# Petroglyphs

> Use this tool when you need to capture and digitize handwriting from an iPad, converting it into a format that can be analyzed by large language models (LLMs). Petroglyphs solves the problem of integrating handwritten input into digital workflows, supporting use cases such as note-taking and idea generation. It takes handwriting input from an iPad app and outputs PNG images, accessible via stdio or HTTP transports, with options for saving to Obsidian vaults or exporting to Excalidraw format.

Canonical page: https://skillsregistry.net/skills/surfndev-petroglyphs  
JSON: https://api.skillsregistry.net/v1/skills/surfndev-petroglyphs

## Description

Captures handwriting as PNG images from an iPad companion app and exposes them to LLMs. Supports both stdio and HTTP transports, with tools for retrieving handwriting submissions, saving to Obsidian vaults, and exporting to Excalidraw format. Runs as a local server connecting iPad and Claude Desktop over the same Wi-Fi network.

## Trust

- **Trust score (0–1):** 0.91
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/surfndev-petroglyphs)
- **Repository:** <https://github.com/surfndev/petroglyphs-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "surfndev-petroglyphs"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/surfndev-petroglyphs` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/surfndev-petroglyphs/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt