relbench-api
100 / 100 · Low risk
Fine to try.
How to read a relational benchmark database and its task tables through the relbench library from a sanitized copy: binding the library to the copy, the loader's truncation argument per regime, the task-table masks, the private builders and the calls that probe for stripped labels, and the modelling stack the library ships with. Use when the task's data reference is a relbench dataset, in setup and in every implementation.
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/'relbench-api' ] || [ -L ~/.agents/skills/'relbench-api' ]; then echo 'A skill folder named relbench-api already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Leeroo-AI/kapso' "$d" && git -C "$d" checkout --quiet '35f7b9b26a6b3864fdc8c018577d448c2840345b' -- 'src/kapso/harness/bundled/predictive-modelling/skills/relbench-api' && mkdir -p ~/.agents/skills && cp -R "$d"/'src/kapso/harness/bundled/predictive-modelling/skills/relbench-api' ~/.agents/skills/'relbench-api' && 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/'relbench-api' ~/.claude/skills/'relbench-api' (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/Leeroo-AI/kapso/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-13 | 35f7b9b | 100 |
| 2026-11-09 | eb1d3e8 | 100 |
| 2026-11-07 | 081f710 | 100 |