Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Bidirectional Remarkable Tablet Sync

ASecurity

Bidirectional sync with reMarkable tablet via Cloud API (rmapi). Fetch handwritten notes/sketches, process with AI, and push content back. Use for sketch enhancement, journal extraction, or sending documents/images to the tablet.

19 stars
0 votes
0 copies
1 views
Added 9/19/2026
ai-agentspythongobashgitapi

Works with

api

Security Analysis

A92/100
mediumUses curl or wget to download content
mediumInstalls packages at runtime which could introduce malicious dependencies

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add rondoflow/rondoflow --skill bidirectional-remarkable-tablet-sync --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Bidirectional Remarkable Tablet Sync?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Bidirectional Remarkable Tablet Sync
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/rondoflow-bidirectional-remarkable-tablet-sync/badge)](https://www.skillsdirectory.com/skills/rondoflow-bidirectional-remarkable-tablet-sync)

More formats (shields.io, HTML) on the badges page.

Download with Pro
Files
SKILL.md
---
name: bidirectional-remarkable-tablet-sync
description: "Bidirectional sync with reMarkable tablet via Cloud API (rmapi). Fetch handwritten notes/sketches, process with AI, and push content back. Use for sketch enhancement, journal extraction, or sending documents/images to the tablet."
category: "Media"
author: community
version: "1.0.0"
icon: image
---

# reMarkable Tablet Integration (rmapi)

Bidirectional sync with reMarkable tablet via Cloud API. Fetch sketches and notes, process them (AI enhancement, text extraction), and push content back to the tablet.

## Typical Use Cases

1. **Sketch → AI → Tablet loop** — Fetch rough sketch → enhance with AI → push polished version back
2. **Journal entries** — Fetch handwritten thoughts → interpret → append to memory/journal
3. **Brainstorming** — Fetch diagrams/lists → extract structure → add to project docs
4. **Send reading material** — Push PDFs/documents to tablet for offline reading
5. **AI art to tablet** — Generate images → convert to PDF → push for viewing on e-ink

## Bidirectional Pipeline

```
┌─────────────────────────────────────────────────────────────────┐
│                        FETCH (tablet → agent)                    │
├─────────────────────────────────────────────────────────────────┤
│  reMarkable → Cloud sync → rmapi get → .rmdoc                   │
│                                           ↓                      │
│                              unzip → .rm file → rmc → SVG       │
│                                                      ↓           │
│                                          cairosvg → PNG          │
│                                                      ↓           │
│                               ┌──────────┴──────────┐            │
│                          Text content?         Visual/sketch?    │
│                               ↓                      ↓           │
│                        OCR/interpret          AI image editing   │
│                               ↓                      ↓           │
│                        Add to memory        Enhanced image       │
└─────────────────────────────────────────────────────────────────┘

┌─────────────────────────────────────────────────────────────────┐
│                        PUSH (agent → tablet)                     │
├─────────────────────────────────────────────────────────────────┤
│  Image/document → Convert to PDF (if needed) → rmapi put        │
│                                                      ↓           │
│                                           Cloud sync → tablet    │
└─────────────────────────────────────────────────────────────────┘
```

## Prerequisites

### 1. Install rmapi

Download the latest release from [juruen/rmapi](https://github.com/ddvk/rmapi/releases) (ddvk fork recommended):

```bash
# Example for Linux amd64
curl -L https://github.com/ddvk/rmapi/releases/latest/download/rmapi-linux-amd64 -o ~/bin/rmapi
chmod +x ~/bin/rmapi
```

### 2. Install conversion tools

```bash
pip install --user rmc cairosvg pillow
```

- **rmc** — Converts `.rm` stroke files to SVG
- **cairosvg** — Converts SVG to PNG
- **pillow** — Converts PNG to PDF for pushing back

### 3. Authenticate (ONE-TIME)

1. Go to https://my.remarkable.com/connect/desktop
2. Log in and copy the 8-character code
3. Run `rmapi` and paste the code when prompted
4. Token saved to `~/.rmapi` — future runs are automatic

## Commands

### Fetch (Download from tablet)

```bash
# List files/folders
rmapi ls
rmapi ls -l -t              # Long format, sorted by time

# Refresh from cloud
rmapi refresh

# Navigate
rmapi cd "folder name"

# Find files
rmapi find --starred /              # Starred items
rmapi find --tag="my-tag" /         # By tag
rmapi find / ".*sketch.*"           # By regex

# Download single file
rmapi get "filename"
rmapi get "Folder/Notebook"

# Download with annotations (best for handwritten content)
rmapi geta "filename"

# Bulk download folder
rmapi mget -o ./sync-folder/ "/My Folder"
```

### Push (Upload to tablet)

```bash
# Upload single file (PDF or EPUB only)
rmapi put document.pdf
rmapi put document.pdf "Target Folder/"

# Bulk upload
rmapi mput ./local-folder/ "Remote Folder/"

# Create folder on tablet
rmapi mkdir "New Folder"
```

**Supported formats:** PDF, EPUB

## Conversion Workflows

### Fetch: .rmdoc → PNG

reMarkable notebooks download as `.rmdoc` (a ZIP archive containing stroke data):

```bash
# 1. Download the notebook
rmapi get "Folder/MyNotebook"

# 2. Extract (it's a zip)
unzip "MyNotebook.rmdoc" -d extracted/

# 3. Find the .rm stroke file(s)
# Structure: extracted/<doc-uuid>/<page-uuid>.rm
find extracted -name "*.rm"

# 4. Convert .rm → SVG
rmc -t svg -o page.svg "extracted/<doc-uuid>/<page-uuid>.rm"

# 5. Convert SVG → PNG (reMarkable dimensions: 1404×1872)
python3 -c "
import cairosvg
cairosvg.svg2png(url='page.svg', write_to='page.png', output_width=1404, output_height=1872)
"
```

### Push: Image → PDF

reMarkable only accepts PDF/EPUB, so convert images first:

```python
from PIL import Image

img = Image.open('image.png')
rgb = img.convert('RGB')
rgb.save('image.pdf', 'PDF', resolution=150)
```

Then push:
```bash
rmapi put image.pdf "My Folder/"
```

## Full Workflow Example

**Sketch enhancement loop:**

```bash
# 1. Fetch sketch from tablet
rmapi get "Sketches/MyDrawing"

# 2. Extract and convert to PNG
unzip MyDrawing.rmdoc -d MyDrawing_extracted/
RM_FILE=$(find MyDrawing_extracted -name "*.rm" | head -1)
rmc -t svg -o sketch.svg "$RM_FILE"
python3 -c "import cairosvg; cairosvg.svg2png(url='sketch.svg', write_to='sketch.png', output_width=1404, output_height=1872)"

# 3. [Your AI enhancement step here]
# Example: use any image-to-image AI tool to enhance sketch.png → enhanced.png

# 4. Convert to PDF and push back
python3 -c "from PIL import Image; Image.open('enhanced.png').convert('RGB').save('enhanced.pdf', 'PDF', resolution=150)"
rmapi put enhanced.pdf "Sketches/"
```

## Sharing Strategies

Create a dedicated sync folder on your tablet, or use:
- **Tags** — Tag items for discovery with `rmapi find --tag`
- **Stars** — Star items for quick access with `rmapi find --starred`

## Notes

- **Cloud sync required** — Tablet must sync to cloud before files are available (pull down to refresh on tablet)
- **Format** — `.rmdoc` is a ZIP containing JSON metadata + `.rm` binary stroke files
- **Warnings** — `rmc` may show warnings about newer format versions — usually still works
- **Dimensions** — reMarkable display is 1404×1872 pixels (portrait)
- **Text extraction** — For handwritten text, use vision models to interpret visually rather than traditional OCR

## Troubleshooting

| Issue | Solution |
|-------|----------|
| `rmapi` not connecting | Re-authenticate: delete `~/.rmapi` and run `rmapi` again |
| File not found after upload | Wait for cloud sync, or refresh tablet manually |
| `rmc` format warnings | Usually safe to ignore; output still generated |
| SVG looks empty | Check if the correct `.rm` file was used (multi-page notebooks have multiple) |

Attribution

rondoflowrondoflow
View sourceMore from rondoflow →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

693621 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →