AugmentClaude

CLAUDE.md Optimizer

Optimize your CLAUDE.md file for clarity, efficiency, and maintainability.

Installation

  1. Make sure Claude is on your device and in your terminal.

    Skills load from ~/.claude/skills/ when Claude Code starts up — so you need it on your machine first. If you don't have it yet, install it once with the command below, then run claude in any terminal to verify.

    One-time setup
    npm i -g @anthropic-ai/claude-code

    Already have it? Skip ahead.

  2. Paste into Claude Code or into your terminal.

    This copies the whole skill folder into ~/.claude/skills/claude-md-progressive-disclosurer-daymade/ — the SKILL.md plus any scripts, reference docs, or templates the skill ships with. Safe default: works for every skill.

    Faster alternative (instruction-only skills)

    Skips the clone and grabs only the SKILL.md file. Don't use this if the skill ships Python scripts, reference markdowns, or asset templates — they won't be downloaded and the skill will fail when it tries to load them.

    Quick install (SKILL.md only)
    Sign up to copy
  3. Restart Claude Code.

    Quit and reopen Claude Code (or any other agent that loads from ~/.claude/skills/). New skills are picked up on startup.

  4. Just ask Claude.

    Skills auto-activate when your request matches the skill's description — no slash command needed. Trigger phrases live in the skill's own frontmatter; you can read them in the “What this skill does” section above.

Prefer to read the source first? Open on GitHub.

When Claude uses it

Optimize CLAUDE.md files using progressive disclosure. Goal: Maximize information efficiency, readability, and maintainability. Use when: User wants to optimize CLAUDE.md, information is duplicated across files, or LLM repeatedly fails to follow rules.

What this skill does

This skill optimizes your CLAUDE.md file using progressive disclosure architecture to maximize information efficiency, readability, and maintainability.

What it does

  • Organizes content into two levels: Level 1 (CLAUDE.md, loaded every conversation) holds core commands, rules, code patterns, and diagnostic flows; Level 2 (docs/references/) holds detailed SOPs, edge cases, and historical records—loaded only when triggered.
  • Creates multiple entry points to the same resources, serving different user workflows: a Reference Index at the start (for troubleshooting), a "Before Modifying Code" table in the middle, and a Reference Trigger Index at the end (for long conversations).
  • Establishes rules against information loss: content must move intact to Level 2, never compressed during the move; every deletion requires explicit canonical source documentation.
  • Eliminates redundancy without fragmentation: the same information never lives in multiple places, but single resources can have multiple entry points—like a book's table of contents, index, and quick reference card.
  • Prevents future bloat by adding an "Information Recording Principles" section that teaches Claude itself where new information belongs (Level 1 vs Level 2).
  • Validates completeness with backup, content classification, reference file creation, and three-phase verification: file existence, content integrity, and prohibition of line-count metrics.

How to use it

Pass your CLAUDE.md file and describe your optimization goal (or just request a full progressive-disclosure refactor). The skill backs up your original, classifies each section by frequency and consequence, moves low-frequency content to Level 2 reference files while preserving complete information, creates trigger-condition tables at the start and end, and verifies that no information was lost—only repositioned.

Note: this skill's internal instructions are written in Chinese. Claude reads them natively and will work with you in English.

Related skills