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 digital-stoic-org/agent-skills --skill ux-polishgit clone --depth 1 https://github.com/digital-stoic-org/agent-skillsWrote 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/digital-stoic-org/agent-skills/ux-polish)<a href="https://agentmods.dev/skills/digital-stoic-org/agent-skills/ux-polish"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/ux-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/digital-stoic-org/agent-skills/ux-polish"><img src="https://agentmods.dev/badge/skills/digital-stoic-org/agent-skills/ux-polish.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 5 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00081 | $0.02039 |
| Opus 5 | $0.00041 | $0.01019 |
| Sonnet 5 | $0.00016 | $0.00408 |
| Haiku 4.5 | $0.00008 | $0.00204 |
Grade A, and why
ux-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 12d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UX Polish
Workflow
-
Parse
$ARGUMENTS→{subcommand}+{target}+ options. Default subcommand =polish. Missing target → AskUserQuestion. -
Resolve target — in order:
- Exact file path → use directly
- Directory path → Glob
*.htmlin it - Subject name → Glob
dev/ux/wireframes/{target}/*.html - Nothing found → AskUserQuestion
-
Load context:
- Glob
dev/ux/design-system.yaml→ read design tokens (required forcolorize/polish) - Glob
biz/ux/empathy-map-{subject}.md→ emotional tone hints (optional) - Missing design system on
polish/colorize→ AskUserQuestion or create defaults
- Glob
-
Read HTML — Read each target file. Assess current state.
-
Execute subcommand — Read
references/design-rules.mdfirst, then apply per subcommand:
Analysis subcommands (read-only)
| Subcommand | Action | Reference sections |
|---|---|---|
audit |
Report all design issues: contrast failures, spacing inconsistencies, anti-pattern violations (§3), heuristic violations (§10). Output structured markdown report grouped by severity. | §1-3, §10 |
critique |
Opinionated design suggestions with priority ranking. Like audit but prescriptive — "increase CTA size by 20%", "add shadow to separate card from background". Include rationale from Gestalt/hierarchy principles. | §1-3, §10 |
Modification subcommands (write files)
| Subcommand | Focus | What to apply | Reference sections |
|---|---|---|---|
polish |
Full pass — the "do everything" command | Typography + color + spacing + motion + interaction + responsive. Apply all rules. | All sections |
colorize |
Color only | Read design-system.yaml palette. Apply color harmony algorithm (§5): analogous secondary, complementary accent, tinted neutrals, semantic colors. Test WCAG AA contrast. Apply 60-30-10 rule. | §5, §3 color anti-patterns |
typeset |
Typography only | Font pairing (serif+sans), modular scale, line-height per size, measure (45-75ch body, 20-35ch hero), tracking, OpenType features (tabular-nums, small-caps, hanging-punctuation), baseline grid. | §4, §3 typography anti-patterns |
space |
Spacing only | Apply 4px scale system. Fix Gestalt Proximity violations (space within group < space between groups). Vertical rhythm. White space hierarchy (micro/meso/macro). Section breathing room. | §6, §1 Gestalt, §2 White Space |
animate |
Motion only | Add CSS transitions: hover states (100-150ms ease-out), focus-visible, enter/exit animations (ease-out/ease-in), stagger siblings (+50ms), skeleton loading. Include prefers-reduced-motion. |
§7, §8 interaction states |
adapt |
Responsive only | Mobile-first breakpoints (375/768/1024/1440). Container queries. Touch targets 44px. Thumb zone. Stack columns on mobile. Fluid typography with clamp(). Max content width 1200px. | §9 |
bolder |
Increase assertiveness | Increase type scale ratio, strengthen contrast, enlarge CTAs, add bolder shadows, increase font-weight on headings, more saturated primary color. Push Von Restorff effect. | §2 hierarchy, §4, §5 |
quieter |
Reduce visual noise | Desaturate palette toward monochromatic, increase whitespace, reduce border-radius variation, soften shadows, lighter font-weights on non-critical elements, remove decorative elements. | §2 hierarchy, §5 monochromatic, §6 macro whitespace |
delight |
Add micro-delights | Subtle hover animations beyond defaults, success state celebrations (checkmark animation), empty state illustrations/messages, loading skeleton with brand-tinted pulse, stagger entrance on list items. | §7 motion, §8 affordance, §11 UX writing |
extract |
Reverse-engineer design system | Parse all CSS values from HTML. Identify color palette, font families, spacing values, border-radius values. Detect inconsistencies (ad-hoc values). Generate dev/ux/design-system.yaml with detected tokens. Report deviations. |
§12 |
What ships with it
1 file 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.
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.
- 12d ago First seen · 100 lines · 81 tokens per session scan A d0d3056de195
ux-polish is a skill published in the GitHub repository digital-stoic-org/agent-skills (20 stars, last pushed 6d ago), licensed MIT. It adds 81 tokens to every session and 2,039 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
chakra-ui-builder
Build responsive, accessible UI components and layouts using Chakra UI v3, install or configure Chakra UI in new and existing projects, and design scalable themes using tokens, semantic tokens, recipes, and slot recipes. Use this skill whenever a user asks to build, create, or generate any UI component, page, form…
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
frontend-ui-dark-ts
Build dark-themed React applications using Tailwind CSS with custom theming, glassmorphism effects, and Framer Motion animations. Use when creating dashboards, admin panels, or data-rich interfaces with a refined dark aesthetic.
reveal-hover-effect
Build cursor-following spotlight reveals that expose a second aligned image through a soft radial mask. Use for hover-to-color, before-and-after, x-ray, material, texture, product-detail, and illustrated hero effects where a desaturated or embossed base image should remain visible while another treatment follows an…
frontend-visual-qa
Audits already-rendered web, landing-page, HTML deck/slide, browser tool/game, dashboard/admin, design-system, and desktop UIs using real-browser or native-app journeys, inspected screenshots, DOM geometry, responsive or projection viewports, and a bundled Playwright sweep. Use after UI implementation to find…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.