Skip to content
TrustedSkillsbeta
Back to all skills

Agent Evaluation

Checked
tavi-agency·vlatest·agents·MIT

Evaluates Tavi Agency agents' performance against defined metrics, providing 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 tavi-agency/antigravity-awesome-skills --skill agent-evaluation -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

tavi-agency

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 tavi-agency/antigravity-awesome-skills at c9a76a2d94.

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

Commit
c9a76a2d94
Manifest
skills/agent-evaluation/SKILL.md
Scanned
2 files, 139 lines
Copies in repo
2 — all of them scanned
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

This skill, tavi-agency-agent-evaluation, provides a mechanism for evaluating the performance of AI agents. It assesses agent behavior and outputs structured feedback based on predefined criteria. The evaluation results can be used to identify areas for improvement in agent design or training.

When to use it

  • Debugging Agent Behavior: After an agent exhibits unexpected actions, use this skill to diagnose the root cause.
  • Performance Benchmarking: Regularly evaluate agents against a standardized set of tasks to track progress and compare different versions.
  • Training Data Validation: Assess how well an agent generalizes to new scenarios after training on a specific dataset.
  • Agent Comparison: Evaluate multiple agents performing similar tasks to determine which performs best based on defined metrics.

Key capabilities

  • Structured feedback generation
  • Assessment of agent behavior
  • Evaluation against predefined criteria
  • Performance benchmarking

Example prompts

  • "Evaluate the agent's response to this user query: 'What is the capital of France?'"
  • "Assess the agent’s performance in completing task X, focusing on efficiency and accuracy."
  • "Provide feedback on the agent’s interaction with the user during scenario Y."

Tips & gotchas

The skill's effectiveness depends on clearly defined evaluation criteria. Ensure these are specific and measurable for accurate assessment.