Install one, then just prompt in plain English. The FLOW.md fires the right skill at the right moment. No re-orchestration, no babysitting.
Featured
A research-first AI/ML research-engineer workflow for Claude Code
@mxslrUse when an existing model's results are disappointing and the user wants higher accuracy - 'accuracy is still too low', 'improve/boost the model', 'why is it…
@mxslrUse BEFORE training any model, to build correct train/val/test splits and hunt data leakage - the #1 cause of fake-high accuracy. Covers group/patient/subject…
@mxslrUse as the FIRST step of any ML task, before choosing a model, to inspect and understand the actual dataset. Works for a LOCAL dataset (Claude reads the files…
@mxslrUse when turning a trained model into something usable (an app, an inference function, a demo) or adding explainability. Selects the RIGHT interpretability…
@mxslrUse for 3D and point cloud tasks: point cloud classification, 3D semantic or instance segmentation, 3D object detection from LiDAR, and depth or mesh analysis,…
@mxslrUse for anomaly, outlier, and novelty detection across data types: industrial or visual defect detection, time-series or sensor anomalies and predictive…
@mxslr© 2026 Flowy · Free and open source
Built for Claude Code · Not affiliated with Anthropic
