Awesome Design Skills is a curated registry of design-system instruction files for AI-powered coding and design agents. It helps agents follow particular visual styles, component rules, accessibility constraints, and quality checks when building interfaces. The catalogue entries are the listed design skills that users can pull into their projects.
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.
npx skills add bergside/awesome-design-skills --skill claudegit clone --depth 1 https://github.com/bergside/awesome-design-skillsWrote 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.
[](https://agentmods.dev/skills/bergside/awesome-design-skills/claude)<a href="https://agentmods.dev/skills/bergside/awesome-design-skills/claude"><img src="https://agentmods.dev/badge/skills/bergside/awesome-design-skills/claude/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.
<a href="https://agentmods.dev/skills/bergside/awesome-design-skills/claude"><img src="https://agentmods.dev/badge/skills/bergside/awesome-design-skills/claude.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
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 →
- high Prompt Injection · line 8 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00041 | $0.00886 |
| Opus 5 | $0.00020 | $0.00443 |
| Sonnet 5 | $0.00008 | $0.00177 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
claude 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 11d ago.
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.
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Design System Skill (Universal)
Mission
You are an expert design-system guideline author for Claude. Create practical, implementation-ready guidance that can be directly used by engineers and designers.
Brand
A research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm ivory parchment (never pure white), with near-black slate as the dominant ink. The chromatic budget is intentionally tiny: a single earthy clay accent held in reserve, deployed sparingly. Typography pairs a tight grotesque (Anthropic Sans) for UI chrome with a serif at display scale (Anthropic Serif) reserved for inverted dark feature cards. Emphasis comes from typography and underlines — never from color or glow. Surfaces use hard-edged contrast, zero shadows, and an alternating ivory ↔ near-black rhythm. Buttons are flat with 0px corners; the only signature curvature is the asymmetric flat-top/rounded-bottom on the primary CTA.
Style Foundations
- Visual style: modern, minimal, clean
- Typography scale: 12/14/16/20/24/32 | Fonts: primary=Anthropic Sans, display=Anthropic Sans, mono=JetBrains Mono | weights=100, 200, 300, 400, 500, 600, 700, 800, 900
- Color palette: primary, secondary, neutral, success, warning, danger | Tokens: primary=#141413, secondary=#FAF9F6, success=#16A34A, warning=#D97706, danger=#DC2626, surface=#FFFFFF, text=#111827
- Spacing scale: 4/8/12/16/24/32
Accessibility
WCAG 2.2 AA, keyboard-first interactions, visible focus states
Writing Tone
concise, confident, helpful
Rules: Do
- prefer semantic tokens over raw values
- preserve visual hierarchy
- keep interaction states explicit
Rules: Don't
- avoid low contrast text
- avoid inconsistent spacing rhythm
- avoid ambiguous labels
Expected Behavior
- Follow the foundations first, then component consistency.
- When uncertain, prioritize accessibility and clarity over novelty.
- Provide concrete defaults and explain trade-offs when alternatives are possible.
- Keep guidance opinionated, concise, and implementation-focused.
What ships with it
1 file 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.
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.
- 11d ago First seen · 82 lines · 41 tokens per session scan A 19822c37ce8f
claude is a skill published in the GitHub repository bergside/awesome-design-skills (2,722 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 886 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
ai-accessibility
A Chinese-language assistant for diagnosing accessibility and ease-of-use problems in a page or service. Accessibility means making digital products usable by people with different abilities and needs.
ai-baoyu-image-cards
A visual content assistant for creating image cards, which are graphics that present information in a readable format. It can assess a card concept, suggest prompts or storyboards, and check publishing specifications.
ai-design-taste-frontend
A frontend visual-quality reviewer that examines whether an interface looks polished and coherent. It produces visual or creative diagnoses, prompt or storyboard ideas, and publishing checks.
ai-extract-design-system
A visual-quality review assistant for examining a product or software interface and its design patterns.
ai-frontend-design
A visual-quality review assistant for checking whether a design is ready to publish.
ai-high-end-visual-design
A visual-quality review assistant for checking whether an image is ready to publish and identifying creative improvements.