load-memory

Restores session context by reading MEMORY.md and CLAUDE.md from the repository root.

Updated Dec 18, 2025
One-click install
npx skills add https://github.com/l0lxl0lw/dotfiles --skill load-memory-l0lxl0lw
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: load-memory
Source: https://github.com/l0lxl0lw/dotfiles/tree/main/ai/shared/skills/utilities/load-memory
Command: npx skills add https://github.com/l0lxl0lw/dotfiles --skill load-memory-l0lxl0lw

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Starting a new AI session often means losing all context from previous work, forcing you to re-explain project state, decisions, and next steps. This Skill reloads your saved working memory so you can pick up exactly where you left off. ## Core Features & Use Cases - Context Restoration: Reads MEMORY.md and CLAUDE.md from the repository root to recover prior session state and project conventions. - Concise Summarization: Presents a short structured summary covering last session, current state, key context, and next steps instead of dumping raw file contents. - Read-Only Operation: Never modifies any files, making it safe to run at the start of any session. - Use Case: You return to a project after a week away. Run this Skill to instantly see what was in progress, what is blocked, and what was planned next, then continue working without re-briefing the AI. ## Quick Start Ask the AI to load memory and restore context from the previous session for this repository.

Frequently Asked Questions about load-memory

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

FAQPage Schema
How do I restore context from a previous AI session?

Run the load-memory Skill at the start of a new session. It locates the repository root with git rev-parse, reads MEMORY.md and CLAUDE.md in parallel, and presents a concise summary of prior state and next steps.

What files does load-memory read to restore context?

It reads MEMORY.md, which contains saved session memory from a previous /save-memory run, and CLAUDE.md, which holds project instructions and conventions. Both are read from the repository root.

What happens if MEMORY.md does not exist in my repository?

The Skill informs you that no saved memory exists for the project and suggests using /save-memory to create one. It does not fail or create any files on its own.

Does load-memory modify any files in my project?

No, the Skill is strictly read-only. It only reads MEMORY.md and CLAUDE.md and presents a summary, never writing to or altering any files.

Can I use load-memory outside a Git repository?

No, it relies on git rev-parse --show-toplevel to locate the repository root, so it requires the working directory to be inside a Git repository.