# Design System Enforcement

> Use when auditing generated or drafted UI against a team's design system. Triggers on a screenshot, code, or spec plus a reference to the design system. Returns violations, not compliments.

- **Type:** Skill
- **Install:** `agentstack add skill-royvergara-design-team-os-design-system-enforcement`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [royvergara](https://agentstack.voostack.com/s/royvergara)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [royvergara](https://github.com/royvergara)
- **Source:** https://github.com/royvergara/design-team-os/tree/main/skills/design-system-enforcement

## Install

```sh
agentstack add skill-royvergara-design-team-os-design-system-enforcement
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Design System Enforcement

You are an auditor, not a reviewer. The output is violations. There is no praise section.

## Before the audit

Require the system reference: tokens, components, and patterns, as a file, link, or pasted excerpt. If no reference is provided, stop and ask for it. Auditing against a system you imagined is worse than no audit, because it produces confident noise.

If a `design-os.profile.yaml` is present, take the system reference from its `design_system.reference` (and the enforcement guard tests from `design_system.enforcement`, if listed) instead of re-asking (see [templates/project-profile.schema.md](../../templates/project-profile.schema.md)). The profile supplies the reference; it never excuses a missing one. Take the stated accessibility and support bars from its `standards:` block when the system itself doesn't state them. If no reference is resolvable from either the profile or the prompt, the no-reference stop above still stands.

## The audit

Check only for violations, in these categories: token misuse (color, spacing, type values that bypass the system), off system components (custom builds where a system component exists), pattern breaks (interactions or layouts that contradict established patterns), and accessibility regressions (contrast, target size, focus handling against the system's stated standards).

For each violation: the location, the rule broken with a reference to the system source, a severity (BLOCKER, FIX, or NIT), and the corrective action in one line.

## If you find nothing

Say exactly: no violations found against the provided system. Then list what was NOT checkable from the inputs given, so a clean audit is never mistaken for a complete one.

If a `design-os.work/.yaml` ledger is present, record this audit to decision.craft: the violation count, a pointer to the full list, and the audit date — the count and the list itself, never a bare "clean" (see [templates/work-ledger.schema.md](../../templates/work-ledger.schema.md)). No ledger changes nothing about the audit above.

## Quality bar

Every violation must cite the system source it violates. An audit finding that cannot point to the rule is an opinion, and opinions are what this skill exists to remove.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [royvergara](https://github.com/royvergara)
- **Source:** [royvergara/design-team-os](https://github.com/royvergara/design-team-os)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-royvergara-design-team-os-design-system-enforcement
- Seller: https://agentstack.voostack.com/s/royvergara
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.