agentleFS
slidaysliday/google-fonts-skill/SKILL.md

google-fonts

Skill16 starsChanged 3 months agoMITView on GitHub

Google Fonts typography system generator. Suggests single fonts (strict mode) and font pairs (contrast mode) with complete typographic scales following Tailwind Typography rhythm concepts. Generates CSS custom properties, Tailwind config, and embed links. Trigger: "choose a font", "font pairing", "typography system", "type scale", "Google Font", "heading font", "body font", "web font", "font for my site", "typographic scale", "font suggestion", "which font", "font recommendation", "serif or sans".

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    MCP note: If the google-fonts MCP server is connected, prefer its tools — search_fonts, generate_typography_system, lookup_font, …

    line 30
  2. Very specific:

    Always use display=swap in Google Fonts embed

    line 117
  3. Distinctive:

    Prefer variable fonts (fewer HTTP requests, full weight flexibility)

    line 118
  4. Distinctive:

    Never suggest a single-weight font for body text

    line 119
  5. Distinctive:

    Verify Weight_Range covers needed weights before suggesting

    line 120
  6. Very specific:

    When a user says "show me examples", "pick a style for me", or "what would work for a SaaS app", read showcase/showcase.json and filter by …

    line 140

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Auto Google Font

Typography system generator for web projects using Google Fonts. Searches 1,923 fonts enriched with typographic personality tags (geometric, humanist, neo-grotesque, etc.), contrast levels, and body-suitability ratings. Generates complete typographic rhythm systems.

Data Files

  • data/fonts.csv — 1,923 Google Fonts with: Family, Category, Stroke, Personality, Expressive, Contrast, Width, Styles, Weight_Range, Variable, Variable_Axes, Body_Suitable, Quality_Tier (A/B/C), Popularity_Rank, Mood, Best_For, Keywords, Subsets, Google_Fonts_URL, CSS_Import
  • data/pairings.csv — 73 proven font pairings with contrast type and scale recommendations
  • data/scales.csv — 8 modular type scales with sizes, line-heights, letter-spacing, margins
  • references/typographic-rhythm.md — Scale math, line-height tiers, spacing rules
  • references/pairing-principles.md — Contrast theory, decision trees, superfamilies

Modes

MCP note: If the google-fonts MCP server is connected, prefer its tools — search_fonts, generate_typography_system, lookup_font, list_scales, list_pairings — over the scripts below. The scripts are the fallback for skill-only installs.

Single Font (Strict)

One font for headings AND body. Must have weight range covering 400+700. Body-suitable required.

python3 scripts/search.py "modern clean SaaS" --mode single
python3 scripts/search.py "geometric professional" --mode single --tier A

Font Pair (Contrast)

Two fonts with typographic contrast. Searches proven pairings first.

python3 scripts/search.py "elegant editorial luxury" --mode pair
python3 scripts/search.py "tech startup bold" --mode pair

Lookup & Scale

python3 scripts/search.py "Inter" --mode lookup        # full metadata for a named font
python3 scripts/search.py "marketing bold" --mode scale  # search type scales

Full System Output

Generate CSS + Tailwind + embed link from font selection + scale choice.

# Single font
python3 scripts/generate-css.py --font "Inter" --scale major-third --format all

# Font pair
python3 scripts/generate-css.py --heading "Playfair Display" --body "Inter" \
  --scale perfect-fourth --format all

# Custom weights and base size
python3 scripts/generate-css.py --heading "Space Grotesk" --body "DM Sans" \
  --heading-weights "400;700" --body-weights "300;400;500;700" \
  --scale minor-third --base 16 --format css

Workflow

  1. Understand context — Ask: product type, mood, content density, existing brand
  2. Search fonts — Run search.py with relevant keywords and mode
  3. Present top 3 — Show Family, Personality, Contrast, Quality Tier, Weight Range
  4. Generate system — Run generate-css.py with chosen font(s) and appropriate scale
  5. Deliver — Provide CSS custom properties, Tailwind config, and embed link

Quick Decision Guide

Project TypeModeScaleSuggested Search
SaaS / Dashboardsinglemajor-second"clean professional geometric"
Blog / Contentpairmajor-third"editorial readable"
Marketing / Landingpairperfect-fourth"bold modern confident"
Luxury / Fashionpairaugmented-fourth"elegant premium serif"
Documentationsingleminor-third"readable accessible humanist"
E-commercepairminor-third"clean friendly conversion"
Portfoliopairperfect-fourth"creative distinctive"
Enterprise / Govsinglemajor-second"trustworthy accessible corporate"

Scale Reference

ScaleRatioBest For
minor-second1.067Dense UI, dashboards
major-second1.125Apps, admin panels
minor-third1.2General purpose
major-third1.25Blogs, content
perfect-fourth1.333Marketing, editorial
augmented-fourth1.414Magazines, expressive
perfect-fifth1.5Display-heavy
golden-ratio1.618Hero sections

Pairing Contrast Types

  • Structure: Serif + Sans (safest, most contrast)
  • Proportion: Geometric sans + Humanist sans (subtle, modern)
  • Era: Old-style serif + Neo-grotesque sans (dramatic)
  • Weight: Single font family, different weights (simplest)

Quality Rules

  1. Always use display=swap in Google Fonts embed
  2. Prefer variable fonts (fewer HTTP requests, full weight flexibility)
  3. Never suggest a single-weight font for body text
  4. Verify Weight_Range covers needed weights before suggesting
  5. For body text: only suggest Body_Suitable=="Yes" fonts
  6. Tier A fonts first, then B, then C
  7. Include preconnect hints for fonts.googleapis.com and fonts.gstatic.com
  8. Max 3 font families per project (heading + body + optional mono)
  9. css2 URLs separate weights with semicolons (wght@400;700), ranges with .. (wght@100..900); commas are normalized, while malformed axes and dash ranges are rejected

Output Includes

  • CSS custom properties: font families, sizes, line-heights, letter-spacing, measure
  • Tailwind config: fontFamily, fontSize with lineHeight and letterSpacing
  • Google Fonts <link> embed with preconnect
  • Responsive breakpoint guidance

Showcase Gallery

100 pre-made typography systems applied to fictional projects. Browse at showcase/index.html or reference showcase/showcase.json for programmatic access.

When a user says "show me examples", "pick a style for me", or "what would work for a SaaS app", read showcase/showcase.json and filter by project type to suggest a pre-built system.

Regenerating

python3 scripts/generate-showcase.py

For detailed typographic theory, read references/typographic-rhythm.md. For pairing decision trees, read references/pairing-principles.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.