Stats
Actions
Tags
From mltoolkit
Run cross-validated model comparison for the current task. Produces a leaderboard CSV + markdown.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mltoolkit:compareThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
An active session scratchpad at `.mltoolkit/session.py`. If missing, invoke `mltoolkit:setup` first, then the task-specific skill (`classify`/`regress`/`cluster`/`anomaly`).
An active session scratchpad at .mltoolkit/session.py. If missing, invoke mltoolkit:setup first, then the task-specific skill (classify/regress/cluster/anomaly).
.mltoolkit/session.py (look for imports of classify/regress/cluster/anomaly modules).python .mltoolkit/session.py --data <DATA> --target <TARGET> --output-dir .mltoolkit --stage compare
--target only if task is supervised..mltoolkit/results/leaderboard.csv and present as markdown.npx claudepluginhub olatechie/mltoolkit-pluginCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.