Caveman Optimize

by JuliusBrussee

Caveman Optimize is a Quality skill for Claude Code, published by JuliusBrussee in caveman.

97.8K stars5.6K forkson JuliusBrussee/cavemanAdded 2026/08/13Repository updated 2026/08/13

View source on GitHub Download repo ZIP

aianthropiccavemanclaudeclaude-codellmmemeprompt-engineeringskilltokens

Install in seconds

Install Caveman Optimize

Copy Caveman 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/JuliusBrussee/caveman/tree/main/skills/caveman-optimize ~/.claude/skills/caveman-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/JuliusBrussee/caveman.git

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

In this catalog

Source file: skills/caveman-optimize/SKILL.md in JuliusBrussee/caveman
Installs to: ~/.claude/skills/caveman-optimize
Collection: One of 20 skills cataloged from this repository
Category: Quality — 1354 skills

What Caveman Optimize does

Caveman Optimize turns Caveman's exact report-only repository observations into an operator-chosen optimization candidate with a paired baseline/candidate evaluation. Use when a Claude Code session needs to inspect an optimization observation, evaluate a candidate change, or act on the current Caveman optimization report.

Caveman Optimize is cataloged under Quality on DirSkills. Caveman Optimize comes from a repository tagged ai, anthropic, caveman, claude and claude-code.

Documentation

README

Excerpt

Evaluate an optimization observation

Use Caveman's report-only observations as diagnostic input. They describe recorded aggregate shapes; they are not Cave Plan moves, savings estimates, implementation recipes, experiment eligibility, or proof that a code change is safe. Keep the workflow operator-chosen and evidence-first.

1. Read the exact observations

Require a logged-in Caveman CLI session and run:

caveman opportunities list

Read only the report_only_observations array. Do not select from the lifecycle data array. Preserve each server-provided title and observation verbatim. Handle these exact repository-profile ids:

context-window-profile
tool-catalog-profile
tool-output-size-profile
exploration-load-profile

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

Frequently asked about Caveman Optimize

What else does JuliusBrussee publish alongside Caveman Optimize?
Caveman Optimize is one of 20 skills that DirSkills catalogs from JuliusBrussee/caveman, the repository it ships in. Its siblings there include Cavecrew, Caveman and Caveman Commit. Each one is a separate skill with its own page in this directory, installs the same way Caveman Optimize does, and is maintained by JuliusBrussee in that same repository. The rest of the collection is listed on the JuliusBrussee/caveman page.
How does Caveman Optimize compare to other Quality skills?
Caveman Optimize ranks #13 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. 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 Caveman Optimize against them. Open each page to compare what they document and how they install.