# apple-notes

Adopt this skill: https://proskills.md/skills/other/claude-world-claude-agent-claude-skills-apple-notes

Page: https://proskills.md/skills/other/claude-world-claude-agent-claude-skills-apple-notes
This document is the public skill bundle for that page. It contains SKILL.md and every helper file the catalog carries. No login is required.

## File: .claude/skills/apple-notes/SKILL.md
size: 2698
upstream: https://github.com/claude-world/claude-agent/blob/main/.claude/skills/apple-notes/SKILL.md

````text
---
name: apple-notes
description: >
  Manage macOS Apple Notes via the memo CLI — create, view, edit, delete, search,
  move, and export notes across folders. Use when user says "add note", "find note",
  "show my notes", "create note about...", or "export note".
allowed-tools:
  - Bash
  - Read
  - Write
model: haiku
user-invocable: true
when_to_use: >
  When user wants to create, read, search, edit, or manage Apple Notes on macOS.
  Triggers: "add a note", "create note", "find note about...", "show notes",
  "edit note", "delete note", "export note", "move note to folder".
argument-hint: "<action: list|create|view|edit|delete|search|move|export> <details>"
---

# Apple Notes

Manage native macOS Apple Notes using the `memo` CLI. macOS only.

## Prerequisites

```bash
brew install antoniorodr/memo/memo
```

After install, grant Notes access when macOS prompts. If not prompted:
System Settings → Privacy & Security → Contacts/Notes → allow Terminal.

## Commands

| Command | Description |
|---------|-------------|
| `memo list` | List all notes (title + folder) |
| `memo list --folder "<Folder>"` | List notes in a specific folder |
| `memo create "<Title>" --body "<Content>"` | Create a new note |
| `memo view "<Title>"` | View note content |
| `memo edit "<Title>" --body "<New Content>"` | Replace note body |
| `memo delete "<Title>"` | Delete a note |
| `memo search "<Query>"` | Search notes by content |
| `memo move "<Title>" --folder "<Destination>"` | Move note to a folder |
| `memo export "<Title>" --format md` | Export note as Markdown |

## Usage Examples

**Create a quick note:**
```bash
memo create "Meeting notes 2026-03-21" --body "Discussed Q2 roadmap. Next steps: draft proposal."
```

**Search for a note:**
```bash
memo search "quarterly roadmap"
```

**View a specific note:**
```bash
memo view "Meeting notes 2026-03-21"
```

**Export as Markdown to a file:**
```bash
memo export "Meeting notes 2026-03-21" --format md > workspace/meeting-notes.md
```

**Move note to a folder:**
```bash
memo move "Meeting notes 2026-03-21" --folder "Work"
```

## Rules

- Always check if CLI is installed first: `which memo`
- If not installed, show the brew install command and stop
- macOS only — if not on macOS, inform the user and stop
- When creating notes with multi-line content, write content to a temp file and pipe it, or use heredoc via Bash
- When viewing long notes, save to `workspace/note-<slug>.md` and summarize inline rather than dumping full content
- Search is case-insensitive; use concise query terms
- Keep output concise: confirm action taken in one line
- If a title is ambiguous, run `memo list` first and ask the user to clarify
````

## File: README.md
upstream: https://github.com/claude-world/claude-agent/blob/main/README.md

````text
# Claude-Agent

[![CI](https://github.com/claude-world/claude-agent/actions/workflows/ci.yml/badge.svg)](https://github.com/claude-world/claude-agent/actions/workflows/ci.yml)
[![npm](https://img.shields.io/npm/v/claude-agent-app)](https://www.npmjs.com/package/claude-agent-app)
[![Node.js](https://img.shields.io/badge/node-%3E%3D22-brightgreen)](https://nodejs.org)
[![License: MIT](https://img.shields.io/badge/License-MIT-blue.svg)](LICENSE)

> Turn Claude Code into a persistent personal assistant with autonomous memory, multi-channel support, and intelligent task delegation.

Claude-Agent is a ready-to-use [Claude Code](https://docs.anthropic.com/en/docs/claude-code) project that transforms Claude into a long-running personal assistant. It receives messages from multiple channels (Telegram, Discord, webhooks, terminal), remembers context across sessions, and delegates complex tasks to specialist agents — all within Claude Code's native architecture.

## Features

| Category | What |
|----------|------|
| **50 Skills** | Productivity, smart home, media, messaging, security — full [OpenClaw](https://github.com/openclaw/openclaw) feature parity |
| **4 Use Methods** | CLI, Web UI (localhost:3456), Desktop App (.dmg/.exe), Telegram/Discord |
| **12-Page Control Panel** | Chat, History, Projects, Skills, Agents, Memory, MCP, Secrets, Schedule, Config Bot, Settings, Channels |
| **Scheduled Tasks** | Cron-based agent scheduling with execution history and manual trigger |
| **Project Discussion** | Multi-expert roundtable, debate, relay modes with streaming + Markdown output |
| **4 Agents** | researcher, writer, analyst, content-publisher (import/export/create with AI) |
| **Persistent Memory** | Autonomous markdown-based memory surviving compaction and restarts |
| **4 MCP Servers** | trend-pulse, claude-101, cf-browser, notebooklm (66 tools) |
| **CLI Detection** | Auto-detects claude, codex, gemini, opencode, node, uvx, gh |
| **Content Pipeline** | Trend discovery → patent-scored posts → NotebookLM image cards / podcasts |
| **4 Lifecycle Hooks** | Session bootstrap, message classifier, context guardian, session farewell |
| **i18n** | English, 繁體中文, 日本語 — all 12 pages fully translated |
| **OpenClaw Migration** | One-click import of memory, skills, agents, config |
| **Desktop App** | Electron packaging for macOS (.dmg), Windows (.exe), Linux (.AppImage) |

## Architecture

Modular server architecture inspired by [Claude Code](https://github.com/anthropics/claude-code)'s internal service layer pattern.

```
claude-agent/
├── .claude/
│   ├── settings.json            Hook configuration + env vars
│   ├── hooks/ (4)               Session lifecycle (Node.js)
│   ├── agents/ (4)              researcher, writer, analyst, content-publisher
│   ├── skills/ (50)             7 categories — see Skills Reference below
│   └── rules/ (4)               memory, channels, MCP, content quality
├── app/
│   ├── server/
│   │   ├── index.ts             App assembly + server startup (pure wiring)
│   │   ├── routes/ (14)         Modular REST API routes by domain
│   │   │   ├── sessions.ts      Session CRUD
│   │   │   ├── settings.ts      Language/model/CLI settings
│   │   │   ├── project.ts       Project directory management
│   │   │   ├── skills.ts        Skill management (50 skills)
│   │   │   ├── agents.ts        Agent management
│   │   │   ├── mcp.ts           MCP server configuration
│   │   │   ├── channels.ts      Telegram/Discord channel control
│   │   │   ├── roles.ts         Per-chat role system (14 APIs)
│   │   │   ├── scheduled-tasks.ts  Cron task scheduling
│   │   │   ├── secrets.ts       API key management
│   │   │   ├── discussions.ts   Multi-expert discussion
│   │   │   ├── memory.ts        Memory file read/write
│   │   │   ├── history.ts       Cross-session search
│   │   │   ├── cli.ts           CLI detection + migration
│   │   │   └── system.ts        Health, export, stats, webhook
│   │   ├── ws/handler.ts        WebSocket session management
│   │   ├── agent.ts             AgentSession (Claude CLI wrapper)
│   │   │   ├── sendMessage()     Injects system context + session summary
│   │   │   ├── spawnClaude()     Dynamic 5-layer system prompt
│   │   │   ├── rotate()          Async rotation with compact summary
│   │   │   └── generateCompactSummary()  9-section summary via haiku
│   │   ├── stream-handler.ts    Shared streaming (flush/typing/memory strip)
│   │   ├── memory-extractor.ts  Non-blocking background memory extraction
│   │   ├── telegram.ts          Telegram bridge (polling + media + commands)
│   │   ├── discord.ts           Discord bridge (client + attachments)
│   │   ├── reply-filter.ts      Group reply decision (5 modes)
│   │   ├── discussion.ts        Multi-expert discussion engine
│   │   ├── scheduler.ts         Cron task scheduler
│   │   ├── db.ts                SQLite data layer
│   │   ├── middleware/
│   │   │   ├── security.ts      Path validation + name sanitization
│   │   │   └── rate-limiter.ts  API rate limiting
│   │   ├── prompts/
│   │   │   ├── config-bot.ts    Config Bot system prompt
│   │   │   └── compact.ts       9-section compact summary prompt
│   │   └── constants/
│   │       └── languages.ts     Multi-language rules (en/zh-TW/ja)
│   ├── client/
│   │   ├── App.tsx              React 19 + Tailwind (12 pages)
│   │   ├── i18n.ts              Translations (en, zh-TW, ja)
│   │   └── components/ (12)     Chat, History, Projects, Skills, Agents, Memory, MCP, Secrets, Tasks, Config Bot, Settings, Channels
│   ├── electron/main.cjs        Desktop app entry point
│   └── package.json             App dependencies
├── memory/                      Persistent memory (auto-managed)
├── scripts/migrate-openclaw.cjs One-click OpenClaw migration
├── workspace/                   Runtime output (gitignored)
├── .mcp.json                    4 MCP servers (trend-pulse, claude-101, cf-browser, notebooklm)
├── CLAUDE.md                    Assistant identity + operating rules
└── README.md
```

## Installation

```bash
git clone https://github.com/claude-world/claude-agent.git
cd claude-agent
```

### Prerequisites

- **Node.js** >= 22 — required by the Web UI / Desktop app (the lifecycle hooks themselves use only built-in modules and run on any recent Node)
- **Claude Code CLI** — for Method 1 & 3. [Install here](https://docs.anthropic.com/en/docs/claude-code)

### Three Ways to Use

| Method | Best For | Command |
|--------|----------|---------|
| **1. CLI** | Developers, terminal users | `claude` |
| **2. Web UI** | Everyone, visual setup | `cd app && npm install && npm run dev` |
| **3. Telegram/Discord** | Mobile, on-the-go | Via CLI Channels or Web UI |

---

### Method 1: CLI (Terminal)

```bash
# Start Claude Code in the project directory
claude

# First time? Run guided setup
/setup
```

`/setup` will:
- Detect your OS and installed CLI tools
- Configure your profile (name, timezone, language)
- Show available skills grouped by category
- Set up scheduled routines (memory consolidation, daily briefing)

After setup, just talk naturally:
- "What's the weather in Taipei?"
- "Play some music"
- "Remind me to call the dentist at 3pm"
- "What's trending?"

---

### Method 2: Web UI (Browser)

```bash
cd app
npm install    # First time only
npm run dev    # Start the control panel
```

Open **http://localhost:3456** in your browser.

**12 Pages:**

| Page | Description |
|------|-------------|
| **💬 Chat** | Talk to your agent with streaming responses and tool call visualization |
| **📋 History** | Browse all session messages, search across conversations, view tool calls |
| **🏛️ Projects** | Multi-expert collaborative discussion with cross-CLI debate |
| **⚡ Skills** | Browse 50 skills, search, import/export, create new skills with AI |
| **🤖 Agents** | Manage 4 agents, import/export, create new agents with AI |
| **🧠 Memory** | View and edit your agent's memory files |
| **🔌 MCP** | Add/remove MCP serve
````
