How do I install the Remarkable skill?

Run npx skillmds@latest add sammorrowdrums/remarkable in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Remarkable safe to use?

SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: executes scripts, reads secrets. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Remarkable?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Remarkable free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Remarkable?

SamMorrowDrums (@sammorrowdrums) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Remarkable by sammorrowdrums — Agent Skill

Name: Remarkable
Rating: 4.2 (5 reviews)
Author: SamMorrowDrums

Remarkable

Access reMarkable tablet documents, notebooks, PDFs, and EPUBs. Use when the user wants to read, search, browse, or extract text from their reMarkable tablet. Supports handwriting OCR, typed text, annotations, highlights, and page rendering to PNG/SVG. Triggers: "reMarkable", "tablet notes", "handwritten notes", "remarkable read", "remarkable search", "remarkable browse".

File contents

reMarkable Tablet

Access your reMarkable tablet as a second brain. Browse, search, read, and extract content from all documents including handwritten notes via OCR.

Setup

Add to openclaw.json:

{
  "mcpServers": {
    "remarkable": {
      "command": "uvx",
      "args": ["remarkable-mcp", "--usb"]
    }
  }
}

USB mode is recommended — connect via USB and enable "USB web interface" in tablet Settings → Storage. No subscription or developer mode needed.

Alternative Modes

SSH (requires developer mode):

{
  "mcpServers": {
    "remarkable": {
      "command": "uvx",
      "args": ["remarkable-mcp", "--ssh"]
    }
  }
}

Cloud (requires Connect subscription):

{
  "mcpServers": {
    "remarkable": {
      "command": "uvx",
      "args": ["remarkable-mcp"],
      "env": {
        "REMARKABLE_TOKEN": "your-token"
      }
    }
  }
}

OCR Support

For handwriting OCR, add a Google Vision API key:

{
  "mcpServers": {
    "remarkable": {
      "command": "uvx",
      "args": ["remarkable-mcp", "--usb"],
      "env": {
        "GOOGLE_VISION_API_KEY": "your-api-key"
      }
    }
  }
}

Tools

Tool	Purpose
`remarkable_read`	Read document content with text extraction, pagination, grep
`remarkable_browse`	Browse folders, search by name, filter by tags
`remarkable_search`	Multi-document content search with OCR
`remarkable_recent`	List recently modified documents
`remarkable_image`	Render pages as PNG or SVG
`remarkable_status`	Check connection and device info

Workflow

Use remarkable_browse or remarkable_search to find documents
Use remarkable_read to extract text content
Use remarkable_image to render visual pages
Use page parameter to paginate through multi-page documents

---name: remarkabledescription: Access reMarkable tablet documents, notebooks, PDFs, and EPUBs. Use when the user wants to read, search, browse, or extract text from their reMarkable tablet. Supports handwriting OCR, typed text, annotations, highlights, and page rendering to PNG/SVG. Triggers: "reMarkable", "tablet notes", "handwritten notes", "remarkable read", "remarkable search", "remarkable browse".---# reMarkable TabletAccess your reMarkable tablet as a second brain. Browse, search, read,and extract content from all documents including handwritten notes via OCR.## SetupAdd to `openclaw.json`:```json{ "mcpServers": { "remarkable": { "command": "uvx", "args": ["remarkable-mcp", "--usb"] } }}```USB mode is recommended — connect via USB and enable "USB web interface"in tablet Settings → Storage. No subscription or developer mode needed.### Alternative ModesSSH (requires developer mode):```json{ "mcpServers": { "remarkable": { "command": "uvx", "args": ["remarkable-mcp", "--ssh"] } }}```Cloud (requires Connect subscription):```json{ "mcpServers": { "remarkable": { "command": "uvx", "args": ["remarkable-mcp"], "env": { "REMARKABLE_TOKEN": "your-token" } } }}```### OCR SupportFor handwriting OCR, add a Google Vision API key:```json{ "mcpServers": { "remarkable": { "command": "uvx", "args": ["remarkable-mcp", "--usb"], "env": { "GOOGLE_VISION_API_KEY": "your-api-key" } } }}```## Tools| Tool | Purpose ||------|---------|| `remarkable_read` | Read document content with text extraction, pagination, grep || `remarkable_browse` | Browse folders, search by name, filter by tags || `remarkable_search` | Multi-document content search with OCR || `remarkable_recent` | List recently modified documents || `remarkable_image` | Render pages as PNG or SVG || `remarkable_status` | Check connection and device info |## Workflow1. Use `remarkable_browse` or `remarkable_search` to find documents2. Use `remarkable_read` to extract text content3. Use `remarkable_image` to render visual pages4. Use `page` parameter to paginate through multi-page documents

Frequently asked questions