StamKavid

StamKavid/last-ds-mile

Plugin Claude Code

A guided data-science lifecycle for Claude Code, with leakage and honesty checks built into every stage.

StamKavid/last-ds-mile

Plugin Claude Code

A guided data-science lifecycle for Claude Code: frame, explore, baseline, validate, model, evaluate, and report — with leakage and honesty checks built into every stage.

StamKavid/last-ds-mile

Instructions file

Instructions for StamKavid/last-ds-mile, covering claude.md, what this repo is, hard rules, working in this repo and style.

StamKavid/last-ds-mile

Agent

Fast structural profiling sweep for a dataset — shape, dtypes, missingness, cardinality, duplicate keys. Use during /ds-data or /ds-explore for a quick first-pass profile. Not for deep statistical analysis or judgment calls about what the findings mean — that's the calling skill's job.

StamKavid/last-ds-mile

Agent

Runs the ds-method discipline checklist against a notebook or pipeline before /ds-report — baseline present, validation strategy sound, slice performance checked, metric matches the problem. Use before final reporting/handoff, or when asked to sanity-check a DS pipeline end to end. Not for hunting leakage specifically…

StamKavid/last-ds-mile

Agent

Adversarially hunts for target leakage across a feature pipeline — features that encode the target directly, temporal leakage where future information reaches training data, and validation-split leakage. Use before /ds-model or /ds-report when a metric looks implausibly good, or as a final check before a pipeline…

StamKavid/last-ds-mile

Command

Score a dumb baseline so the model has a number to beat.

StamKavid/last-ds-mile

Command

Rewrite the results as a one-page brief with no jargon.

StamKavid/last-ds-mile

Command

Profile a dataset — columns, rows, dtypes, missingness, provenance.

StamKavid/last-ds-mile

Command

Serve a packaged model with monitoring, drift detection, and rollback.

StamKavid/last-ds-mile

Command

Evaluate a model at an operating point, by slice, not one aggregate score.

StamKavid/last-ds-mile

Command

Interpret a model — permutation importance and SHAP — to check it learned sense.

StamKavid/last-ds-mile

Command

Explore a dataset — distributions, feature-target relationships, hypotheses.

StamKavid/last-ds-mile

Command

Frame a vague data request into a target, a decision, and a success metric.

StamKavid/last-ds-mile

Command

Make the project reproducible — pinned environment, model card, rerunnable.

StamKavid/last-ds-mile

Command

Diagnose what the evaluation found and route back to the stage that fixes it.

StamKavid/last-ds-mile

Command

Capture a failure-and-fix pair as a project lesson.

StamKavid/last-ds-mile

Command

Train, tune, and compare candidate models against baseline and validation.

StamKavid/last-ds-mile

Command

Package a model as a servable unit and prove prediction parity.

StamKavid/last-ds-mile

Command

Clean data and engineer features without leaking the target.

StamKavid/last-ds-mile

Command

Write results up for stakeholders with assumptions and limitations.

StamKavid/last-ds-mile

Command

Design a leakage-safe train/test split or cross-validation scheme.

StamKavid/last-ds-mile

Command

Show the Last DS Mile pipeline map and which stage comes next.

StamKavid/last-ds-mile

Hook

Runs when a session starts on startup, resume and clear, executing ds-python.sh via bash. From StamKavid/last-ds-mile.