Claude Md Optimizer

Optimize oversized agent instruction files using progressive disclosure. Handles CLAUDE.md (Claude Code), AGENTS.md (OpenAI Codex / GitHub Copilot agents), and copilot-instructions.md (GitHub Copilot). Auto-detects all three formats in your repo, analyzes content tiers, creates sub-documents using each format's native mechanism, and rewrites the main file with zero information loss. Triggers: optimize CLAUDE.md, AGENTS.md too long, reduce copilot-instructions.md, agent instructions file too large, shrink context file, apply progressive disclosure, instructions file bloated

26 stars 7 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add wrsmith108/claude-md-optimizer --skill claude-md-optimizer

Manual install

git clone --depth 1 https://github.com/wrsmith108/claude-md-optimizer.git /tmp/claude-md-optimizer
mkdir -p ~/.claude/skills
cp -r /tmp/claude-md-optimizer/. ~/.claude/skills/claude-md-optimizer

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Agent Instructions Optimizer

**Behavioral Classification: Guided Decision (ASK, THEN EXECUTE)**

This skill analyzes CLAUDE.md files and proposes optimizations using progressive disclosure patterns. It NEVER makes destructive changes without explicit user approval. Always present the plan, get confirmation, then execute.

## Quick Start

### Phase 1: Detect & Analyze
1. Scan the repo for agent instruction files:
   - `./CLAUDE.md` or `./.claude/CLAUDE.md` (Claude Code)
   - `./AGENTS.md` and any nested `AGENTS.md` in subdirectories (OpenAI Codex / GitHub Copilot)
   - `.github/copilot-instructions.md` and `.github/instructions/*.instructions.md` (GitHub Copilot)
2. Report each file found with its line count and the format's optimization threshold (see [Supported Formats](#supported-formats))
3. If multiple files need optimization, confirm with the user which to address first
4. Parse the selected file into sections and categorize each:
   - **Essential** - Required for every session (build commands, test patterns, security rules)
   - **Reference** - Needed occasionally (architecture docs, API references, troubleshooting)
   - **Redundant** - Duplicates existing docs or overly verbose

### Phase 2: Detect Constraints
1. Check `.gitattributes` for `filter=git-crypt diff=git-crypt` patterns
2. Identify encrypted paths (docs/, .claude/, etc.)
3. Find safe unencrypted directory for sub-documents (prefer project root or subdirs)

Read the full skill on GitHub

Details

Skill name: claude-md-optimizer
Repository: wrsmith108/claude-md-optimizer
Repo updated: 25 June 2026

FAQ

What does the Claude Md Optimizer skill do?

How do I install the Claude Md Optimizer skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add wrsmith108/claude-md-optimizer --skill claude-md-optimizer. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Claude Md Optimizer popular?

It lives in wrsmith108/claude-md-optimizer, which has 26 GitHub stars and 7 forks.

Related skills

Ncm Listening Profile

dragonknightk/ncm-listening-profile

当用户想在 Windows 或 macOS 上采集网易云音乐/NetEase Cloud Music 桌面版听歌画像数据、导出主歌单和听歌排行、生成本地 JSONL/CSV/aggregate 文件与 AI 分析 prompt 时使用。此 Skill 通过 CDP 启动或连接本机网易云音乐客户端，在已登录页面上下文用网易云 `/api` 采集用户创建歌单、主歌单、最近一周听歌排行和所有时间听歌排行；本 Skill 不在采集会话内做人格或画像分析。

AI, LLMs & Agents10

Agent Research Radar

maddness/agent-research-radar

Радар фундаментальных публикаций про автономных AI-агентов в блогах AI-лабораторий и продуктовых команд (Anthropic, Claude, OpenAI, Cursor, LangChain, Amp, Cognition). Собирает ленты и HTML-индексы за окно дат, отсеивает продуктовые анонсы и релизы моделей, оставляет глубокие посты про архитектуру агентов: память и контекст, long-running циклы, self-improvement, оркестрация, экономика прогона, эвалы, риски длинных горизонтов. Отдаёт дайджест со ссылками, сутью каждого поста и тем, что забрать в свою работу. Use when (используй когда): пользователь хочет узнать, что нового вышло в блогах про AI

AI, LLMs & Agents

Skill Router

hussi9/skill-router

Use when a [skill-router] route card appears in the turn, when no card appeared on a non-trivial task, or when a route looks wrong. Routes every prompt to the right installed skill, pairs it with a process skill, tiers enforcement, and briefs sub-agents. 79 local skills + plugin skills indexed.

AI, LLMs & Agents

Zeng Shiqiang

jangviktor-web/zeng-shiqiang

曾仕强（1934–2018）思维蒸馏 persona。将曾仕强的中国式管理、易理处世、道德经与人际智慧蒸馏为可被 AI 调用的"曾师视角"技能，覆盖管理领导、人际相处、情绪化解、人性洞察、易经/道德经义理、家庭教育。当用户提到"曾仕强视角""曾师会怎么看""中国式管理思维""把曾仕强思维方式做成技能""用曾仕强口吻回答""圆通不是圆滑/持经达变/修己安人怎么理解"时触发。不适用于：中医诊疗、命理占卜、金融投资建议、纯西方管理学实证——这些是其他技能范畴；本技能是"管理·处世·易理"人物 persona，非医疗/命理技能。

AI, LLMs & Agents

Search Answer Reviewer

57-H/search-answer-reviewer

Web search review. Use when an agent is about to search the web, receives web search results or retrieved pages, or checks an answer based on them. Activate before the first search; review results before using them, even without an explicit audit request. 中文：网页搜索前启用，结果返回后审查。

AI, LLMs & Agents

Surrealdb

24601/surreal-skills

Expert SurrealDB 3 architect and developer skill (tracks v3.1.4+). SurrealQL mastery, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, security, deployment, performance tuning, SDK integration (JS, Python, Go, Rust, Java, .NET, C, PHP, Swift, Kotlin, Ruby), Surrealism WASM extensions, SurrealML scope coverage (preview), built-in MCP (v3.1+) and standalone SurrealMCP, LangChain Python integration, editor tooling (LSP v0.1.6, tree-sitter, CodeMirror v1.0.6, VS Code/JetBrains/Neovim/Zed), and ecosystem integrations (Surrealist v3.9, Surreal-Sync, Surrea

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.