UI Skills is a collection of skills and lessons for design engineers working on user interfaces. Developers and coding agents use it through a command-line interface or MCP tools to browse and retrieve design-engineering guidance. The catalogue add-ons contain selected UI skills and an instruction for using them.
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 ibelick/ui-skills --skill create-design-mdgit clone --depth 1 https://github.com/ibelick/ui-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/ibelick/ui-skills/create-design-md)<a href="https://agentmods.dev/skills/ibelick/ui-skills/create-design-md"><img src="https://agentmods.dev/badge/skills/ibelick/ui-skills/create-design-md/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/ibelick/ui-skills/create-design-md"><img src="https://agentmods.dev/badge/skills/ibelick/ui-skills/create-design-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 4 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 114 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 MCP Rug Pull · line 223 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 MCP Rug Pull · line 229 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 MCP Rug Pull · line 239 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]
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 | $0.00066 | $0.03249 |
| Opus 5.5 | $0.00026 | $0.01300 |
| Sonnet 5.5 | $0.00013 | $0.00650 |
| Haiku 4.5 | $0.00007 | $0.00325 |
Grade A, and why
create-design-md 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 1mo 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create DESIGN.md
Create a DESIGN.md for one product or coherent website. Record the design language that governs it, not every value that happens to exist.
Boundaries
- Modify only
DESIGN.md. Do not change product source, dependencies, configuration, or generated files. - Use the DESIGN.md format contract below. Do not invent a competing schema.
- Do not copy every discovered token or component into the document.
- Do not convert repetition, local styling, or visual preference into product intent.
1. Choose the mode
Repository mode
Use when a local product repository is available. Create or update DESIGN.md at the root of the selected product.
If the repository contains multiple deployable products, select the one named by the user. If the request does not identify one and ownership is ambiguous, ask before writing.
Repository evidence may establish normative values, token names, component ownership, and documented rationale.
URL mode
Use when the user provides a public URL without its source repository. Create a reconstructed DESIGN.md draft in the current workspace.
URL mode requires rendered browser access. Inspect the DOM, computed styles, and publicly loaded stylesheets at desktop and mobile widths. Screenshots may support interpretation but cannot establish exact values by themselves.
Inspect the supplied page and shared chrome. For a site-wide request, sample up to three same-origin pages that represent distinct templates.
URL evidence may establish only observable visual patterns and computed values. It cannot establish internal token names, component ownership, undocumented rationale, or whether a pattern is intentionally canonical.
If rendered inspection is unavailable, ask for screenshots or source files. Do not create a DESIGN.md from copy, metadata, or HTML structure alone.
Choose repository mode whenever source is available. A supplied URL may verify rendered presentation but does not replace repository evidence.
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.
- 1mo ago First seen · 255 lines · 66 tokens per session scan A adba4fa94a9c
create-design-md is a skill published in the GitHub repository ibelick/ui-skills (10,113 stars, last pushed 4d ago), licensed MIT. It adds 66 tokens to every session and 3,249 once invoked, about $0.0003 per session on Opus 5.5. 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
frontend-design
Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults.
display-glasses-with-jetpack-compose-glimmer
Provides guidelines for developing projected Android XR apps for display glasses using the Jetpack Compose Glimmer UI toolkit. Covers Glimmer design principles, workflows, and interaction models for the glasses form factor. Use this skill to build an Android XR Augmented Experience app with Jetpack Compose Glimmer.…
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
read
Fetches URLs and PDFs, then summarizes or returns clean Markdown; can also search the web through DeepSeek when built-in search is thin. Use when asked to read, fetch, quote, cite, convert, or save a URL or PDF. Not for local text files already in the repo.
visual-edit
Open and collaboratively edit a running local app in Design, with shared fallback previews and source handoff. Use when the user asks to inspect, share, or edit a real local app in Design.
visual-plan
Turn ordinary text plans into rich interactive visual plans with diagrams, file maps, annotated code, open questions, and UI/prototype review when useful.