# atelier

> atelier — atelier-oss-atelier. Use this tool when you need to enforce design consistency and semantic token conformance in AI-generated codebases. Atelier solves problems of design token discipline and consistency by linting DESIGN.md files and enforcing explicit precedence rules. It takes in design files and codebases as input and outputs a validated, consistent code structure, making it ideal for use in git-based development workflows.

Canonical page: https://skillsregistry.net/skills/atelier-oss-atelier  
JSON: https://api.skillsregistry.net/v1/skills/atelier-oss-atelier

## Description

Design-token discipline layer for AI-generated codebases. Lints DESIGN.md, enforces explicit > atlas > palette precedence, and ships an MCP server agents can call. +149.98% lift in semantic-token conformance.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** other
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/atelier-oss/atelier)

## 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": "atelier-oss-atelier"
    }
  }
}
```

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