Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From experiment-tracker
Compares multiple ML experiment runs side-by-side using experiment records, building comparison tables, analyzing parameter sensitivity, generating visualizations, and identifying the best configuration.
How this command is triggered — by the user, by Claude, or both
Slash command
/experiment-tracker:compareThe summary Claude sees in its command listing — used to decide when to auto-load this command
Compare multiple ML experiment runs side-by-side to identify the best configuration. ## Steps 1. Load experiment records from the tracking store. 2. Select experiments to compare: 3. Build a comparison table: 4. Analyze parameter sensitivity: 5. Generate visualizations: 6. Identify the winning configuration: 7. Recommend next experiments to try. ## Format ## Rules - Only compare experiments with the same dataset version. - Use consistent metrics across all compared runs. - Statistical significance matters; do not draw conclusions from single runs.
Compare multiple ML experiment runs side-by-side to identify the best configuration.
Comparison: <N> experiments
Best Run: <experiment name>
Key Findings:
- <parameter X> has <impact> on <metric Y>
2plugins reuse this command
First indexed Mar 30, 2026
npx claudepluginhub costrict-plugins-repo/github-trending-plan --plugin experiment-tracker/compareCompares multiple ML experiment runs side-by-side using experiment records, building comparison tables, analyzing parameter sensitivity, generating visualizations, and identifying the best configuration.
/compare-modelsCompares multiple ML models on a shared dataset, computing accuracy, latency, memory, and cost metrics, then generates a ranked recommendation report.
/experimentDesigns an ML experiment with hypothesis, split strategy, leakage checks, and evaluation plan. Searches prior work, detects type (supervised, unsupervised, time-series, anomaly), and tailors workflow.
/reportGenerates formatted terminal report of AI experiments with stats, top tools, rating distribution, tags, recent activity, and latest details. Supports optional tool, tag, days, rating filters.