XGBoost & LightGBM — gradient boosting for tabular data

Prerequisites: a Python environment with xgboost and lightgbm installed, plus tabular data to work on — the skill is a reference the agent consults, not software Install "XGBoost & LightGBM — gradient boosting for tabular data" for me. It gives my agent @tondevrel's gradient boosting reference: when to use each (XGBoost for smaller datasets, LightGBM for millions of rows), speed vs accuracy trade-offs, L1/L2 regularization, categorical handling, missing values, class imbalance, install quick reference and standard imports. Note the pinned versions (xgboost 2.0.3, lightgbm 4.3.0) — check current docs for API changes. MIT-licensed. Repository: https://github.com/tondevrel/scientific-agent-skills/blob/main/skills/xgboost-lightgbm/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, credentials only via the secure vault, allowed hosts declared in the SKILL.md. 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 "xgboost-lightgbm". 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. point the agent at my tabular dataset and tell it which library to use; nothing else — it's a reference). 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.