AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Design System Enforcement

skill-royvergara-design-team-os-design-system-enforcement · by royvergara

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.

No reviews yet
0 installs
6 views
0.0% view→install

Install

$ agentstack add skill-royvergara-design-team-os-design-system-enforcement

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-royvergara-design-team-os-design-system-enforcement)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
23d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Design System Enforcement? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

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.

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

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.