Skip to content
Back to skills

Memory

ASecurity

Two-layer memory system with grep-based recall.

  • 170 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 11, 2026
documentationapi

Works with

  • api

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add InternScience/DrClaw --skill memory --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Memory?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Memory
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/internscience-memory-19a0961d/badge)](https://www.skillsdirectory.com/skills/internscience-memory-19a0961d)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: memory
description: Two-layer memory system with grep-based recall.
always: true
i18n:
  zh:
    description: 用于memory相关任务。
---

# Memory

## Structure

- `MEMORY.md` — Long-term facts (preferences, project context, relationships). Always loaded into your context.
- `HISTORY.md` — Append-only event log. NOT loaded into context. Search it with grep. Each entry starts with [YYYY-MM-DD HH:MM].

## Search Past Events

Use the `exec` tool to run grep: `grep -i "keyword" HISTORY.md`
Combine patterns: `grep -iE "meeting|deadline" HISTORY.md`

## When to Update MEMORY.md

Write important facts immediately using `edit` or `write`:
- User preferences ("I prefer dark mode")
- Project context ("The API uses OAuth2")
- Key relationships ("Alice is the project lead")

## Auto-consolidation

Old conversations are automatically summarized and appended to HISTORY.md when the session grows large. Long-term facts are extracted to MEMORY.md. You don't need to manage this.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…