✂️
AI EngineeringGo

Caveman Learn

by JuliusBrussee

Caveman Learn is an AI Engineering skill for Claude Code, published by JuliusBrussee in caveman.

97.8K stars5.6K forkson JuliusBrussee/cavemanAdded 2026/08/13Repository updated 2026/08/13
aianthropiccavemanclaudeclaude-codellmmemeprompt-engineeringskilltokens
Install in seconds
Install Caveman Learn
Copy Caveman Learn 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-learn ~/.claude/skills/caveman-learn

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-learn/SKILL.md in JuliusBrussee/caveman
Installs to
~/.claude/skills/caveman-learn
Collection
One of 20 skills cataloged from this repository
Category
AI Engineering2451 skills

What Caveman Learn does

Caveman Learn reviews ranked token sinks from a caveman learn report and applies cost-lowering fixes such as trimming heavy CLAUDE.md files or offloading recurring context to cavemem, with per-edit consent. Use it after running 'caveman learn' or when asked to lower an agent's token cost, trim a heavy CLAUDE.md, or offload context that is re-pasted every session.

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

Documentation

README

You are the Caveman Learn editing skill. The "caveman learn" command MEASURES where an agent's tokens go; you are the consent-gated half that turns its findings into edits — with the user approving each one. You never claim a saving you have not measured, and you never make the agent dumber.

Read the plan first:

  1. Run: caveman learn report --json Parse the caveman.learn.v1 JSON. Show the Cave Score, its four components, and the ranked token sinks. For each sink state its class and basis. Behavioral sinks are observations — present their numbers as fact and their suggestion softly. Do not turn a behavioral finding into an imperative.

Then, only for the sinks the user chooses to act on, run the consent loop by class.

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

Frequently asked about Caveman Learn

  • What else does JuliusBrussee publish alongside Caveman Learn?

    Caveman Learn 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 Learn 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 Learn compare to other AI Engineering skills?

    Caveman Learn ranks #36 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 Caveman Learn against them. Open each page to compare what they document and how they install.

More from JuliusBrussee/caveman

Caveman Learn is one of 20 skills cataloged on DirSkills from JuliusBrussee/caveman.

See all 20 skills
🗜️
3w ago

Cavecrew

Cavecrew provides a decision guide for when to spawn caveman-style subagents — investigator, builder, reviewer — to locate code, make small edits, or review diffs, returning compressed output that saves main context. Use it when delegating tasks in Claude Code to reduce token usage.
AI Engineering
97.8K5.6K
🗿
3w ago

Caveman

Caveman compresses AI output into terse, technically accurate caveman-style responses, cutting token usage by 65% while preserving meaning. Use when the user requests caveman mode, brevity, or token efficiency.
AI Engineering
97.8K5.6K
✍️
3w ago

Caveman Commit

Caveman Commit generates concise Conventional Commits messages that cut noise while preserving intent and reasoning. Use it when asked to write a commit message or when staging changes.
AI Engineering
97.8K5.6K
🗜️
3w ago

Caveman Compress

Caveman Compress compresses natural language memory files (CLAUDE.md, todos, preferences) into caveman-speak to save input tokens, preserving code, URLs, paths, and structure. It backs up the original and overwrites the file.
Automation
97.8K5.6K
🏷️
3w ago

Caveman Discover

Caveman Discover finds every LLM workflow in the current repository and labels it so Caveman Cloud groups spend by what the code actually does. Use when the user asks to discover workflows or break LLM spend down by workflow.
AI Engineering
97.8K5.6K
📊
3w ago

Caveman Evidence Review

Caveman Evidence Review reads Caveman Cloud data read-only, covering costs, Cave Score, Cave Plan, workflows, traces, latency, errors, compression, routing, and verified savings. Use it when you need to know where LLM spend goes, why cost or quality changed, or which workflows need attention.
Data
97.8K5.6K