skills.rest
bittlinkm
bittlinkmCOMMUNITY
Explore all skills by this author →
GitHub

caveman

Compresses AI responses into terse caveman-style prose while preserving technical accuracy.

Updated Aug 20, 2026
Search Tags:#brevity#token compression#classical chinese#output optimization#response style#caveman mode#prompt behavior
One-click install
npx skills add https://github.com/bittlinkm/claude-setup --skill caveman-bittlinkm
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/bittlinkm/claude-setup/tree/main/skills/caveman
Command: npx skills add https://github.com/bittlinkm/claude-setup --skill caveman-bittlinkm

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy AI responses waste output tokens and slow down reading. This Skill strips articles, pleasantries, and hedging from every response while keeping code, error strings, and technical terms exact, reducing token usage without losing substance. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, plus three Classical Chinese (wenyan) variants for maximum character compression. - Auto-clarity rule: Automatically reverts to normal prose for security warnings, irreversible-action confirmations, and ambiguous multi-step sequences, then resumes compression. - Language preservation: Replies stay in the user's language; only the style is compressed, never the technical content. - Use Case: During a long debugging session, enable full mode so every explanation arrives as short fragments like "Bug in auth middleware. Token expiry check use < not <=" instead of multi-sentence paragraphs. ## Quick Start Ask the AI to enable caveman mode by saying "talk like caveman" or invoking /caveman, and optionally specify a level such as lite or ultra.

Frequently Asked Questions about caveman

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enable caveman mode for AI responses?▼

Invoke /caveman or say "talk like caveman" to activate full mode by default. Use /caveman lite or /caveman ultra to pick a different intensity, and say "stop caveman" or "normal mode" to revert.

How much does caveman mode reduce output tokens?▼

The Skill documentation reports roughly 65% output token reduction in full mode, measured by its authors. Actual savings depend on the model and workload, and no universal reduction guarantee is published.

Does caveman mode change code blocks or error messages?▼

No. Code blocks, API names, CLI commands, and exact error strings are always preserved verbatim. Only prose style is compressed; technical terms and negations like "not" or "never" are never dropped.

When does caveman mode automatically switch back to normal prose?▼

It drops to normal prose for security warnings, irreversible-action confirmations, ambiguous multi-step sequences, and when the user repeats a question. Compression resumes after the clarity-critical part is done.

Does caveman mode work in languages other than English?▼

Yes. It preserves the user's dominant language and compresses only the style. It also offers three wenyan levels that rewrite responses in Classical Chinese for extreme character-count reduction.

Related Skills

Explore More Software Engineering Skills→
MauricioDMOMauricioDMO

caveman

Compresses AI responses into terse fragments while preserving technical accuracy.

Community
Basic
jacobrocks1212jacobrocks1212

human-writing

Rewrite AI-like prose into natural, opinionated text using the Jacob style guide.

Community
Intermediate
brahiamsinhobrahiamsinho

caveman

Compress technical communication into a caveman-like style with adjustable intensity levels.

Community
Advanced
JNRCHAYANJNRCHAYAN

caveman

Compresses assistant responses into terse, technically accurate language.

Community
Intermediate