working-memory

Maintain timestamped context notes in a working-memory markdown file.

Updated Jan 20, 2026
One-click install
npx skills add https://github.com/vogon101/KnowledgeWork --skill working-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: working-memory
Source: https://github.com/vogon101/KnowledgeWork/tree/main/skills/working-memory
Command: npx skills add https://github.com/vogon101/KnowledgeWork --skill working-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a private scratchpad to maintain context across sessions, reducing the need to repeat information and helping maintain continuity.

Core Features & Use Cases

  • Persistent context between sessions for AI agents
  • Capture blockers, decisions, deadlines, and observations
  • Quick read-back at session start and before important tasks

Quick Start

Append a new note to the context by editing the file .claude/context/working-memory.md and adding a timestamped entry in the format [YYYY-MM-DD] [Project] Note content here. The agent auto-loads this file on startup.

Frequently Asked Questions about working-memory

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

FAQPage Schema
How do I maintain context across AI agent sessions?

To maintain context across sessions, append a timestamped entry to the .claude/context/working-memory.md file using the format [YYYY-MM-DD] [Project] Note content. The agent automatically loads this file on startup to restore previous context.

What is the best way to record blockers and decisions for AI reference?

Recording blockers and decisions is best handled by appending timestamped notes to a persistent markdown context file. This allows quick read-back at session start and before important tasks for immediate reference.

How do I resume a previous session without losing context?

Session resumes are supported by automatically loading a persistent context file on startup. This file contains previously recorded end-of-day summaries, blockers, and observations so the agent picks up exactly where you left off.

Do I need any dependencies to use a scratchpad for session memory?

No dependencies are required to use this scratchpad for session memory. The context loading mechanism operates entirely through a local markdown file, requiring no external libraries or components to function.

When should I use a persistent context file instead of repeating information?

You should use a persistent context file when you need to capture end-of-day summaries, record important blockers, or log decisions for future sessions. It eliminates redundant repetition by auto-loading previous notes on startup.

How does working memory handle structured daily entries?

Working memory handles structured daily entries by appending timestamped notes to a markdown file. Each entry follows the format [YYYY-MM-DD] [Project] Note content, creating an organized chronological log of session context.