Machine Learning — end-to-end PyTorch + scikit-learn pipelines with interpretability
Build reproducible end-to-end ML pipelines with PyTorch and scikit-learn: structured experiment management, stratified cross-validation, Optuna hyperparameter tuning, SHAP interpretability, and experiment tracking with a test-set-touched-once discipline
- What
- Build reproducible end-to-end ML pipelines with PyTorch and scikit-learn: structured experiment management, stratified cross-validation, Optuna hyperparameter tuning, SHAP interpretability, and experiment tracking with a test-set-touched-once discipline
- Cost
- Free
- Needs
- Python 3 with PyTorch, scikit-learn, Optuna, SHAP, numpy installed (pip install torch scikit-learn optuna shap numpy) — a labeled dataset to train on; GPU recommended for deep learning examples
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @itallstartedwithaidea's machine-learning skill, listed here with credit to its creator: an end-to-end ML pipeline construction guide that bridges the gap between a working notebook and a production pipeline. It enforces software-engineering discipline for experiments — version-controlled runs, deterministic training, proper train/validation/test splits with stratified cross-validation, systematic hyperparameter optimization with Optuna, learning-curve analysis, and interpretability as a first-class requirement (SHAP values, feature importance, partial dependence plots for every model — no black-box predictions for scientific or business-critical applications). It includes platform compatibility notes (Cursor, VS Code, Windsurf, Claude Code, Cline, aider), a mermaid pipeline diagram, and working PyTorch implementation code. Honest caveats: the repo is commercially branded ("Agent Skills™ by googleadsagent.ai™") but the skill itself is substantive and free; deep learning examples assume GPU availability for reasonable training times; classical ML coverage is thin next to the dedicated scikit-learn skills — pair accordingly. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Machine Learning is a free listing for an end-to-end ML pipeline guide bridging the gap between a working notebook and a production pipeline. It enforces experiment discipline: version-controlled runs, deterministic training, proper train, validation and test splits, and stratified cross-validation. It adds systematic hyperparameter optimization with Optuna, learning-curve analysis, and interpretability through SHAP values, feature importance and partial dependence plots.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit 7a04ccbStep 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: Python 3 with PyTorch, scikit-learn, Optuna, SHAP, numpy installed (pip install torch scikit-learn optuna shap numpy) — a labeled dataset to train on; GPU recommended for deep learning examples Install "Machine Learning — end-to-end PyTorch + scikit-learn pipelines with interpretability" for me. It gives my agent @itallstartedwithaidea's end-to-end ML workflow: structured experiment management, proper train/validation/test splits with stratified cross-validation, systematic hyperparameter tuning with Optuna, interpretability with SHAP/feature importance/partial dependence plots, and experiment tracking — enforcing the test-set-touched-once discipline. MIT licensed. Repository: https://raw.githubusercontent.com/itallstartedwithaidea/agent-skills/7a04ccbde5f96d4bfe99a15a7e6fd96a7a0d4cd6/skills/scientific-research/machine-learning/SKILL.md Pinned version: install the code at commit 7a04ccbde5f96d4bfe99a15a7e6fd96a7a0d4cd6 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 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 "machine-learning". 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 torch scikit-learn optuna shap numpy; prepare my labeled dataset; confirm a GPU is available if I want the deep learning examples). 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.
Saved to your recent installs. Find it anytime on /connect.
🔒 Security, provenance and what this touches
- It can download and install software packages.
What the scan found — excerpts from the install prompt
- installs packages — Prerequisites: Python 3 with PyTorch, scikit-learn, Optuna, SHAP, numpy installed (pip install torch scikit-le · Prérequis : Python 3 avec PyTorch, scikit-learn, Optuna, SHAP, numpy installés (pip install torch scikit-learn
The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?
Verification certificate
Dated facts about what was checked for this listing, and how. This is not a safety certification.
- Pinned version
- 7a04ccb · 2026-10-13
- Sandbox install test
- Install ran in our test sandbox · Nov 11, 2026
- Creator identity
- Not verified
- Fingerprint watch
- Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
- Install prompt analysis
- 2026-10-13 : installs packages
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Questions
How do I install a skill?
Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.
Where does my money go?
Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.
What does the ✓ next to a creator’s name mean?
It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.