skills.rest
patrickserrano
patrickserranoCOMMUNITY
Explore all skills by this author →
Website𝕏@patrickgserranoGitHub

caveman

Compresses AI responses into terse caveman-style output with multiple intensity levels.

3|Updated Jun 15, 2026
Search Tags:#token efficiency#compression#brevity#wenyan#caveman mode#terse responses#prompt style
One-click install
npx skills add https://github.com/patrickserrano/lacquer --skill caveman-patrickserrano
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman
Source: https://github.com/patrickserrano/lacquer/tree/main/core/skills/caveman
Command: npx skills add https://github.com/patrickserrano/lacquer --skill caveman-patrickserrano

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Long, filler-heavy AI responses waste tokens and slow down reading when you only need the technical substance. This Skill switches responses into an ultra-compressed terse style that cuts roughly 75% of tokens while preserving full technical accuracy. ## Core Features & Use Cases - Terse Response Mode: Drops articles, filler words, pleasantries, and hedging while keeping technical terms, code blocks, and error messages exact. - Six Intensity Levels: Choose from lite, full, ultra, and three classical Chinese (wenyan) variants via /caveman commands, with the level persisting across the session. - Auto-Clarity Safety: Automatically reverts to normal prose for security warnings, irreversible action confirmations, and multi-step sequences, then resumes terse mode. - Use Case: During a long debugging session, invoke /caveman ultra so every diagnosis arrives as a compact fragment like "Inline obj prop → new ref → re-render. useMemo." instead of a paragraph. ## Quick Start Ask the AI to switch to caveman mode by saying "use caveman" or invoking /caveman full before your next technical question.

Frequently Asked Questions about caveman

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

FAQPage Schema
How do I make AI responses shorter and use fewer tokens?▼

Activate caveman mode by saying "caveman mode", "be brief", or invoking /caveman. The Skill strips articles, filler, and pleasantries, achieving roughly 75% token reduction while keeping technical content exact.

What intensity levels does caveman mode support?▼

Six levels: lite, full, ultra, wenyan-lite, wenyan-full, and wenyan-ultra. Switch with /caveman followed by the level name. Lite keeps full sentences; ultra uses abbreviations and arrows; wenyan levels use classical Chinese terseness.

Does terse mode affect code blocks and error messages?▼

No. Code blocks, commits, and PR text remain unchanged and written normally, and errors are quoted exactly. Only the surrounding explanatory prose is compressed.

When does caveman mode turn off automatically?▼

It temporarily drops terse style for security warnings, irreversible action confirmations, and multi-step sequences where fragments risk misreading, then resumes afterward. It fully reverts only on "stop caveman" or "normal mode".

Does caveman mode persist across a conversation?▼

Yes. Once activated it stays active every response for the whole session, with no filler drift. The chosen level persists until changed or the session ends.

Related Skills

Explore More Personal & Entrepreneur Skills→
Base-AnaliticaBase-Analitica

ponytail-help

Displays a quick-reference card of ponytail modes, skills, and commands.

Official
Basic
grojedagrojeda
25

caveman

Reduce token consumption by generating terse, technically accurate responses.

Community
Basic
karuhun-developerkaruhun-developer

caveman-review

Generates terse one-line code review comments for pull request diffs.

Official
Basic
AlphaLab-USTCAlphaLab-USTC
131

customize-system-prompt

Customize OhMyCode system prompts via OHMYCODE.md, CLAUDE.md, and system_prompt.py.

Community
Intermediate