memory-maintenance

Distill daily conversations and update today.md, workspace.md, and human.md state files.

120|6|Updated Jan 29, 2026

Search Tags:#automation #memory #journal #distillation #state-files #self-maintenance

Ready to run

npx skills add https://github.com/ascorbic/macrodata --skill memory-maintenance

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-maintenance
Source: https://github.com/ascorbic/macrodata/tree/main/plugins/macrodata/skills/memory-maintenance
Command: npx skills add https://github.com/ascorbic/macrodata --skill memory-maintenance

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill automates the end-of-day hygiene of your working memory by distilling today's conversations, pruning stale data, and updating core state files so you start the next day with a clean, actionable base.

Core Features & Use Cases

End-of-day distillation: Consolidates scattered learnings into the working memory.
State maintenance: Updates today.md, workspace.md, and human.md to reflect new insights.
Noise reduction: Prunes stale or completed items to keep memory lean and actionable.
Use Case: At the end of each day, run memory-maintenance to ensure the agent starts the next session with accurate context and prioritized tasks.

Quick Start

Run the memory-maintenance workflow at the end of the day to distill today's conversations and refresh state files.

Frequently Asked Questions about memory-maintenance

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

FAQPage Schema

How do I automate end-of-day memory maintenance to distill conversations?▼

Automated end-of-day memory maintenance distills daily conversations and updates core state files. It consolidates scattered learnings, prunes stale data, and ensures the agent starts the next session with accurate context and prioritized tasks.

What is the best way to update state files like today.md and workspace.md?▼

Updating state files like today.md and workspace.md is handled automatically by distilling daily conversations into identity, journal, topics, and workspace contexts. This safely refreshes the files to reflect new insights without manual interaction.

How does memory distillation reduce noise in journal and workspace state files?▼

Memory distillation reduces noise by pruning stale or completed items from state files. This keeps working memory lean and actionable, consolidating only fresh insights into today.md, workspace.md, and human.md.

Does automated memory upkeep require manual interaction or dependencies?▼

Automated memory upkeep requires no user interaction and operates with zero dependencies. It safely runs within the existing memory model to update state files automatically at the end of the day.

When should I run an automated memory maintenance workflow?▼

Run memory maintenance at the end of each day. This ensures the agent starts the next session with a clean base, accurate context, and prioritized tasks by distilling today's conversations.