prompt-compressor

Community

Compress prompts to save tokens and speed up LLMs

Authorgeorgekhananaev
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Compress verbose prompts & context before processing. This skill reduces token usage and speeds up LLM interactions by trimming unnecessary language while preserving meaning.

Core Features & Use Cases

  • Prompt trimming: Remove filler phrases and hedging to focus on intent.
  • Token reduction: Achieve noticeable savings in token counts for long prompts.
  • Use Case: Paste a long instruction or transcript and obtain a concise prompt ready for the LLM.

Quick Start

Use the prompt-compressor skill to shrink a verbose user prompt before sending it to the LLM:

  1. Provide the prompt text to compress (or pipe from a file).
  2. Choose a compression level (light, medium, heavy).
  3. Review the compressed result and token savings.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 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: prompt-compressor
Download link: https://github.com/georgekhananaev/claude-skills-vault/archive/main.zip#prompt-compressor

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 223,000+ vetted skills library on demand.