Auto Memory Design — Design skill for Claude Code
Explore an agent and design a tailored memory system.
How to install Auto Memory Design
Installs to ~/.claude/skills/hkuds-automemory-auto-memory-design/SKILL.md
mkdir -p ~/.claude/skills/hkuds-automemory-auto-memory-design && curl -fsSL https://raw.githubusercontent.com/HKUDS/AutoMemory/HEAD/commands/auto-memory-design.md -o ~/.claude/skills/hkuds-automemory-auto-memory-design/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Auto Memory Design does
name: auto-memory-design description: Explore an agent and design a tailored memory system argument-hint: agent-repo-path [user-requirements] alwaysApply: true
auto-memory-design
**Target agent repository**: $ARGUMENTS
note.md — Your Working Memory
**First thing you do**: create `/_memory/worktraces/note.md` (template at `@Auto_Memory/scaffolds/note-template.md`)
This file is your own persistent working memory across the entire pipeline. Write into it an
Alternatives in Design
- Brand Guidelines — Apply Anthropic's official brand colors and typography to artifacts 94.1k ★
- Od Contribute — Open a first-contribution PR (or bug issue) on nexu-io/open-design — works for non-coders too 91.8k ★
- Export Diagram — Export a diagram-design HTML file to .svg and .png next to the source 27.2k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Auto Memory Implement
Implement a memory system from an existing design document
Auto Memory
End-to-end memory system creation — design, implement, and refine
Memory Auto Split
Content-preserving fallback split for an over-ceiling topic file that has no other applicable reduction path —
Code Apex
CodeApex — a Claude Code-style coding agent CLI in your terminal: planning, subagent delegation, HITL approval
Design Review Workflow
by Patrick Ellis - A tailored workflow for enabling automated UI/UX design review, including specialized sub a
Fireworks Design
Generate a world-class frontend page via fireworks-design (explore → judge → synthesize → refine → polish)
Related Agents
Part 11: Auto-Capture Hook (Stop Manually Writing Memory)
By Terp - Terp AI Labs --- The vault system from Part 9 is powerful, but there's a gap: you have to manually w
Supervisor Agent
You are the supervisor agent for Correctless Auto Mode. You receive structured messages and return structured
Git Pull
Safely pull updates (fork/upstream aware), stash-first, resolve conflicts via memory-bank context, no auto-sta