Agent Evaluation

by Prism-Shadow

Agent Evaluation is an AI Engineering skill for Claude Code, published by Prism-Shadow in penguin-harness.

1.5K stars149 forkson Prism-Shadow/penguin-harnessAdded 2026/08/19+21% in starsRepository updated 2026/08/19

View source on GitHub Download repo ZIP

agentagentic-aiaibuild-toolclaude-codedeepseekdeepseek-harnessdesktopharnessllmrsiself-evolving

Install in seconds

Install Agent Evaluation

Copy Agent Evaluation into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.

terminal

npx degit https://github.com/Prism-Shadow/penguin-harness/tree/main/packages/skills/skills/agent-evaluation ~/.claude/skills/agent-evaluation

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Prism-Shadow/penguin-harness.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file: packages/skills/skills/agent-evaluation/SKILL.md in Prism-Shadow/penguin-harness
Installs to: ~/.claude/skills/agent-evaluation
Collection: One of 21 skills cataloged from this repository
Category: AI Engineering — 2451 skills

What Agent Evaluation does

Agent Evaluation runs one specified test agent on one benchmark case exactly once, privately scores the execution, and returns one protocol result. Use it when a run_subagent caller needs a single isolated agent evaluation without managing loops or scoreboards.

Agent Evaluation is cataloged under AI Engineering on DirSkills. Agent Evaluation comes from a repository tagged agent, agentic-ai, ai, build-tool and claude-code.

Documentation

README

Excerpt

Agent Evaluation

Handle one evaluation request from a run_subagent caller: run the specified Test Agent on one Benchmark Case once, score that execution privately, and return one protocol result.

The top-level Benchmark Designer or Optimizer owns all Case and Run loops, concurrency, and follow-up handling. This worker handles no other Case or Run, launches no evaluator or subagent, modifies no Agent or Benchmark, and never writes scoreboard.yaml. Use the Penguin CLI only to launch the specified Test Agent; do not use it to create another phase, designer, optimizer, or evaluator.

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Agent Evaluation

What else does Prism-Shadow publish alongside Agent Evaluation?
Agent Evaluation is one of 21 skills that DirSkills catalogs from Prism-Shadow/penguin-harness, the repository it ships in. Its siblings there include Agent Creation, Agent Optimization and AgentHub Models. Each one is a separate skill with its own page in this directory, installs the same way Agent Evaluation does, and is maintained by Prism-Shadow in that same repository. The rest of the collection is listed on the Prism-Shadow/penguin-harness page.
How does Agent Evaluation compare to other AI Engineering skills?
Agent Evaluation ranks #998 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Agent Evaluation against them. Open each page to compare what they document and how they install.