deflate

Name: deflate
Availability: InStock
Author: wjlmrzd

Compress OpenClaw conversations with Cornell-MapReduce while preserving IDs, dates, and amounts.

Updated Aug 27, 2026

Search Tags:#memory-management #token-cost #topic-tracking #openclaw #context-compression #deflate

Ready to run

npx skills add https://github.com/wjlmrzd/OpenClaw-Wren --skill deflate

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deflate
Source: https://github.com/wjlmrzd/OpenClaw-Wren/tree/main/skills/deflate
Command: npx skills add https://github.com/wjlmrzd/OpenClaw-Wren --skill deflate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

OpenClaw conversations often grow without bound, driving token costs and slowing responses. Deflate provides a structured, lossless compression approach that preserves critical data while reducing overall context length.

Core Features & Use Cases

Tracks topics across a session and marks when topics are completed.
Recommends /new over /compact when memory holds essential data, saving tokens and cost.
Applies Cornell-MapReduce to compress each topic independently while preserving IDs, dates, and amounts for auditability.
Use Case: In a long support chat, compress completed topics into memory and continue with active topics without losing key identifiers.

Quick Start

Run the Deflate skill to compress your current conversation while preserving critical data.

Frequently Asked Questions about deflate

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

FAQPage Schema

How do I compress OpenClaw conversation context to reduce token cost?▼

To compress OpenClaw conversation context and reduce token cost, the Deflate skill applies the Cornell-MapReduce method to compress topics independently while preserving critical identifiers, dates, and amounts for auditability.

Does context compression preserve IDs and dates for auditability?▼

Yes, context compression preserves IDs, dates, and amounts for auditability. The lossless data preservation approach ensures critical identifiers are retained when compressing each topic independently during a session.

When should I use /new instead of /compact for session transitions?▼

You should use /new instead of /compact when memory holds essential data that cannot be lost. The skill recommends /new to save tokens and cost while ensuring safe session transitions via MEMORY.md flush workflows.

What is the best way to manage multi-topic sessions without losing key data?▼

The best way to manage multi-topic sessions without losing key data is tracking topics across the session, marking completed topics, and compressing them independently to preserve critical identifiers while reducing overall context length.

Can I report compression quality after compressing a conversation?▼

Yes, you can report compression quality after compressing a conversation. The skill enforces lossless data preservation and reports compression quality to verify that critical data is retained while reducing token cost.