← All skills

eval-designer

80 / 100 · Low risk

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

By NickCrew/Claude-Cortex (GitHub) · coding · 68 stars · scanned at commit bb47af7

Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.

Works with any agent that supports SKILL.md skills.

What this skill can do

Install

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

if [ -e ~/.agents/skills/'eval-designer' ] || [ -L ~/.agents/skills/'eval-designer' ]; then echo 'A skill folder named eval-designer already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NickCrew/Claude-Cortex' "$d" && git -C "$d" checkout --quiet 'bb47af79ad3befe01ae01940fcf5f16e30a1b6df' -- 'skills/eval-designer' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/eval-designer' ~/.agents/skills/'eval-designer' && 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/'eval-designer' ~/.claude/skills/'eval-designer' (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 NickCrew/Claude-Cortex shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/NickCrew/Claude-Cortex.svg)](https://zalavijaysinh.github.io/skilltrust/repos/NickCrew/Claude-Cortex/)

Score history