claude-memory

Build and optimize CLAUDE.md memory structures for Claude Code projects.

223|68|Updated Aug 18, 2025
One-click install
npx skills add https://github.com/Melvynx/aiblueprint --skill claude-memory-melvynx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: claude-memory
Source: https://github.com/Melvynx/aiblueprint/tree/main/claude-code-config/skills/meta-claude-memory
Command: npx skills add https://github.com/Melvynx/aiblueprint --skill claude-memory-melvynx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

CLAUDE memory systems are essential for maintaining context across Claude Code sessions. This skill provides a structured approach to creating and optimizing CLAUDE.md memory files or the modular .claude/rules/ directories, enabling consistent guidance, faster onboarding, and improved context awareness for projects of all sizes.

Core Features & Use Cases

  • Guidance on building single-file CLAUDE.md memories (CLAUDE.md) for small projects.
  • Guidance on modular memory rules using the .claude/rules/ directory for larger projects.
  • Best practices for file hierarchy, content structure, path-scoped rules, formatting, emphasis techniques, and anti-patterns to avoid.
  • Use Case: Onboard a new Claude Code project by generating a clear memory blueprint, then iteratively refine rules as the project evolves.

Quick Start

Start by running /init in Claude Code to auto-generate a CLAUDE.md with project memory, or create manually at project root:

  • Place a CLAUDE.md with sections (What/Why/How) and commands, then add a minimal .claude/rules/ directory for modular needs as projects grow.

Frequently Asked Questions about claude-memory

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

FAQPage Schema
How do I set up a CLAUDE.md memory file for a new Claude Code project?

A modular memory structure uses the `.claude/rules/` directory to store path-scoped rules for larger projects. This approach guides file hierarchy, content structure, and retrieval behavior, preventing context fragmentation as the codebase grows.

When should I use modular .claude/rules instead of a single CLAUDE.md file?

No, this memory optimization approach is framework-agnostic and applies to any Claude Code project regardless of the underlying tech stack. It focuses strictly on structuring CLAUDE.md files and .claude/rules directories to maintain context across sessions.

Why does my Claude Code context break down in large projects with a single memory file?

After generating a CLAUDE.md memory blueprint, the next step is iterative refinement. You update the `.claude/rules/` directory and path-scoped rules as the project evolves, maintaining structured guidance and consistent context loading across new sessions.

What is the best way to organize .claude/rules for path-scoped memory?

To maintain Claude Code memory, you should continuously refine the `.claude/rules/` directory and CLAUDE.md sections as the project evolves. This iterative process updates path-scoped rules and context structure, ensuring consistent guidance and preventing anti-patterns.