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 Muminur/frontend-design-craft-skill --skill polishgit clone --depth 1 https://github.com/Muminur/frontend-design-craft-skillWrote 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/muminur/frontend-design-craft-skill/polish)<a href="https://agentmods.dev/skills/muminur/frontend-design-craft-skill/polish"><img src="https://agentmods.dev/badge/skills/muminur/frontend-design-craft-skill/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/muminur/frontend-design-craft-skill/polish"><img src="https://agentmods.dev/badge/skills/muminur/frontend-design-craft-skill/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 | $0.00115 | $0.02853 |
| Opus 5 | $0.00057 | $0.01426 |
| Sonnet 5 | $0.00023 | $0.00571 |
| Haiku 4.5 | $0.00012 | $0.00285 |
Grade A, and why
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 8d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Polish
The fastest way to tell whether a frontend was thought about or generated is to look at the type, the spacing, and the alignment. Color and content can be middling, but if these three are right, the page reads as professional. If they are wrong, no amount of motion or visual flair can rescue it.
Typography
Font selection
The single most overused font in AI-generated frontends is Inter. It is not a bad face — it is just the visual signature of generic. Reach for it only when nothing else fits.
Better defaults by context:
| Context | Sans options | Serif / display options | Mono options |
|---|---|---|---|
| Product UI, dashboards | Geist, IBM Plex Sans, Söhne (commercial), Hanken Grotesk | Source Serif 4 (for body) | JetBrains Mono, Geist Mono |
| Marketing, landing pages | General Sans, Satoshi, Cabinet Grotesk, Geist | Fraunces, Instrument Serif, Newsreader | Berkeley Mono (commercial) |
| Editorial, content-heavy | Inter Tight, Söhne, Söhne Breit | Source Serif 4, Newsreader, EB Garamond | Berkeley Mono, JetBrains Mono |
| Brand, expressive | Cabinet Grotesk, Boogy Brut, PP Editorial New | Fraunces (variable), PP Editorial New | — |
| Brutalist / raw | Helvetica, Inter (yes, here), Departure Mono | Times New Roman (yes, intentionally) | Departure Mono |
Pair a sans with a serif for editorial work. Pair a single high-quality sans with a mono for product work. Three families is the maximum; two is usually right.
Type scale
For product UI, use a fixed scale, never fluid. Fluid type makes app interfaces feel unstable across breakpoints — buttons resize, table headers shift, line lengths jump. Reserve fluid type for marketing/editorial.
A reliable product scale (modular, ratio ~1.2):
12px → captions, micro-labels
14px → secondary body, dense UI
16px → primary body, default
18px → emphasis body
20px → h4
24px → h3
30px → h2
36px → h1
A marketing scale can be more expressive (ratio ~1.333 or golden):
14, 16, 18, 24, 32, 48, 64, 96, 128
What ships with it
2 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.
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.
- 8d ago First seen · 222 lines · 115 tokens per session scan A eac948631e7e
polish is a skill published in the GitHub repository Muminur/frontend-design-craft-skill (4 stars, last pushed 3mo ago), licensed MIT. It adds 115 tokens to every session and 2,853 once invoked, about $0.0006 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.