What does this skill do, and when should you use it?
typeui is a Grok-facing skill by Bergside LLC that supplies UI generation context through the TypeUI remote MCP server (https://mcp.typeui.sh). It provides four kinds of resources: project design skills, brand kits with logo/typography/color tokens, UI prompt libraries for common sections and full-product flows, and layout variation guidance. It is one of four skills bundled in the bergside/typeui repository, located at plugins/grok/typeui/skills/typeui/SKILL.md. It suits developers who want consistent visual direction and brand adherence when AI generates their UI.
The skill is an instructional SKILL.md that directs Grok to prefer TypeUI MCP tools when available, ask the user which TypeUI project or design skill to use when unspecified, apply the selected project context before choosing colors, type, spacing, component tone, or page composition, and separate brand parameters (logo, project name, typography, brand colors) from the design skill (UI style, component behavior, visual hierarchy, spacing, interaction patterns). It registers the remote MCP server https://mcp.typeui.sh; the actual design resources come from that server, not local files.
- A developer building a landing page with Grok who wants their existing TypeUI project design context applied automatically
- A product team needing brand consistency (logo, typography, brand colors) across multiple generated pages
- A designer who wants several layout variations for pricing sections or dashboards before committing to one
- An engineer redesigning an existing UI who wants to pull the project's design skill first as the style source of truth
How do you install this skill?
- Shell / CLI
- Network access
- MCP Server
TypeUI remote MCP server (https://mcp.typeui.sh)Grok CLI (for grok mcp add command)
The skill lives at plugins/grok/typeui/skills/typeui/ in the bergside/typeui repository (the README does not document a separate install command for this specific sub-skill). If the TypeUI MCP server is not available in the current Grok session, connect it manually: grok mcp add --transport http typeui https://mcp.typeui.sh
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/bergside/typeui.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/plugins/grok/typeui/skills/typeui" ~/.claude/skills/
rm -rf "$tmp"Generated from the source repository and skill path; it copies only this skill's folder. If the author's install steps above differ, follow those first. To scope it to one project, replace ~/.claude/skills with that project's .claude/skills.
How do you use this skill?
Once installed, send your agent any of these to trigger it:
- Use my TypeUI project and build a landing page
- Generate three pricing section variations with TypeUI
- Redesign this dashboard using my TypeUI design skill
- Pull the TypeUI context for this project before changing the UI
In a Grok session connected to TypeUI MCP, request UI in plain language, e.g.: "Use my TypeUI project and build a landing page", "Generate three pricing section variations with TypeUI", "Redesign this dashboard using my TypeUI design skill", or "Pull the TypeUI context for this project before changing the UI". If the request does not specify a project, the skill instructs asking which TypeUI project or design skill to use.
What are this skill's strengths and limitations?
- Connects via a remote MCP server, so no design resource files need local maintenance
- Cleanly separates brand kit values from design skill guidance, preventing style and brand information from mixing
- Supports generating layout variations so options can be compared before implementation
- MIT-licensed SKILL.md with complete author and homepage metadata
- Hard dependency on the availability of the TypeUI remote MCP server; without it the skill is largely inert
- Explicitly targeted at Grok (includes the grok mcp add command); using it on other platforms requires manual adaptation
- Actual design resources are hosted on typeui.sh, and the README mentions a paid Pro version; the free/paid boundary is not explained in the skill file
- The repository-level GitHub license is marked NOASSERTION, which needs verification against the MIT claim in SKILL.md
How does this skill compare with similar options?
Side by side with related skills; every score comes from the same FSRS standard.
| Skill | FS score | Stars | Last updated | License |
|---|---|---|---|---|
| TypeUI for Grok this page | 59 · Recommended | ★ 2k | 3mo ago | NOASSERTION |
| TypeUI (Hermes Agent Design Skill) | 59 · Recommended | ★ 2k | 3mo ago | NOASSERTION |
| TypeUI (OpenClaw Skill) | 59 · Recommended | ★ 2k | 3mo ago | NOASSERTION |
| Stitch Prompt Refiner | 49 · Use with care | ★ 8.5k | 2mo ago | Apache-2.0 |
| Stitch Design System Manager | 45 · Not recommended | ★ 8.5k | 2mo ago | Apache-2.0 |
The README names a separately installable typeui-fundamentals skill (UI/UX fundamentals) within the same repo as a complementary/alternative option; this skill instead relies on the TypeUI MCP for project-level design context, so their scopes differ.
How did FollowSkills review this skill?
The Grok-platform adaptation of TypeUI; the 4 platform variants (this is the Grok one) are highly similar — fundamentally the same design-system context integration.
Connects to a remote MCP server (mcp.typeui.sh) for brand assets and design context — involves a third-party hosted service; the specific data flow wasn't verified.
Open a dimension to read why it scored that way
Evidence confidence：Low — Mostly static review, author material or a limited demo; useful for discovery, not high-risk decisions.
This review was completed under FSRS 1.0. Dimension scores are not converted; it is queued for re-review under FSRS 2.0.
See the full review method →