/meta--pipeline-run

Generates a new skill from a plain-language description, together with its permission manifest and a test file.

Scans your project, detects its tech stack and activates only the relevant skills, saving the choice as a project configuration file.

Turns a raw dataset into a clean, well-split, leakage-free base for modeling: profiling, cleaning, train/validation/test splits and balance checks.

Designs features for a tabular ML problem inside a leakage-safe pipeline: encodings, scaling, interactions and date-based features.

Gives an ML project reproducible training, experiment tracking, a model registry and CI, sized to the team instead of a full platform.

Takes a trained model to production: batch or online serving pattern, prediction API, packaging, monitoring, drift detection and rollback plan.