← All skills

AI Agent Evaluation

85 / 100 · Low risk

Fine to try.

By PramodDutta/qaskills (GitHub) · coding · 246 stars · scanned at commit 8d6cf5f

Comprehensive evaluation patterns for AI agents including multi-turn conversation testing, LLM-as-judge frameworks, benchmark suites, regression detection, and systematic eval pipelines for measuring agent quality and safety.

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/'ai-agent-evaluation' ] || [ -L ~/.agents/skills/'ai-agent-evaluation' ]; then echo 'A skill folder named ai-agent-evaluation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/PramodDutta/qaskills' "$d" && git -C "$d" checkout --quiet '8d6cf5f6db54e56d14bd0ea2c9cfe7a097fb07ee' -- 'seed-skills/ai-agent-eval' && mkdir -p ~/.agents/skills && cp -R "$d"/'seed-skills/ai-agent-eval' ~/.agents/skills/'ai-agent-evaluation' && 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/'ai-agent-evaluation' ~/.claude/skills/'ai-agent-evaluation' (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 PramodDutta/qaskills shows the score of its lowest-scoring skill.

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

Score history