⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
apple-notes
>
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
Claude-Agent
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 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 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'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
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
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)
# 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)
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 |
// HOW IT'S BUILT
// FILES
2 files shipped with this skill. Inline text is the catalog copy. The upstream link is the source repository.
.claude/skills/apple-notes/SKILL.md2.6 KBupstream ↗
--- 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 clarifyREADME.mdupstream ↗
Contents are not inlined in the catalog. Open the upstream file.
Plain-text copy, no login: /skill-bundles/claude-world-claude-agent-claude-skills-apple-notes.md