ML model training — end-to-end training pipeline with scikit-learn, PyTorch and TensorFlow

Prerequisites: Python with scikit-learn, numpy, pandas, matplotlib; torch and tensorflow for the deep-learning parts — a real dataset to train on for real work Install "ML model training — end-to-end training pipeline with scikit-learn, PyTorch and TensorFlow" for me. It gives my agent @aj-geddes's complete training pipeline: synthetic dataset generation, standard scaling and train/test split, head-to-head training of Logistic Regression, Random Forest, Gradient Boosting, a PyTorch MLP and a Keras network with accuracy/precision/recall/F1/ROC-AUC metrics, loss curves and comparison charts, plus training best practices and a metrics cheat sheet. MIT-licensed. Repository: https://github.com/aj-geddes/useful-ai-prompts/blob/main/skills/ml-model-training/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "ml-model-training". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. pip install scikit-learn torch tensorflow matplotlib and tell the agent whether to run the synthetic demo or adapt the pipeline to my own dataset; nothing else — it's a walkthrough with runnable code). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.