Design & Frontend

TypeUI (OpenClaw Skill)

Injects project design skills, brand kits, UI prompts, and layout variation guidance from the TypeUI MCP server so AI agents produce better, on-brand interfaces.

59/ 100
Recommended

Generally reliable with disclosed limitations; trial as directed and keep a rollback path.

See how it was scored ↓
Works as-is in
Codex · Claude Code
Stars
★ 2k
Last updated
3mo ago
License
NOASSERTION
mcp-serverdesign-systemui-promptsbrand-kit
+3openclawlayout-variationstypeui

What does this skill do, and when should you use it?

TypeUI is an AI-first design platform by Bergside LLC, and this skill wires it into OpenClaw agents. Once installed, the agent can call the TypeUI remote MCP server when building, redesigning, or refining UI, pulling in project design skills, brand kits (project name, logo, typography, brand color tokens), UI prompt libraries, and layout variation guidance. The skill's core job is to steer the agent to apply TypeUI context before choosing colors, type, spacing, component tone, or page composition. Brand kit values are treated strictly as brand parameters, while the design skill governs UI style, component behavior, visual hierarchy, spacing, and interaction patterns. The remote MCP server lives at https://mcp.typeui.sh.

Instructs the agent to prefer TypeUI MCP tools when available; ask which TypeUI project or design skill to use when the request is ambiguous; apply brand kit values (logo, project name, typography, brand colors) as brand parameters only; treat the design skill as the source for UI style, component behavior, visual hierarchy, spacing, and interaction patterns; and install the remote MCP server via OpenClaw commands when tools are missing.

Good fit
  • A developer on OpenClaw wants the agent to generate a landing page grounded in their existing TypeUI project context
  • A designer wants three pricing section variations generated at once to compare before implementation
  • A team needs the agent to automatically apply brand colors, typography, and component tone when redesigning a dashboard
  • A frontend engineer wants to pull the project's TypeUI design context before making UI changes for consistency

How do you install this skill?

Before you start
Your agent needs
  • Shell / CLI
  • Network access
  • MCP Server
Install first
  • TypeUI remote MCP server (https://mcp.typeui.sh)
  • OpenClaw CLI for install commands

The plugin package installs the TypeUI remote MCP server (https://mcp.typeui.sh). If TypeUI tools are not available in the current OpenClaw session, run: openclaw typeui install-mcp then openclaw mcp login typeui. Agents can also call typeui_install_mcp to write the MCP server entry. The broader repo can be installed with npx skills add (an exact install command for this specific skill name is not documented in the source).

Generic route: install into Claude Code manually (macOS / Linux)
tmp="$(mktemp -d)"
git clone --depth 1 https://github.com/bergside/typeui.git "$tmp"
mkdir -p ~/.claude/skills
cp -R "$tmp/plugins/openclaw/typeui/skills/typeui" ~/.claude/skills/
rm -rf "$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?

Try saying

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

After the MCP server is connected, trigger it with plain-language prompts such as: "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 doesn't specify a project, the skill asks which TypeUI project or design skill to use first.

What are this skill's strengths and limitations?

Pros
  • Clean separation of concerns: brand kits supply only brand parameters; the design skill governs style and interaction
  • Remote MCP server works out of the box with a single OpenClaw command
  • Prompt libraries and layout variation guidance encourage exploring multiple options before implementation
  • Skill file is MIT licensed and explicitly open source
Limitations
  • Hard dependency on the hosted TypeUI service (https://mcp.typeui.sh); offline or outage renders the skill largely inert
  • README marks the repo license as NOASSERTION, which conflicts with the SKILL.md MIT claim — verify before commercial use
  • Real-world quality depends on TypeUI project configuration on the platform side; the source provides no benchmarks or test evidence
  • Written for OpenClaw specifically; other agent platforms need their own MCP setup rather than this skill file

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 (OpenClaw Skill) this page 59 · Recommended ★ 2k 3mo ago NOASSERTION
TypeUI for Grok 59 · Recommended ★ 2k 3mo ago NOASSERTION
TypeUI (Hermes Agent Design 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

How did FollowSkills review this skill?

FollowSkills review · FSRS-1.0
Recommended
59/ 100 5-point scale 3.0 / 5
1Utility12 / 20 · 3.0/5
2Reliability12 / 20 · 3.0/5
3Safety16 / 25 · 3.2/5

Same as above, the OpenClaw platform adaptation, also connecting to the remote MCP server.

4Evidence5 / 15 · 1.7/5
5Usability7 / 10 · 3.5/5
6Maintenance7 / 10 · 3.5/5
1 2 3 4 5 6

Open a dimension to read why it scored that way

Reviewed Jul 17, 2026 Review evidence[1]

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 →

More skills from this repository

All from bergside/typeui

Related skills