🧪
AI EngineeringPython

Optimize

by evo-hq

Optimize is an AI Engineering skill for Claude Code, published by evo-hq in evo.

1.4K stars105 forkson evo-hq/evoAdded 2026/08/19+1% in starsRepository updated 2026/07/17
agent-skillsautonomous-agentsautoresearchclaude-codecode-optimizationcodexevolutionary-algorithmsllm-agents
Install in seconds
Install Optimize
Copy Optimize 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/evo-hq/evo/tree/main/plugins/evo/skills/optimize ~/.claude/skills/optimize

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/evo-hq/evo.git

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

In this catalog

Source file
plugins/evo/skills/optimize/SKILL.md in evo-hq/evo
Installs to
~/.claude/skills/optimize
Collection
One of 8 skills cataloged from this repository
Category
AI Engineering2451 skills

What Optimize does

Optimize drives structured autoresearch iteration after evo:discover and the baseline commit, orchestrating subagents to run experiments and improve the current best frontier. Use it when the user invokes /evo:optimize or asks to try ideas, variants, or continue an evo search.

Optimize is cataloged under AI Engineering on DirSkills. Optimize comes from a repository tagged agent-skills, autonomous-agents, autoresearch, claude-code and code-optimization.

Documentation

README

Run the evo optimization loop. Each round, the orchestrator writes structured briefs and spawns subagents that execute within them. Each subagent is semi-autonomous: it reads the pointer traces, forms the concrete edit, runs experiments, and can iterate within its branch. Runs until interrupted or the stall limit is reached.

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

Commands Optimize provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /optimize
  • /workflows

Frequently asked about Optimize

  • What else does evo-hq publish alongside Optimize?

    Optimize is one of 8 skills that DirSkills catalogs from evo-hq/evo, the repository it ships in. Its siblings there include Discover, Evo Report and Evo Subagent Protocol. Each one is a separate skill with its own page in this directory, installs the same way Optimize does, and is maintained by evo-hq in that same repository. The rest of the collection is listed on the evo-hq/evo page.

  • How does Optimize compare to other AI Engineering skills?

    Optimize ranks #1071 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 Optimize against them. Open each page to compare what they document and how they install.

More from evo-hq/evo

Optimize is one of 8 skills cataloged on DirSkills from evo-hq/evo.

See all 8 skills
🔍
2w ago

Discover

Discover initializes an evo workspace for the current repository by exploring the codebase, proposing optimization dimensions, constructing a benchmark, and running a baseline experiment. Use it when starting a new evo run or instrumenting a project for autonomous optimization.
AI Engineering
1.4K105
📊
2w ago

Evo Report

Evo Report provides read-only reports from recorded evo workspace state, including score charts, frontier candidates, and status summaries. Use it when someone asks what happened overnight, what improved, or wants a quick chart without opening the dashboard.
Data
1.4K105
🤖
2w ago

Evo Subagent Protocol

Evo Subagent Protocol defines the brief shape and execution loop that evo optimization subagents follow when dispatched from /optimize. Orchestrators use it to write valid briefs and debug subagent behavior; subagents use it to drive required verifier checks and read-edit-run iteration.
AI Engineering
1.4K105
🎯
2w ago

Finetuning

Finetuning selects or diagnoses a training move—SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF—based on reward shape and literature, then gates runs with smoke tests, early stopping, and diagnostics. Use it when fine-tuning, post-training, reward design, or weight updates come up.
AI Engineering
1.4K105
⚙️
2w ago

Infra Setup

Infra Setup guides switching the evo backend between local worktrees, pool slots, and remote providers like Modal, E2B, or SSH. It checks prerequisites, verifies auth, and shows the exact config commands so experiments run on the intended infrastructure.
DevOps
1.4K105
🧬
2w ago

Optimize

Optimize runs the evo optimization loop with parallel subagents until interrupted or the stall limit is reached. Use it after a baseline experiment is committed to evolve code changes against benchmarks and prune dead branches.
AI Engineering
1.4K105