probabl-ai/skills

1

data-science-python-stack Opinionated Python stack for data-science / ML work — one library per job, organized into tiers (mandatory / user cho…

probabl-ai/skills

225

2

evaluate-ml-pipeline Methodology for evaluating a single sklearn-compatible learner (in particular, the `SkrubLearner` produced by `build-…

probabl-ai/skills

128

3

iterate-ml-experiment Owns the iteration loop on top of an ML workspace: the `journal/JOURNAL.md` index and the per-experiment `journal/NN_…

probabl-ai/skills

122

4

build-ml-pipeline Declare the pipeline from data source to predictor as a **skrub DataOps graph** (not as a bare `sklearn.Pipeline`). E…

probabl-ai/skills

121

5

python-api Look up the public API of a Python package against the *installed version* and cache what's worth keeping. Four shape…

probabl-ai/skills

120

6

python-code-style Owns Python code style for this stack: ruff for lint + format, numpydoc for docstrings. Three responsibilities — (1) …

probabl-ai/skills

120

7

organize-ml-workspace Decide where files live in an ML experimentation project: reusable code in `src/<pkg>/`, one `# %%` script per experi…

probabl-ai/skills

118

8

python-env-manager Single source of truth for "which Python environment manager does this project use, and how do I install a package wi…

probabl-ai/skills

117

9

test-ml-pipeline Owns the `tests/` folder of an ML workspace and the pairing rule between an experiment and its tests. Lightweight rou…

probabl-ai/skills

117

10

smoke-test-ml-pipeline Owns the smoke test contract for an ML experiment: a small, diagnostic-by-construction pytest that fits the experimen…

probabl-ai/skills

115

11

iterate-from-skore Source the next ML experiment proposal by **reading the audit digest** at `scratch/audit/<stem>/audit.md` (produced b…

probabl-ai/skills

112

12

iterate-from-user Source the next ML experiment proposal from the user via one of three entry points selected by `AskUserQuestion`: (a)…

probabl-ai/skills

112

13

audit-ml-pipeline Owns the `audit/` folder: one `# %%` (jupytext percent) Python file per experiment, aligned 1:1 with `experiments/NN_…

probabl-ai/skills

99

14

explore-ml-data Owns data understanding BEFORE any model is designed. Places and executes `data/eda.py` (a jupytext `# %%` script) vi…

probabl-ai/skills

87

15

data-scientist-companion Front door for an ML / data-science session. Single responsibility: read the workspace state on the opening turn, pic…

probabl-ai/skills

1