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 curiositech/some_claude_skills --skill typography-expertgit clone --depth 1 https://github.com/curiositech/some_claude_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/curiositech/some_claude_skills/typography-expert)<a href="https://agentmods.dev/skills/curiositech/some_claude_skills/typography-expert"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/typography-expert/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/curiositech/some_claude_skills/typography-expert"><img src="https://agentmods.dev/badge/skills/curiositech/some_claude_skills/typography-expert.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
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 | $0.00213 | $0.08693 |
| Opus 5 | $0.00106 | $0.04346 |
| Sonnet 5 | $0.00043 | $0.01739 |
| Haiku 4.5 | $0.00021 | $0.00869 |
Grade A, and why
typography-expert 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 — 448 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Typography Expert
Written by someone who picks type for a living. The goal of this skill is breadth and taste, not a blessed shortlist. There is never one right typeface — there is a right register, and several good faces that hit it at different budgets. If you reach for the same four fonts every time, you are not choosing; you are defaulting. Stop defaulting.
When to Use This Skill
✅ Use for:
- Font selection and pairing driven by mood / era / industry / register, not by habit
- Typographic hierarchy and tokens for design systems
- Type scales (modular ratios, fluid
clamp()) - Variable-font integration and axis control (
wght,wdth,opsz,slnt,GRAD) - Web-font performance (subsetting,
font-display, self-host vs CDN,size-adjustfallback metrics to kill CLS) - OpenType feature implementation (ligatures, small caps, numerals, stylistic sets)
- Licensing decisions (OFL vs commercial EULA; desktop/web/app; trial fonts)
- Accessibility for type (WCAG contrast, minimum sizes, zoom, line/letter spacing)
- Dark-mode typographic compensation
- Multilingual support (RTL, CJK, diacritics, character-set coverage)
❌ Do NOT use for:
- Logo or wordmark creation → design-system-creator
- Icon fonts / icon systems → web-design-expert (use SVG, not icon fonts)
- General CSS unrelated to type
- Image-based or rasterized lettering → different domain
- Brand naming or strategy → this is visual implementation
- Kinetic/motion typography → native-app-designer
0. Retire the Defaults (read this first)
These faces are not bad. They are exhausted — reached for reflexively, so they signal "a machine or a hurried human picked this," not "someone chose this." If a brief has no reason to use one of these, don't. For each: one sentence on why it's a cliché, then two fresher faces that fill the same role.
| Overused face | Why it reads as a cliché | Reach for instead |
|---|---|---|
| Inter (Rasmus Andersson, OFL) | The default UI sans of the entire 2018–2025 web; competent and invisible to the point of anonymity. | Hanken Grotesk (Alfredo Marco Pradil, OFL — warmer humanist UI sans) · Public Sans (USWDS, OFL — neutral but distinct) · paid: Söhne is also now overused; try Untitled Sans (Klim) instead. |
| Roboto (Christian Robertson, Apache) | Android's system font; "I used whatever was already loaded." | Schibsted Grotesk (Bakken & Bæck, OFL) · Onest (OFL) |
| Open Sans (Steve Matteson, Apache) | The 2013 "safe corporate" sans; reads as a CMS template. | Source Sans 3 (Paul Hunt / Adobe, OFL) · IBM Plex Sans (Bold Monday for IBM, OFL) |
| Montserrat (Julieta Ulanovsky, OFL) | Geometric "startup deck" sans, over-set at heavy weights everywhere. | Hanken Grotesk · paid: Aktiv Grotesk (Dalton Maag) or GT America (Grilli Type) |
| Poppins (Indian Type Foundry, OFL) | The "friendly app" geometric circle-o sans of a thousand landing pages. | Gabarito (OFL, geometric with character) · Figtree (OFL) · paid: Visby (Connary Fagen) |
| Lato (Łukasz Dziedzic, OFL) | 2010s humanist default; pleasant, forgettable. | Instrument Sans (Rodrigo Fuenzalida + Jordan Egstad, OFL) · Mona Sans (GitHub, OFL) |
| Helvetica / Helvetica Neue (Linotype) | "Neutral" became a cliché the moment everyone agreed it was neutral; also a paid license many fake with Arial. | Neue Haas Grotesk (the real thing, Linotype/Monotype) if you must; or pivot to a grotesque with grit: GT America (Grilli Type), ABC Diatype (Dinamo). Libre swap: Archivo (Omnibus-Type, OFL). |
| Fraunces (Undercase Type, OFL) | The "soft serif with the wonky g and opsz axis" that became the indie-SaaS display serif. | Newsreader (Production Type, OFL — has opsz too, far less seen) · paid: Signifier (Klim) or Domaine (Klim) for high-contrast display. |
| Geist (Vercel, OFL) | Ships with every Next.js starter; "I scaffolded this an hour ago." | Sans: Mona Sans / Hubot Sans (GitHub, OFL) or Hanken Grotesk. Mono: Commit Mono (OFL) or Martian Mono (OFL). |
| Söhne (Klim) | The premium-newsletter / AI-company house sans of 2021–present (you've seen it on a dozen "we raised a Series A" pages). | Other Klim grotesques: Untitled Sans or National 2; or off-Klim: ABC Diatype (Dinamo), Aeonik (CoType). |
| Fontshare / ITF "starter pack" — Satoshi, General Sans, Clash Display, Cabinet Grotesk, Switzer, Space Grotesk (Indian Type Foundry, free) | Free + slick + on every dribbble shot since 2021; "Clash Display + Satoshi body" is now a look, not a choice. | Clash Display → Bricolage Grotesque (Mathieu Triay, OFL) or Anybody/Big Shoulders (OFL) for display · Satoshi/General Sans → Hanken Grotesk, Schibsted Grotesk, Instrument Sans · Space Grotesk → Departure Mono / Space Mono is fine but tired; try Spline Sans or Familjen Grotesk (OFL). |
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.
- 8d ago First seen · 448 lines · 213 tokens per session scan A d1cdedc634b2
typography-expert is a skill published in the GitHub repository curiositech/some_claude_skills (221 stars, last pushed 5d ago), licensed MIT. It adds 213 tokens to every session and 8,693 once invoked, about $0.0011 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 2026-09-03.
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.