# Optical Context

> Use this tool when you need to efficiently process and analyze large, visually structured documents, such as operating manuals or product catalogs, by converting them into compact PNG images that preserve layout relationships. It solves problems of manual document analysis and data extraction by using Mistral OCR to extract page content and figures, and then recomposing them into dense images. Ideal for agent workflows that require rapid processing of complex documents with embedded figures and layouts.

Canonical page: https://skillsregistry.net/skills/chrboebel-optical-context  
JSON: https://api.skillsregistry.net/v1/skills/chrboebel-optical-context

## Description

Converts large, visually structured PDFs into compact packed PNG images optimized for agent workflows. Uses Mistral OCR to extract page content and embedded figures, then recomposes them into dense images that preserve visual grouping and layout relationships. Designed for operating manuals, scanned handbooks, product catalogs, and slide decks.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/chrboebel-optical-context)
- **Repository:** <https://github.com/chrboebel/optical-context-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": "chrboebel-optical-context"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/chrboebel-optical-context` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/chrboebel-optical-context/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