Skip to content
Back to skills

Agent Evals

ASecurity

Build repeatable evaluations for an agent from production failures, deterministic verifiers, cost, latency, and trace evidence.

  • 3 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 19, 2026
ai-agents

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 23, 2026

npx -y skills add getedgehq/skills --skill agent-evals --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Agent Evals?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Agent Evals
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/getedgehq-agent-evals/badge)](https://www.skillsdirectory.com/skills/getedgehq-agent-evals)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: agent-evals
description: Build repeatable evaluations for an agent from production failures, deterministic verifiers, cost, latency, and trace evidence.
---

Turn representative failures into isolated tasks with objective checks and comparable runs.

Files in this skill

  • DERIVATION.json1.8 KB
  • LICENSE10.5 KB
  • SKILL.md5.4 KB
  • agents/openai.yaml221 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.