caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1.00x

Quality

95%

Does it follow best practices?

Impact

96%

1.00x

Average score across 38 eval scenarios

Securityby

Passed

No findings from the security scan

The canonical home for this skill is caveman in JuliusBrussee/caveman

Preview

This is a new way to view eval results. We're still working on it, so the layout may change.

Run	Type	Date	Status
baseline vs usage-spec With / without context 6 months ago Completed	With / without context	6 months ago	Completed

Eval run

019d7e00-3844-73fb-aa3e-bef9aca06870

Run 6 months ago

Stats are not available yet

The run is available. Its result stats will appear here when they are ready.

Repository: anthonystepvoy/caveman-opencode
Path: .opencode/skills/caveman/SKILL.md
Commit: d3f5b6e

Evaluated: 6 months ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Developer Q&A Session in Compact Mode Architecture Decision Records in Maximum Compression Mode Database Maintenance Session with Mixed Criticality

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.