What is design-system-creator?

A workflow that builds a portable design-system folder for a brand, containing the guidance and assets used to keep websites, campaigns, presentations, and other materials consistent. It checks required research and browser tools before proceeding.

Use it to create or update a brand design system from researched source material and prepare it for Claude Design or other asset-producing tools.

It reduces repeated brand decisions and helps keep design work aligned across different asset types. The prerequisite check also prevents it from inventing design details when source data is unavailable.

design-system-creator — Skill for Claude Code by naveedharri

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add naveedharri/benai-skills --skill design-system-creator

Clone the repo

git clone --depth 1 https://github.com/naveedharri/benai-skills

Made for: Claude Code.

Or install benai-marketing, the plugin that ships this one along with the rest of its 13 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/naveedharri/benai-skills/design-system-creator/github.svg)](https://agentmods.dev/skills/naveedharri/benai-skills/design-system-creator)

Your own site

<a href="https://agentmods.dev/skills/naveedharri/benai-skills/design-system-creator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/design-system-creator/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/naveedharri/benai-skills/design-system-creator"><img src="https://agentmods.dev/badge/skills/naveedharri/benai-skills/design-system-creator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 210 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,842 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium MCP Rug Pull · line 67
npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Fix: Pin the version: npx @scope/[email protected]
medium Memory Poisoning · line 85
Skill injects content designed to persist in agent memory or context across interactions. Persistent injection can alter agent behavior long after the initial interaction.

Fix: Do not allow untrusted input to persist in agent memory or context. Validate all content before storing and implement memory isolation between sessions.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00210	$0.01842
Opus 5	$0.00105	$0.00921
Sonnet 5	$0.00042	$0.00368
Haiku 4.5	$0.00021	$0.00184

Measured 6d ago against content hash b2283edc9df3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-system-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (assets/templates/components/utils.ts, scripts/render.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/benai-marketing/skills/design-system-creator/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Design System Creator

Produces a complete, portable design system folder: the single source of truth a brand uses for every asset it ships (web, landing pages, pitch decks, Instagram and LinkedIn carousels, emails, infographics, ads). The folder uploads directly to Claude Design's "Set up your design system" flow, feeds any LLM that produces brand assets, and doubles as a living style guide for a design team.

Step 0: Prerequisite check

Extraction and research run on real scraped data, not invented content. Before asking any discovery question or generating anything, run the diagnostic in references/setup.md to verify the three tools this skill depends on are installed and working: Firecrawl CLI, the extract-design-system skill, and Playwright Chromium.

All three present: proceed.
Anything missing: pause, share the install command for that specific tool from references/setup.md, and wait for the user to confirm.

Do not silently skip a step when a tool is missing. Inventing color values or logo paths without scraping and rendering defeats the whole point of the skill.

Step 1: Pick the branch

Once the tools are in place, ask the user exactly one question:

Are we creating a brand-new design system from scratch, or are we extracting the design system from a business you already run?

Do not branch, suggest, or assume. Route on their answer:

New / from scratch / nothing yet: Branch A. Load references/branch-a-fresh.md.
Existing business / existing site / existing brand: Branch B. Load references/branch-b-extract.md.

If the answer is ambiguous ("we have a logo but nothing else," "we've been running for a year but it's all ad-hoc"), they are almost certainly on Branch B (extraction), because you have real artifacts to work from. Confirm this with them before proceeding.

What the skill produces

Both branches output a design-system/ folder at the working-directory root, same tree, content differing by branch. Every file in the tree gets produced. Full folder tree and field-by-field content spec: references/output-structure.md.

Read the full file on GitHub · 100 lines

Files

What ships with it

40 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 100 lines · 0 tokens per session scan A b2283edc9df3

Subscribe to this mod's changes

design-system-creator is a skill published in the GitHub repository naveedharri/benai-skills (61 stars, last pushed 7d ago), licensed MIT. It adds 210 tokens to every session and 1,842 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.

Claude Code Design and UX Marketing and SEO agent-skills ai anthropic claude claude-plugins

design-sync-upload

An uploader for design-system files such as DESIGN.md, tokens, logos, fonts, and images into Claude Design. It can either use an authenticated connection or prepare a folder and guide for manual upload.

modu-ai/moai-cowork · 211 tokens

design-tokens-transformer

A converter for design tokens, which are named values for colors, fonts, spacing, borders, shadows, and motion. It translates one shared token source into CSS variables and Tailwind or shadcn-style theme files, and can convert them back for checking.

modu-ai/moai-cowork · 255 tokens

design-prompt-builder

A prompt builder for Claude Design that selects a suitable UX approach and fills in the role, goal, limits, and expected output.

modu-ai/moai-cowork · 197 tokens

design-system-prep

A preparation tool that turns scattered brand materials—such as logos, colors, fonts, websites, design files, and presentations—into a DESIGN.md file for Claude Design. Claude Design is a tool for creating interface designs from shared visual guidelines.

modu-ai/moai-cowork · 164 tokens

doc-pptx

A PowerPoint (.pptx) presentation generator and designer for business reports, investor pitches, training materials, conference talks, and product demos. It can build slides from direct content, HTML, NotebookLM, or a Markdown script.

modu-ai/moai-cowork · 266 tokens

design-handoff-reader

A reader for Claude Design handoff bundles containing the design files, conversation, and README, which is the file explaining the bundle.

modu-ai/moai-cowork · 179 tokens