skills sourced live from GitHub · all skills listed are free · each skill is provided under its author's license.
home / AI Agents & MCP / Agent Evals Skill by @BagelHole
The skill is the devops/ai/agent-evals folder inside that repository. Copy it into the folder your agent loads skills from; check your agent's documentation for where that is.
Shows how to build automated evaluation suites for AI agents with golden datasets, rubrics, LLM-as-judge scoring and CI regression gates.
Covers four layers of evaluation: prompt-level checks, tool-decision quality, multi-step end-to-end tasks and adversarial safety. It includes Promptfoo configuration, GitHub Actions wiring and advice on tracking drift so prompt changes cannot silently degrade behaviour.
Written and maintained by @BagelHole. It is published under the MIT license, which allows reuse with attribution. See the author profile. SkillDirectory does not claim authorship: this page adds our own review and links back to the original, and the skill's text belongs to its author.
(Excerpt. Full file: https://github.com/BagelHole/DevOps-Security-Agent-Skills/blob/main/devops/ai/agent-evals/SKILL.md)
Excerpt only, quoted from the author's repository. Open the repository for the complete file.