What is the primary purpose of the Memory Rotate skill?

It automatically summarizes and indexes old session memory files when they are rotated, keeping your workspace clean while preserving important historical data.

How does the skill know when to start summarizing?

The skill listens for a specific [MEMORY_KEEPER_ROTATE] trigger message, which is typically generated by a memory-management hook when a file reaches its limit.

Where are the generated summaries stored?

Summaries are saved as .summary.json files within the .claude/memory/ directory for easy programmatic access.

Which model does this skill use for summarization?

It utilizes the Claude 3 Haiku model to provide fast, efficient, and cost-effective summaries of your memory files.

What happens if a summarization task fails?

If a task fails, the skill logs the error and maintains the 'summaryGenerated: false' status in your index; a retry will automatically fire at the start of your next session.

Memory Rotate & Summarize

Name: Memory Rotate & Summarize
Author: ZipperBagCoffee

byZipperBagCoffee

0•

生産性とワークフロー

Automates the summarization and archival of AI session memory files to maintain clean and efficient context windows.

Memory Rotate is a specialized Claude Code skill designed to optimize the way AI agents handle long-term project context. When a memory file is rotated out of the active context, this skill automatically invokes a lightweight Haiku subagent to generate a concise summary of the archived session. By converting raw logs into structured JSON summaries and updating a centralized index, it ensures that critical project history remains searchable and retrievable without consuming unnecessary token space in future sessions.

主な機能

01Centralized indexing for easy context retrieval

02Lightweight Haiku-powered session summarization

03Automated failure recovery and retry logic

04Automatic trigger-based memory log processing

05Structured JSON archival for machine-readable history

060 GitHub stars

ユースケース

01Archiving project milestones and technical decisions for future reference

02Managing long-running development sessions without losing key historical context

03Optimizing token usage by summarizing historical logs instead of loading full transcripts

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add zipperbagcoffee/memory-keeper-plugin memory-rotate

For use in Claude.ai and ChatGPT

主な機能

01Centralized indexing for easy context retrieval

02Lightweight Haiku-powered session summarization

03Automated failure recovery and retry logic

04Automatic trigger-based memory log processing

05Structured JSON archival for machine-readable history

060 GitHub stars

ユースケース

01Archiving project milestones and technical decisions for future reference

02Managing long-running development sessions without losing key historical context

03Optimizing token usage by summarizing historical logs instead of loading full transcripts

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add zipperbagcoffee/memory-keeper-plugin memory-rotate

For use in Claude.ai and ChatGPT