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 lihytaihe-lang/aetherpane --skill web-ui-polishgit clone --depth 1 https://github.com/lihytaihe-lang/aetherpaneWrote 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/lihytaihe-lang/aetherpane/web-ui-polish)<a href="https://agentmods.dev/skills/lihytaihe-lang/aetherpane/web-ui-polish"><img src="https://agentmods.dev/badge/skills/lihytaihe-lang/aetherpane/web-ui-polish/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/lihytaihe-lang/aetherpane/web-ui-polish"><img src="https://agentmods.dev/badge/skills/lihytaihe-lang/aetherpane/web-ui-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00028 | $0.03628 |
| Opus 5 | $0.00014 | $0.01814 |
| Sonnet 5 | $0.00006 | $0.00726 |
| Haiku 4.5 | $0.00003 | $0.00363 |
Grade A, and why
web-ui-polish 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 10d 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 — 419 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Turn rough or ugly web pages into polished, premium interfaces with strong structure, spacing, typography, restrained motion, thoughtful media usage, and selective use of glass surfaces.
Use When
- The user wants a page to look better, more premium, more polished, more modern, more Apple-inspired, or more structured
- The task involves landing pages, showcase pages, dashboard shells, settings pages, component galleries, or case-study pages
- The task is web-only
- The task should preserve existing business logic while upgrading presentation quality
Do Not Use When
- The task is backend-only
- The task is unrelated to presentation or page quality
- The task is for native apps or non-web UI
- The user explicitly wants a raw utility layout with no polish pass
Workflow
- Inspect the current page or requested page type
- Identify the page job before proposing visual changes
- Fix structure first: section order, hierarchy, spacing, density, and focus
- Apply an appropriate page pattern based on page type
- Add surface treatment only where it improves hierarchy
- Add media only where it improves storytelling or comprehension
- Add restrained motion only after structure and readability are solid
- Ensure responsive behavior and maintainable code structure
- Review consistency across spacing, radii, borders, shadows, and transitions
- Verify that the result still feels like one system rather than a collage of tricks
Design Rules
- Avoid cheap glassmorphism
- Favor premium spacing and calm typography
- Use Apple-inspired module rhythm, not imitation for its own sake
- Keep content readable
- Prefer one focal point per section
- Keep visual systems consistent across the page
- Use large media sparingly and intentionally
- Treat media containers as part of the design system
- Use motion to reinforce hierarchy and continuity
- Reserve strong contrast shifts for actions and important state changes
- Let page type drive pattern choice before decoration choices
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- COLLABORATION.md 11 KB
- collaboration/agent-profiler.cjs 3.8 KB runs code
- collaboration/agent-profiles.json 2.2 KB
- collaboration/README.md 4.1 KB
- collaboration/task-allocator.cjs 3.4 KB runs code
- collaboration/workflow-optimizer.cjs 5.4 KB runs code
- critique/critique-engine.cjs 23 KB runs code
- critique/README.md 5.7 KB
- critique/report-generator.cjs 14 KB runs code
- critique/templates/html-report.html 5.1 KB
- critique/templates/markdown-report.md 302 B
- critique/visualizer.cjs 9.6 KB runs code
- DESIGN_INTELLIGENCE.md 16 KB
- evolution/diff-analyzer.cjs 8.0 KB runs code
- evolution/pattern-extractor.cjs 9.9 KB runs code
- evolution/README.md 2.3 KB
- evolution/reports/.gitkeep 0 B
- evolution/tracker.cjs 12 KB runs code
- examples/dashboard-classic.html 3.6 KB
- examples/dashboard-signal.html 3.6 KB
- examples/landing-classic.html 3.5 KB
- examples/landing-editorial.html 3.8 KB
- examples/landing-signal.html 3.1 KB
- examples/settings-signal.html 5.0 KB
- examples/showcase-editorial.html 4.0 KB
- learning-data/bad-examples/.gitkeep 0 B
- learning-data/bad-examples/README.md 793 B
- learning-data/comparison-pairs/.gitkeep 0 B
- learning-data/comparison-pairs/README.md 708 B
- learning-data/good-examples/.gitkeep 0 B
- learning-data/good-examples/README.md 591 B
- patterns/card-patterns/feature-grid.json 2.4 KB
- patterns/card-patterns/pricing-table.json 3.1 KB
- patterns/card-patterns/testimonial-carousel.json 2.3 KB
- patterns/compose.cjs 7.2 KB runs code
- patterns/hero-patterns/centered-cta.json 2.0 KB
- patterns/hero-patterns/split-content.json 2.4 KB
- patterns/hero-patterns/video-background.json 2.0 KB
- patterns/layout-patterns/bento-box.json 2.5 KB
- patterns/layout-patterns/masonry-grid.json 2.7 KB
- patterns/layout-patterns/sidebar-content.json 2.3 KB
- patterns/pattern-registry.json 1.2 KB
- patterns/README.md 5.2 KB
- resources/checklist.json 5.9 KB
- resources/component-recipes.md 12 KB
- resources/layout-rules.md 9.0 KB
- resources/media-recipes.md 4.8 KB
- resources/motion-recipes.md 4.4 KB
- resources/repair-heuristics.md 6.7 KB
- resources/style-guide.json 3.9 KB
- resources/surface-rules.md 4.7 KB
- resources/theme-personalities.json 4.2 KB
- resources/tokens.json 3.2 KB
- resources/typography-rules.md 5.0 KB
- scripts/design-critique.cjs 9.3 KB runs code
- scripts/validate-a11y.cjs 4.1 KB runs code
- scripts/validate-html.cjs 3.2 KB runs code
- scripts/validate-tokens.cjs 4.2 KB runs code
- tools/cli.cjs 13 KB runs code
- tools/README.md 2.6 KB
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.
- 10d ago First seen · 419 lines · 28 tokens per session scan A b5ee5e5bb31c
web-ui-polish is a skill published in the GitHub repository lihytaihe-lang/aetherpane (3 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 3,628 once invoked, about $0.0001 per session on Opus 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 2026-08-31.
Other skills, from other repositories
brand-visual-language
A brand's visual tone — playful or serious, rounded or angular — should be consistent across all UI elements. Shape language in typography, border-radius, and iconography communicates personality before a single word is read. Use when establishing a design system, choosing icon libraries, setting border-radius tokens…
loading-states-and-perceived-performance
Manage user expectations during wait times with appropriate loading states — from simple spinners to complex skeleton screens and staggered animations. Perceived performance is often more important than actual load time. Use when designing data-heavy components, handling API calls, building hero sections, or improving…
micro-interactions
Micro-interactions are small, purposeful animations and responses that reward the user and make the interface feel alive — an animated icon, a satisfying toggle, a subtle reveal. Borrowed from the natural world, they add delight without distraction. Use when designing interactive components, success states, toggles…
motion-and-storytelling
Disney's 12 animation principles, cinematic storytelling techniques, and comic book conventions apply to web UI — used subtly, they make interfaces feel alive, intentional, and emotionally resonant. Use when designing transitions, micro-interactions, onboarding flows, scroll animations, or any motion in the UI.
responsive-paradigms
Mobile, tablet, and desktop are different interaction paradigms — not the same layout scaled up or down. Sections can be hidden, repositioned, or made sticky on mobile. Navigation and primary actions move. Use when designing responsive layouts, adapting desktop UI for mobile, or deciding what to show on each…
elevation-and-depth
Elevation — subtle shadows and layering — communicates visual hierarchy by lifting elements above the surface. Combined with border-radius, it creates the tactile quality of cards, modals, and interactive surfaces. Use when designing cards, dropdowns, modals, tooltips, or any floating UI element.