SkillTrust

← All skills

evals-design

90 / 100 · Low risk

Fine to try. Some of what it can do is expected: a coding skill usually runs build and test commands.

By tonone-ai/tonone (GitHub) · coding · 77 stars · scanned at commit 117b48f

Design an LLM eval — task schema, scoring rubric, dataset composition, and pass/fail thresholds. Use when asked to "design an LLM eval", "write a scoring rubric", or "how do we measure this model".

Works with any agent that supports SKILL.md skills.

What this skill can do

Runs commands on your computer

The author does not mention this. It runs automatically when the plugin is installed. Expected for a coding skill.

Found in 29 places.

Show 17 more

and 9 more places

Connects to the internet

The author does not mention this. It runs automatically when the plugin is installed.

Found in 1 place.

Other copies in this repository

tonone-ai/tonone has 1 more folder with a skill named evals-design. This page shows the lowest-scoring copy.

Install

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

if [ -e ~/.agents/skills/'evals-design' ] || [ -L ~/.agents/skills/'evals-design' ]; then echo 'A skill folder named evals-design already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/tonone-ai/tonone' "$d" && git -C "$d" checkout --quiet '117b48ffd82ffc8429954da42f2bf062e84e1b26' -- 'skills/evals-design' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/evals-design' ~/.agents/skills/'evals-design' && 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/'evals-design' ~/.claude/skills/'evals-design' (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 tonone-ai/tonone shows the score of its lowest-scoring skill.

SkillTrust badge for tonone-ai/tonone

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/tonone-ai/tonone.svg)](https://zalavijaysinh.github.io/skilltrust/repos/tonone-ai/tonone/)

Score history

DateVersionScore
2026-11-13117b48f90
2026-11-08437fb6290