skills.rest
lugassawan
lugassawanCOMMUNITY
Explore all skills by this author →
GitHub

principle-communication

Enforce caveman-style terse output at selectable compression levels.

2|8|Updated Apr 20, 2026
Search Tags:#code review#technical communication#token efficiency#concise writing#caveman mode#output style control#safety clarity
One-click install
npx skills add https://github.com/lugassawan/swe-workbench --skill principle-communication
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: principle-communication
Source: https://github.com/lugassawan/swe-workbench/tree/main/skills/principle-communication
Command: npx skills add https://github.com/lugassawan/swe-workbench --skill principle-communication

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of wasting tokens on filler and hedging by letting you switch to a consistent, ultra-terse communication style on demand.

Core Features & Use Cases

  • Caveman output modes (lite/full/ultra): Quickly reduces verbosity while keeping technical meaning intact.
  • Mode control with persistence: Keeps the selected level across turns until you explicitly stop it.
  • Safety/clarity carve-outs for destructive actions: Forces full prose for risky confirmations to avoid ambiguous ordering or missing steps.
  • Example use case: When iterating on code review feedback, use lite for professional brevity, switch to ultra when you want maximum compression.

Quick Start

Turn on caveman mode by telling the assistant to use caveman mode for brief replies.

Frequently Asked Questions about principle-communication

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

FAQPage Schema
How do I reduce token usage during AI code review feedback?▼

You can reduce token usage during code review feedback by enabling caveman mode, which enforces ultra-terse, compressed phrasing while preserving technical meaning. This strips conversational filler, accelerating iteration speed without altering code identifiers.

What is caveman mode for technical communication?▼

Caveman mode is an output style control mechanism that reduces conversational verbosity by enforcing ultra-terse formatting at a selectable compression level. It tightens phrasing for technical discussions to save tokens and improve iteration speed.

How do I make AI replies more concise without losing technical details?▼

You can make AI replies more concise without losing technical details by applying a lite, full, or ultra caveman compression level. This removes hedging and filler while strictly non-abbreviating identifiers inside code or inline spans.

Does terse output formatting work safely for destructive command execution?▼

Terse output formatting includes safety carve-outs for destructive command execution, forcing full prose for risky confirmations. This prevents ambiguous ordering or missing steps during destructive workflows, ensuring operational safety.

Can I lock AI communication to a specific brevity level across multiple turns?▼

You can lock AI communication to a specific brevity level across multiple turns using mode control with persistence. The system deterministically adheres to your chosen intensity ladder until you explicitly disable the caveman mode.

Related Skills

Explore More Content & Communication Skills→
borkwebborkweb
7

caveman

Compress AI-generated text responses to reduce token usage.

Community
Intermediate
ChimeraFoundationaChimeraFoundationa

claude-code

Delegate coding tasks to Claude Code via Hermes CLI with PTY for interactive sessions.

Community
Advanced
mattbutlerengineeringmattbutlerengineering
1

caveman

Compress technical communication by removing filler while preserving accuracy and code blocks exactly.

Community
Basic
doanchienthangdevdoanchienthangdev
4

optimizing-tokens

Reduce token usage in AI prompts to lower API costs.

Community
Intermediate