Skip to content
TrustedSkillsbeta
Back to all skills

Agent Evals

Checked
bagelhole·vlatest·agents·MIT

Automatically assesses agent performance using custom metrics and provides actionable feedback for improvement.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add bagelhole/devops-security-agent-skills --skill agent-evals -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

bagelhole

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned bagelhole/devops-security-agent-skills at 0365f57a07.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
0365f57a07
Manifest
devops/ai/agent-evals/SKILL.md
Scanned
1 file, 373 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The agent-evals skill provides capabilities for evaluating the performance of AI agents. It allows users to define evaluation criteria and metrics, then assesses agent outputs against these standards. This enables iterative improvement and ensures agents are meeting desired objectives.

When to use it

  • Testing new agent workflows: Evaluate a newly built agent's ability to complete tasks before deployment.
  • Comparing different agent designs: Determine which architecture or prompt engineering approach yields the best results.
  • Monitoring ongoing agent performance: Track key metrics over time to identify degradation and trigger retraining.
  • Benchmarking against competitors: Assess your agents’ capabilities relative to alternatives in the market.

Key capabilities

  • Define evaluation criteria.
  • Specify evaluation metrics.
  • Assess agent outputs.
  • Provide iterative improvement feedback.

Example prompts

  • "Evaluate this agent's response: [agent output] against these criteria: accuracy, completeness, and clarity."
  • "Give me a score for the agent’s performance on summarizing this document: [document content]."
  • "Compare the outputs of Agent A and Agent B when asked to write a Python function for sorting a list. Evaluate based on efficiency and correctness."

Tips & gotchas

The effectiveness of agent-evals depends heavily on clearly defined evaluation criteria and appropriate metrics. Vague or poorly chosen standards will lead to unreliable assessments.