format.

2.87k repo starsObserved in 3 repos
Development

new-notebook

Creates a Jupyter notebook with Jupytext pairing and registers it in _quarto.yml. Use when adding a new notebook.

2.87k repo starsObserved in 3 repos
Development

polars

Polars DataFrame library for high-performance data manipulation. Lazy/eager execution, expressions, I/O (CSV, Parquet, JSON), aggregations, joins, string/datetime ops, pandas interop. Use for Polars DataFrames or reading/writing Parquet files.

2.87k repo starsObserved in 3 repos
Development

python-econ-computing

Use when writing Python code for DSGE models, HANK models, numerical economic computation, causal inference, or quantitative economic data analysis

2.87k repo starsObserved in 3 repos
Development

r-python-translation

R-to-Python translation for data analysis. Maps R packages (tidyverse, ggplot2, fixest, survey, sf, plm) to Python equivalents (polars, plotnine, pyfixest, svy, geopandas). Use when user has R background or requests R-equivalent code comments.

2.87k repo starsObserved in 3 repos
Development