ClawHub

UI/UX Design Guide

v1.0.0

Expert guidance on mobile-first UI/UX design, color systems, typography, accessibility (WCAG 2.2), Tailwind + Shadcn/ui integration, micro-interactions, and...

⭐ 23· 11.2k·88 current·95 all-time
by@itsjustdri
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The skill name and content are aligned: markdown files provide UI/UX principles, component examples, accessibility guidance, and Tailwind/Shadcn setup instructions — all coherent for a design guide.
✓
Instruction Scope
SKILL.md and the reference documents stay on-topic (design rules, code snippets, and recommended CLI commands for setting up Next.js + Tailwind + shadcn). Instructions do not ask the agent to read unrelated system files, exfiltrate data, or access secrets.
ℹ
Install Mechanism
There is no formal install spec and no code shipped to run on install. The docs recommend running npx commands (create-next-app, shadcn) which will fetch code from npm at runtime — expected for the stack but worth noting because executing those commands will download and run external packages.
✓
Credentials
The skill requests no environment variables, credentials, or config paths. All examples and snippets operate on local project files and typical frontend dependencies, so requested access is minimal and proportionate.
✓
Persistence & Privilege
The skill is instruction-only, not always-enabled, and does not request persistent system-wide presence or changes to other skills. Agent autonomous invocation is allowed (platform default) but is not a red flag here given the benign content.
Assessment
This is a content-only UI/UX design guide (no code files that run on install) and appears coherent and safe. If you plan to follow the setup steps, be aware that running the suggested npx/create-next-app and npx shadcn commands will download and execute packages from the public npm registry — only run them in a trusted/dev environment and verify package sources/versions. If you allow the agent to act autonomously, it could suggest or execute those CLI steps; consider limiting autonomous runs or reviewing proposed commands before execution.

Like a lobster shell, security has layers — review code before you run it.

accessibilityvk97ftawta7j5qpsj9502mdmnwx80j1cddesignvk97ftawta7j5qpsj9502mdmnwx80j1cdlatestvk97ftawta7j5qpsj9502mdmnwx80j1cdresponsivevk97ftawta7j5qpsj9502mdmnwx80j1cdshadcnvk97ftawta7j5qpsj9502mdmnwx80j1cdtailwindvk97ftawta7j5qpsj9502mdmnwx80j1cduivk97ftawta7j5qpsj9502mdmnwx80j1cduxvk97ftawta7j5qpsj9502mdmnwx80j1cd

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments