auditing-data-and-ground-truth
100 / 100 · Low risk
Fine to try.
Audit datasets, joins, labels, and ground truth before analysis or modeling. Use when data meaning, row grain, time semantics, source-of-truth reliability, or label construction may invalidate conclusions; not for general model evaluation after the evidence base is already trusted.
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/'auditing-data-and-ground-truth' ] || [ -L ~/.agents/skills/'auditing-data-and-ground-truth' ]; then echo 'A skill folder named auditing-data-and-ground-truth already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/aiopshwang/data-analysis-ml-agent-skills' "$d" && git -C "$d" checkout --quiet '82a1dc2c7a9f40a052b20f32dcb805d86132f29b' -- 'skills/auditing-data-and-ground-truth' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/auditing-data-and-ground-truth' ~/.agents/skills/'auditing-data-and-ground-truth' && 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/'auditing-data-and-ground-truth' ~/.claude/skills/'auditing-data-and-ground-truth' (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
[](https://zalavijaysinh.github.io/skilltrust/repos/aiopshwang/data-analysis-ml-agent-skills/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-07 | 82a1dc2 | 100 |