ワンクリックで
remarkable-expert
reMarkable tablet expert. Use when users want to list, download, or upload files to their reMarkable tablet.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
reMarkable tablet expert. Use when users want to list, download, or upload files to their reMarkable tablet.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | remarkable-expert |
| description | reMarkable tablet expert. Use when users want to list, download, or upload files to their reMarkable tablet. |
You are an expert on managing files on a reMarkable tablet using rmapi.
rmapi must be installed at ~/.local/bin/rmapi and authenticatedpandoc is required for markdown conversion| Command | Description |
|---|---|
rmapi ls [path] | List files in folder (default: root) |
rmapi get <path> | Download file as .rmdoc (zip archive) |
rmapi put <local> [remote] | Upload file to tablet |
rmapi mkdir <path> | Create folder |
rmapi find <dir> [pattern] | Find files recursively |
All files download as .rmdoc (a zip archive). What's inside depends on the file type:
| Original Type | Contents of .rmdoc | How to View |
|---|---|---|
| Uploaded PDF | .pdf + .content + .metadata | Extract the .pdf from zip |
| Native notebook | .rm strokes + .content + .metadata | No good local converter exists |
Important: rmapi geta (annotation export) is currently broken - it generates empty 490-byte PDFs.
rmapi ls # Root folder
rmapi ls Books # Specific folder
Output format: [f] = file, [d] = folder
# 1. Download (creates <name>.rmdoc)
rmapi get "Books/MyBook.pdf"
# 2. Check if it contains a PDF
unzip -l "MyBook.pdf.rmdoc" | grep "\.pdf$"
# 3. Extract the PDF
unzip -j "MyBook.pdf.rmdoc" "*.pdf" -d /tmp/
# 4. Open it
open /tmp/*.pdf
Native notebooks (handwritten notes without a source PDF) only contain .rm stroke data. There's no reliable local converter - options:
http://10.11.99.1pandoc document.md -o /tmp/document.pdf
rmapi put /tmp/document.pdf "Documents/"
rmapi put report.pdf "Work/"
| What you see | Actually stored as | Viewable locally? |
|---|---|---|
| Uploaded PDF | PDF inside .rmdoc | Yes - extract from zip |
| Web article | Native notebook | No - needs converter |
| Handwritten notes | Native notebook | No - needs converter |
| ePub | Converted internally | Partial |
| Issue | Solution |
|---|---|
| "Unauthorized" | Re-authenticate: rmapi (get new code from my.remarkable.com) |
| File not found | Use rmapi ls to check exact path and name |
| Upload fails | Check file size (<100MB for cloud) |
| Empty/corrupt PDF from geta | Known bug - extract PDF from .rmdoc instead |
| Can't view notebook | Native format - export from tablet or use desktop app |
File review tool — launch GUI, process comments, or install. Use when user mentions file-review, reviewing files, leaving comments, or processing review comments.
Execute a single DAG step as an autonomous background sub-agent. Sibling of phase-running for DAG plans produced by v-planning. Reads a step-<n>.md file directly, atomically claims it via frontmatter status, runs the three-bucket Success Criteria, and reports back. Spawned by v-implementing or by /run-step.
Parallel DAG-plan implementation skill. Reads a v-planning plan directory (root.md + step-<n>.md files), topologically schedules ready steps, and fans them out as parallel sub-agents. Use whenever the user invokes /v-implement, points at a plan directory produced by /v-plan, or asks to "run the parallel plan", "implement the DAG", or "fan out the steps" — even without those exact words. For linear plans (single .md file), use `implementing` instead.
Vertical / parallel implementation planning skill. Creates DAG-structured plan directories where each step is an independent, QA-able vertical slice that sub-agents can pick up and implement in parallel. Use whenever the user wants a plan that fans out (multiple independent features), invokes /v-plan, or asks for a "parallel plan", "DAG plan", "vertical plan", or "plan that can be parallelized" — even if they don't say those exact words. Prefer the linear `planning` skill for strictly sequential work.
Interactive exploration of ideas through Socratic Q&A. Produces progressive documents that serve as lightweight pre-PRDs feeding into research.
Plan implementation skill. Executes approved technical plans phase by phase with verification checkpoints.