{"@context":"https://schema.org","@graph":[{"@type":"SoftwareApplication","@id":"https://hol.org/registry/plugins/jananthan-paramsothy%2Fml-pipeline#plugin","name":"ML Pipeline","description":"Ask a coding agent to \"train a model on this data\" and it calls .fit() within five minutes. Often it fits the scaler before splitting — and that leak doesn't surface until production. It isn't being careless. It's being helpful the way it was trained to be: a number, fast. The number is wrong in a way that looks fine. ml-pipeline makes that impossible. Sixteen steps, fixed order, data first. The split happens before feature engineering. The test set is touched once, at the end. At four gates the agent stops, shows its work with figures, and waits for your go-ahead. • marimo notebooks, matplotlib figures at every data step • PIPELINE.md logs every step and approval — sessions resume, not restart • Security scan: 90/100 (A), zero critical or high findings • Apache-2.0, one 7.8 KB skill file, no dependencies • Works in Claude Code, Codex, and Kimi Code","url":"https://hol.org/registry/plugins/jananthan-paramsothy%2Fml-pipeline","applicationCategory":"Development & Workflow","softwareVersion":"0.1.1","creator":"Jananthan Paramsothy","codeRepository":"https://github.com/jananthan30/ml-pipeline","sameAs":["https://github.com/jananthan30/ml-pipeline","https://github.com/jananthan30/ml-pipeline"],"image":["https://storage.googleapis.com/inscription-uploads/plugin-launch-media%2Fjananthan-paramsothy_ml-pipeline%2F81221a0b-9e2e-4fa4-b628-1cbad6bc9829%2Fbbbc4791-a084-4dbf-bf07-10cb2dff6bbc.png","https://storage.googleapis.com/inscription-uploads/plugin-launch-media%2Fjananthan-paramsothy_ml-pipeline%2F81221a0b-9e2e-4fa4-b628-1cbad6bc9829%2F6a03d519-adef-4e98-9eeb-1e0587a32e59.png","https://storage.googleapis.com/inscription-uploads/plugin-launch-media%2Fjananthan-paramsothy_ml-pipeline%2F81221a0b-9e2e-4fa4-b628-1cbad6bc9829%2F7979fc58-3d7b-40c7-bc4d-2a7083169749.png","https://storage.googleapis.com/inscription-uploads/plugin-launch-media%2Fjananthan-paramsothy_ml-pipeline%2F81221a0b-9e2e-4fa4-b628-1cbad6bc9829%2Fe9352e33-a5c1-4b67-b037-2d9b2476d7ee.png","https://img.shields.io/endpoint?url=https%3A%2F%2Fhol.org%2Fapi%2Fregistry%2Fbadges%2Fplugin%3Fslug%3Djananthan-paramsothy%252Fml-pipeline%26metric%3Dtrust%26style%3Dflat","https://img.shields.io/endpoint?url=https%3A%2F%2Fhol.org%2Fapi%2Fregistry%2Fbadges%2Fplugin%3Fslug%3Djananthan-paramsothy%252Fml-pipeline%26metric%3Dsecurity%26style%3Dflat"],"additionalProperty":[{"@type":"PropertyValue","name":"HOL Trust Score","value":71},{"@type":"PropertyValue","name":"Security Score","value":71},{"@type":"PropertyValue","name":"Skills Bundled","value":1},{"@type":"PropertyValue","name":"MCP Servers Bundled","value":0},{"@type":"PropertyValue","name":"Apps Bundled","value":0},{"@type":"PropertyValue","name":"Latest Launch","value":"ML Pipeline"},{"@type":"PropertyValue","name":"Launch Tagline","value":"Enforces a strict 16-step data-first ML workflow — data inspection, EDA, and pro"}]}]}