claude-md

name	claude-md
description	Create and optimize CLAUDE.md memory files or .claude/rules/ modular rules for Claude Code projects. Covers file hierarchy, content structure, path-scoped rules, best practices, and anti-patterns. Use when working with CLAUDE.md files, .claude/rules directories, setting up new projects, or improving Claude Code's context awareness — even when the user just says "memory file" or mentions Claude instructions without naming the filename.
when_to_use	When the user wants to create, clean up, or update Claude Code memory files. Routes via `$ARGUMENTS` — `init` (scaffold minimal CLAUDE.md), `optimize` (deep cleanup of bloat), `revise` (capture session learnings). Keywords — CLAUDE.md, memory file, instructions file, .claude/rules, optimize CLAUDE, init CLAUDE, revise CLAUDE, auto memory, MEMORY.md, subagent memory. Without a subcommand, treat the argument as free-form guidance about memory files. Skip for subagent system prompts and .claude/agents/ configs — use /agent-creator.
argument-hint	["init | optimize | revise | task description"]
license	MIT
compatibility	Optimized for Claude Code; degrades gracefully on any agent implementing the Agent Skills standard.
metadata	{"author":"coroboros","sources":["code.claude.com/docs/en/memory","github.com/anthropics/claude-plugins-official/tree/main/plugins/claude-md-management","github.com/Melvynx/aiblueprint"]}

CLAUDE.md

Important — Writing rules

These rules govern every prose artifact this skill emits — READMEs, CHANGELOGs, commit messages, PR bodies, release notes, doc paragraphs, non-trivial comments. Apply them at draft time, verify before output.

• Match the surrounding style — punctuation, capitalization, backtick conventions, em-dash vs parens, bullet style.
• Every sentence changes the reader's understanding. Cut it otherwise.
• Front-load the verb — "Creates", not "This helps you create".
• Concrete over abstract. Lists for ≥3 enumerable items.
• Assert positively. Reserve negation for real constraints (NEVER commit secrets).
• No marketing words: powerful, robust, seamlessly, leverage, unlock, comprehensive, delightful.
• No AI tells: delve, tapestry, intricate, pivotal, testament, underscore, crucial, garner, showcase, additionally, moreover, furthermore, indeed.
• After drafting English prose, invoke /humanize-en if installed.

Core Principle

Memory files consume tokens every session. Keep them minimal — include only what the agent cannot discover on its own or what a tool doesn't already enforce (linter, TypeScript, tests).

Three mechanisms carry knowledge across sessions:

• CLAUDE.md — single-file instructions you write. Always loaded.
• .claude/rules/ — modular rule files, optionally path-scoped. Load alongside CLAUDE.md.
• Auto memory — notes Claude writes itself per project. See Auto Memory below.

For most projects, CLAUDE.md and rules combine (hybrid pattern). See Workflow > Storage Strategy for the pick-which decision.

Quick Start

Run /init to auto-generate a CLAUDE.md. Or create manually:

# Project Name

## Tech Stack
- [Primary framework]
- [Key non-obvious libraries]

## Commands
- `npm run dev` - Dev server
- `npm test` - Run tests
- `npm run build` - Build

## Rules
- [2-3 critical project-specific rules]