# Design Systems

> Design system architecture and governance — token taxonomy, component APIs, versioning strategy, adoption metrics, multi-brand theming, and cross-platform consistency

- **Type:** Skill
- **Install:** `agentstack add skill-sarveshsea-design-skills-design-systems`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [sarveshsea](https://agentstack.voostack.com/s/sarveshsea)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [sarveshsea](https://github.com/sarveshsea)
- **Source:** https://github.com/sarveshsea/design-skills/tree/main/skills/design-systems
- **Website:** https://www.memoire.cv/notes/community/

## Install

```sh
agentstack add skill-sarveshsea-design-skills-design-systems
```

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

## About

# Design systems

Read [the design-system architecture guide](references/guide.md). Inventory current product patterns and ownership before proposing a new taxonomy. Separate semantic tokens from implementation tokens, define stable component contracts, and document migration and versioning policy. Prefer measurable adoption and accessibility gates over a component-count vanity metric. Verify decisions against representative products and platforms.

## Source & license

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

- **Author:** [sarveshsea](https://github.com/sarveshsea)
- **Source:** [sarveshsea/design-skills](https://github.com/sarveshsea/design-skills)
- **License:** MIT
- **Homepage:** https://www.memoire.cv/notes/community/

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-sarveshsea-design-skills-design-systems
- Seller: https://agentstack.voostack.com/s/sarveshsea
- 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%.