← All skills

agent-evals

65 / 100 · Review before installing

Check before installing. Some of what it can do is expected: a devops skill usually runs commands, installs tools and uses cloud credentials.

By BagelHole/DevOps-Security-Agent-Skills (GitHub) · devops · 1,197 stars · scanned at commit 0365f57

Build automated evaluation suites for AI agents using golden datasets, rubrics, and regression gates. Use when shipping agent features, validating prompt changes, or gating deployments on quality.

Works with any agent that supports SKILL.md skills.

What this skill can do

Safer alternatives

Low-risk skills in the same category (devops) that look related. Check that one does what you need.

• 80 Low riskpromptfoo-evalspromptfoo/promptfoo · 26,951 stars

Install

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

if [ -e ~/.agents/skills/'agent-evals' ] || [ -L ~/.agents/skills/'agent-evals' ]; then echo 'A skill folder named agent-evals already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/BagelHole/DevOps-Security-Agent-Skills' "$d" && git -C "$d" checkout --quiet '0365f57a079b1332f95cf26e31dd2d5332a8399f' -- 'devops/ai/agent-evals' && mkdir -p ~/.agents/skills && cp -R "$d"/'devops/ai/agent-evals' ~/.agents/skills/'agent-evals' && 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/'agent-evals' ~/.claude/skills/'agent-evals' (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 BagelHole/DevOps-Security-Agent-Skills shows the score of its lowest-scoring skill.

[![SkillTrust](https://zalavijaysinh.github.io/skilltrust/badges/BagelHole/DevOps-Security-Agent-Skills.svg)](https://zalavijaysinh.github.io/skilltrust/repos/BagelHole/DevOps-Security-Agent-Skills/)

Score history