headroom

Community

Shrink LLM context without losing signal.

Authorbobvarkey
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill reduces oversized LLM context by compressing redundant tool output, JSON, code, and text while preserving the information needed to keep working accurately.

Core Features & Use Cases

  • Content Routing: Detects the input type and selects an appropriate compression strategy automatically.
  • Structured Compression: Compresses JSON, code, and long text with specialized methods such as SmartCrusher, CodeCompressor, and LLMLingua-2.
  • Proxy Workflow: Runs as a proxy so existing OpenClaw and OpenAI-compatible setups can benefit from compression without changing application logic.

Quick Start

Use the headroom skill to compress the latest tool output before sending it back into the LLM context.

Dependency Matrix

Required Modules

python3

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: headroom
Download link: https://github.com/bobvarkey/openclaw-workspace/archive/main.zip#headroom

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 537,000+ vetted skills library on demand.