Rank machine learning experiment results and recommend next optimization actions.
npx skills add https://github.com/ChuaHanChong/ml-optimizer --skill analyze-chuahanchong
Please help me install this Agent Skill. Skill: analyze Source: https://github.com/ChuaHanChong/ml-optimizer/tree/main/skills/analyze Command: npx skills add https://github.com/ChuaHanChong/ml-optimizer --skill analyze-chuahanchong
This Skill automates the analysis of machine learning experiment results, providing insights into performance trends, hyperparameter impacts, and failure modes to guide future optimization efforts.
Analyze the completed ML experiment results in the project directory.
High-intent search queries and answers about installing and using this skill.
The Skill analyzes machine learning experiment results to identify hyperparameter correlations and recommend the next optimization action, logging findings to error trackers and dead-end catalogs for branch-aware analysis.
The best way to rank machine learning experiments against a baseline is using this Skill, which processes specified primary metrics and optimization directions to calculate performance improvements and identify top-performing models.
Hyperparameter impact analysis works by processing completed experiment results to identify correlations between specific parameters, such as learning rates or batch sizes, and the primary performance metrics to guide future optimization efforts.
Yes, you can use this Skill with its pandas, scikit-learn, and numpy dependencies to perform failure analysis, investigating why experiments diverged or failed to inform debugging and strategy adjustments.
To decide whether to continue tuning, pivot, or stop optimization, this Skill evaluates your experiment results and recommends the next optimization action based on identified performance trends and failure modes.
Yes, branch-aware experiment analysis supports logging failure findings to error trackers and dead-end catalogs, helping you document why specific branches diverged or failed during hyperparameter tuning.
ChuaHanChongAnalyze ML optimization session logs to generate actionable plugin improvement suggestions.
ovachieverAutomate ML experiment tracking and model registry management via the wandb API.
andikarachmanPreprocess raw data into clean, analysis-ready datasets with pandas and numpy.
thisismynewfmail-uiLog machine learning experiment metrics and visualize training progress with W&B.
