Stats
Actions
Tags
From mltoolkit
Build a clustering pipeline — KMeans, DBSCAN, Agglomerative, GMM. Runs inline with elbow + silhouette + PCA visualization.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mltoolkit:clusterThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
- Session scratchpad: `.mltoolkit/session.py`
.mltoolkit/session.py{SKILL_DIR}/references/cluster_reference.py.mltoolkit/:
python {PLUGIN_ROOT}/scripts/stage_session.py --task cluster --dest .mltoolkit
This copies cluster_reference.py as session.py, plus model_zoo.py and the _shared/ package, co-located.python .mltoolkit/session.py --data <DATA> --output-dir .mltoolkit --stage eda.mltoolkit/artifacts/elbow.png — suggest a k to the user.python .mltoolkit/session.py --data <DATA> --output-dir .mltoolkit --stage compare --n-clusters <K>mltoolkit:package.n_clusters is ignored (density-based).Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub olatechie/mltoolkit-plugin