Feature Engineering Toolkit — create, select, and transform ML features
Engineer better features for machine learning: create interaction terms, select the most relevant features, apply scaling/encoding transforms — the agent generates and executes Python code (review before it runs) and reports feature importance and impact
- What
- Engineer better features for machine learning: create interaction terms, select the most relevant features, apply scaling/encoding transforms — the agent generates and executes Python code (review before it runs) and reports feature importance and impact
- Cost
- Free
- Needs
- Python 3 with pandas and scikit-learn for the generated code to run — a dataset whose features need engineering; file access permissions for the project directory
- Install
- Copy the installer prompt below into your Muse — your agent does the rest.
Curated by Skill Harbor — @jeremylongshore's engineering-features-for-machine-learning skill, listed here with credit to its creator (authored by Jeremy Longshore, designed for Claude Code): a feature-engineering toolkit for machine learning that creates, selects, and transforms features to improve model performance. The workflow: Claude analyzes the request, generates Python code for the feature-engineering task (interaction terms like age × income, top-K feature selection via Random Forest or SelectKBest, scaling/normalization/encoding transforms), executes it, then reports performance metrics and insights (feature importance, impact of transformations). It covers best practices (data validation first, scale numerics, encode categoricals properly), prerequisites, error handling, and integration with other skills for full ML pipelines. Honest caveats: the skill's allowed-tools include Bash(cmd:*) — the agent generates AND EXECUTES code, so review what it plans to run before it runs (especially on shared or production data); it is trigger-driven ("engineer features" style phrases), not a general ML reference — pair it with a dedicated ML skill for modeling. MIT licensed. Skill Harbor never reviews the code, review it yourself before use. Discovered via skills.sh.
Version:
Quick answer
Feature Engineering Toolkit is a free listing for a machine-learning feature-engineering toolkit that creates, selects and transforms features. The workflow: Claude analyzes the request, generates Python code to review before it runs, then executes it, then reports performance metrics, feature importance and impact. It covers interaction terms, top-K selection via Random Forest or SelectKBest, and scaling, normalization and encoding transforms.
Install
Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 11, 2026📌 Pinned version: commit cfae287Step 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 pandas and scikit-learn for the generated code to run — a dataset whose features need engineering; file access permissions for the project directory Install "Feature Engineering Toolkit — create, select, and transform ML features" for me. It gives my agent @jeremylongshore's feature-engineering workflow (by Jeremy Longshore, designed for Claude Code): analyze the feature-engineering request, generate Python code for creating interaction terms, selecting top features, and applying scaling/encoding transforms, execute it, and report feature importance and impact — with best practices, error handling, and integration hooks for full ML pipelines. MIT licensed. NOTE: this skill's allowed-tools include Bash(cmd:*) — it will generate AND EXECUTE code; always review what it plans to run before it runs. Repository: https://raw.githubusercontent.com/jeremylongshore/tons-of-skills-marketplace/cfae287053f6d06aa2c58b548f263476d520238a/plugins/ai-ml/feature-engineering-toolkit/skills/engineering-features-for-machine-learning/SKILL.md Pinned version: install the code at commit cfae287053f6d06aa2c58b548f263476d520238a 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 "engineering-features-for-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. ensure pandas/scikit-learn are installed; point the agent at my dataset; review generated code before execution — the skill runs shell commands). 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
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
- cfae287 · 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 : No commands, network calls, packages, file writes or API keys detected.
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.