# keyline

> keyline — yuvalt-keyline. Use this tool when you need to generate multi-size designs from a JSON scene, solving the problem of creating pixel-exact images in various sizes. It takes a JSON scene as input and outputs PNGs in multiple sizes, leveraging Skia rendering for accuracy. Ideal for use cases where AI-authored designs require flexible and precise image rendering, integrated with git for version control.

Canonical page: https://skillsregistry.net/skills/yuvalt-keyline  
JSON: https://api.skillsregistry.net/v1/skills/yuvalt-keyline

## Description

AI-native design engine: agents design over MCP, keyline renders PNG, JPEG, WebP and PDF at every size. No Chrome or browser: one native binary.

## Trust

- **Trust score (0–1):** 0.52
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/yuvalt/keyline)

## 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": "yuvalt-keyline"
    }
  }
}
```

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