ultrashort

Community

Cut AI output tokens by ~80% without losing accuracy.

Authorheldernoid
Version1.0.0
Installs0

System Documentation

What problem does it solve?

It reduces wasted output tokens caused by preambles, restatements, transitions, and trailing summaries, so you get the same technical content in far fewer words.

Core Features & Use Cases

  • Maximum compression: Strips filler and keeps full technical accuracy with a minimum-token style.
  • Intensity control: Supports tight, ultrashort (default), and micro modes to match the urgency and context.
  • Safety-aware behavior: Automatically drops compression when fragmenting could create ambiguity for warnings or irreversible actions.

Quick Start

Say: ultrashort when you want the AI to answer in the fewest tokens while preserving technical correctness.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: ultrashort
Download link: https://github.com/heldernoid/ultrashort/archive/main.zip#ultrashort

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.