Agent Optimization

by Prism-Shadow

Agent Optimization 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 Optimization

Copy Agent Optimization 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-optimization ~/.claude/skills/agent-optimization

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

What Agent Optimization does

Agent Optimization improves one Test Agent through an evidence → hypothesis → Candidate → evaluation → accept or rollback loop. It uses a frozen Benchmark, Scoreboard, and public Test Traces as black-box feedback while delegating all evaluation to an agent-evaluation subagent.

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

Documentation

README

Excerpt

Agent Optimization

Improve one Test Agent through an evidence → hypothesis → Candidate → evaluation → accept or rollback loop. Use public Statements, scores, and Test Traces as black-box feedback. Delegate every evaluation to an agent-evaluation subagent; never run or score the Test Agent directly.

Before you start

If the request does not identify the Test Agent, frozen Benchmark, desired target score, positive Run count, and round limit, ask for the missing inputs. When they are already supplied, proceed without asking the user to restate them.

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

Frequently asked about Agent Optimization

What else does Prism-Shadow publish alongside Agent Optimization?
Agent Optimization 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 Evaluation and AgentHub Models. Each one is a separate skill with its own page in this directory, installs the same way Agent Optimization 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 Optimization compare to other AI Engineering skills?
Agent Optimization ranks #988 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 Optimization against them. Open each page to compare what they document and how they install.