← All skills

ml-testing-strategy

100 / 100 · Low risk

Fine to try.

By makifbaysal/tasktrooper (GitHub) · coding · 122 stars · scanned at commit 96d8af7

Use when writing tests for data or ML code — what to test at each layer (transforms, schemas, properties, pipeline smoke, model-quality thresholds, determinism and parity), how to build small synthetic fixtures, and what not to test

Works with any agent that supports SKILL.md skills.

What this skill can do

We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.

Install

Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.

if [ -e ~/.agents/skills/'ml-testing-strategy' ] || [ -L ~/.agents/skills/'ml-testing-strategy' ]; then echo 'A skill folder named ml-testing-strategy already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/makifbaysal/tasktrooper' "$d" && git -C "$d" checkout --quiet '96d8af7c0a98ecc099980a6d7ce4681b2a0b0fa3' -- 'catalog/agents/data-scientist/skills/ml-testing-strategy' && mkdir -p ~/.agents/skills && cp -R "$d"/'catalog/agents/data-scientist/skills/ml-testing-strategy' ~/.agents/skills/'ml-testing-strategy' && rm -rf "$d"; fi

Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'ml-testing-strategy' ~/.claude/skills/'ml-testing-strategy' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.

Badge for your README

The badge for makifbaysal/tasktrooper shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/makifbaysal/tasktrooper.svg)](https://zalavijaysinh.github.io/skilltrust/repos/makifbaysal/tasktrooper/)

Score history