AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Better Ui

skill-waffleflopper-ai-tools-better-ui · by waffleflopper

Review or improve UI surfaces, icons, alignment, and motion within an existing design system.

— No reviews yet
0 installs
2 views
0.0% view→install

Install

$ agentstack add skill-waffleflopper-ai-tools-better-ui

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-waffleflopper-ai-tools-better-ui)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 3d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Better Ui? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

UI polish

Preserve the project's approved component library, tokens, density, and motion language. Numerical values and visual recipes in this skill's references are optional starting points where the project has no suitable convention. Do not replace an approved pattern merely to match a recipe; a review finding needs evidence of user impact or inconsistency.

Review without editing unless changes are authorized. Text rendering belongs to better-typography; hit areas, keyboard behavior, focus, ARIA, and reduced motion to better-accessibility; grouping and responsive structure to better-layout.

Inspect the relevant details

  • Surfaces and alignment: Check closely nested radii, optical balance, and whether borders or shadows communicate structure, state, or depth. Preserve structural and focus boundaries. Read [surfaces.md](surfaces.md) for a demonstrated surface or image-edge problem.
  • Icons: Reuse the existing icon set and its optical conventions. Keep icons recognizable at render size, state styling coherent, and direction appropriate under RTL. Read [icons.md](icons.md) when inspecting icon weight, assets, or direction.
  • Interactive motion: Feedback should remain responsive when interrupted. Prefer simple transitions for interactive changes and static feedback for frequent actions. Every state change needs a cue that remains when animation does not run. Read [animations.md](animations.md) for press feedback, initial mount, or theme-switch problems.
  • Entrances, exits, and icon swaps: Animate only when the transition helps communicate the change. Read [enter-exit.md](enter-exit.md) or [icon-transitions.md](icon-transitions.md) for those cases. Use the installed motion package and existing imports; do not add a dependency for a decorative effect.
  • Performance: Name the properties that actually transition. Investigate observed stutter before adding compositing hints; avoid speculative will-change. Read [performance.md](performance.md) for transition or rendering-performance concerns.

Respect reduced-motion preferences in every recipe. Do not add animations, component props, wrappers, or global theme behavior unless the requested outcome needs them.

Verification and reporting

Inspect the relevant hover, focus, active, disabled, loading, empty, and changed states. Use a browser for visual or runtime claims; replay motion slowly when timing is unclear. Source inspection supports implementation claims, but does not verify rendered behavior. Name checks that could not run.

When part of better-interface, use its consolidated report only. Standalone reviews use one row per root cause, ranked by impact:

| Severity | Location | Before | After | Why | | --- | --- | --- | --- | --- |

Cite path/to/file:line and explain the user impact. HIGH breaks an interaction, makes motion unusable, or leaves a state change visible only during animation. MEDIUM is a consequential inconsistency in surfaces, icons, or motion. LOW is isolated polish.

End with Block when any HIGH remains, Approve otherwise, limited to the inspected scope. If there are no findings, say so and report verification.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.