skills.rest
SimonZimmer
SimonZimmerCOMMUNITY
Explore all skills by this author →
GitHub

caveman

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

Updated Jun 16, 2022
Search Tags:#token efficiency#token compression#classical chinese#response style#caveman mode#prompt instructions
One-click install
npx skills add https://github.com/SimonZimmer/dotfiles --skill caveman-simonzimmer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/SimonZimmer/dotfiles/tree/main/.config/opencode/skills/caveman
Command: npx skills add https://github.com/SimonZimmer/dotfiles --skill caveman-simonzimmer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy AI responses waste tokens and slow down reading. This Skill compresses every model response by roughly 65-75% by dropping articles, filler, pleasantries, and hedging, while keeping code, error strings, and technical terms exact. ## Core Features & Use Cases - Six intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, and wenyan-ultra, ranging from light trimming to extreme classical Chinese compression. - Session persistence: the mode stays active across all turns until explicitly stopped with "stop caveman" or "normal mode". - Auto-clarity rule: automatically reverts to normal prose for security warnings, irreversible-action confirmations, and ambiguous multi-step sequences, then resumes compression. - Use Case: During a long debugging session, enable full mode so every explanation arrives as terse fragments like "Bug in auth middleware. Token expiry check use < not <=", cutting token costs without losing precision. ## Quick Start Ask the AI to enable caveman mode by saying "use caveman mode" or invoking /caveman before your next question.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I reduce token usage in AI chat responses?▼

Enable caveman mode by saying "caveman mode" or invoking /caveman. It drops articles, filler, and hedging from every response, cutting output tokens by roughly 65-75% while keeping code and error strings exact.

How do I change the compression level in caveman mode?▼

Invoke /caveman with a level argument: lite, full, ultra, wenyan-lite, wenyan-full, or wenyan-ultra. Full is the default; the chosen level persists for the whole session until changed.

Does caveman mode work with languages other than English?▼

Yes, it preserves the user's dominant language, compressing style rather than translating. It also offers wenyan levels that produce classical Chinese output with up to 80-90% character reduction.

When does caveman mode stop compressing responses?▼

It automatically drops to normal prose for security warnings, irreversible-action confirmations, ambiguous multi-step sequences, and repeated questions. It resumes compression afterward and fully stops only on "stop caveman" or "normal mode".

Does caveman mode change code blocks or error messages?▼

No. Code blocks, function names, API names, CLI commands, and exact error strings are always kept verbatim. Only prose is compressed; technical content stays exact at every intensity level.

Related Skills

Explore More Software Engineering Skills→
whichguywhichguy
2

optimize-system-prompt

Optimize and refine Sheets Chat ClaudeConversation system prompts for GAS-based workflows.

Community
Advanced
parcadeiparcadei
3.9k

tldr-stats

Generate a statistical dashboard of Claude API token usage, costs, and TLDR savings.

Community
Basic
Haohao-endHaohao-end
779

caveman

Compress responses to retain conclusions, constraints, next steps, and file references.

Community
Basic
roanbrasilroanbrasil
5

llm-cost-optimization

Implement model tier routing and prompt caching to reduce LLM API costs.

Community
Advanced