Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Typography Expert

ASecurity

Master typographic craft with type selection, pairing, scale, spacing, and readability best practices.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsgo

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill typography-expert --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Typography Expert?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Typography Expert
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-typography-expert/badge)](https://www.skillsdirectory.com/skills/aicodedecode-typography-expert)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: typography-expert
description: Master typographic craft with type selection, pairing, scale, spacing, and readability best practices.
category: creative-design
---

## Overview

Typography is 90% of most designs' visual voice — and the difference between
amateur and
professional work is rarely the font choice but the spacing, scale, and
discipline. This skill
covers type selection, pairing, hierarchical scale, micro-typography (kerning,
leading, measure),
and readability across print and screen.

## When to use

- Choosing and pairing typefaces for a brand or project

- Building a typographic scale and hierarchy

- Fixing typography that feels "off" but you can't say why

- Setting long-form text for readability (articles, reports, books)

- Reviewing designs for typographic quality

## Core concepts

- - - **Pairing: contrast with harmony.** Pair typefaces that contrast in one
  dimension (serif/sans,
  geometric/humanist) but share another (x-height, proportions). The safest
professional pairing:
  one distinctive display face + one workhorse text face.
- - - **The type scale.** A modular scale (e.g., 1.25 ratio:
  12/15/19/23/29/36/45) creates harmonious
  size relationships. Define roles (display, h1-h4, body, caption) with size,
weight, and
  line-height — then never deviate.
- - - **Line height and measure.** Body text: line-height 1.4-1.6, measure (line
  length) 45-75
  characters. Too tight suffocates; too loose disconnects lines. Headlines can
go tighter (1.0-1.2).
- - - **Micro-typography.** Kerning (space between specific pairs, especially in
  headlines), tracking
  (overall letter-spacing — tighten headlines slightly, loosen small
caps/uppercase), and optical
  alignment (punctuation hangs outside the margin).
- - - **Hierarchy through contrast.** Size, weight, color, and spacing create
  levels. Adjacent levels
  need clear contrast — if h2 and h3 look similar, the hierarchy has failed.
When in doubt,
  exaggerate the difference.
- - - **Readability rules.** Left-aligned body text (never justified on screen —
  it creates rivers),
  adequate contrast (4.5:1 minimum), one idea per paragraph, and hyphenation off
for narrow columns.

## Practical workflow

1. 1. 1. **Define the typographic job.** Brand personality, content types
   (headlines? long-form?
   data?), contexts (screen, print, both?). The job determines the requirements.
2. 2. 2. **Select the text face first.** The workhorse matters most — it carries
   90% of words. Test
   candidates with real content at real sizes: does it stay readable at 14px?
Does it have the
   needed weights and italics?
3. 3. 3. **Choose the display face.** Personality lives here. Ensure it
   contrasts with the text face in
   a controlled way and works at large sizes (check distinctive letters: g, a,
R).
4. 4. 4. **Build the scale.** Define every role with
   size/weight/line-height/letter-spacing. Test the
   full scale on a real page — headlines through captions — before finalizing.
5. 5. 5. **Set the details.** Kerning on headlines and logos (check AV, To, Wa
   pairs), hanging
   punctuation, proper dashes (— em, – en, - hyphen), curly quotes, and tabular
figures for data.
6. 6. 6. **Stress-test.** Long paragraphs, short labels, all-caps treatments,
   tiny captions, dark mode.
   Fix widows/orphans, awkward breaks, and any size where the hierarchy
collapses.
7. 7. 7. **Document the system.** A one-page type spec: faces, scale table,
   usage rules, and don'ts.
   Typography systems die when the next person guesses.

## Common pitfalls

- - - **Too many typefaces.** Each additional face dilutes the voice. Two is the
  professional
  standard; three needs justification.
- - - **System fonts by default.** Nothing wrong with system fonts functionally,
  but they're the
  typographic equivalent of a blank wall — fine, forgettable, and sometimes
exactly right for
  native-feeling UI.
- - - **Ignoring line height.** Default line-heights (usually 1.2) are too tight
  for body text. This
  single fix improves more designs than any font swap.
- - - **Fake styling.** Faux bold/italic (browser-synthesized) instead of real
  weights. If the face
  lacks a true bold, pick a different face.
- - - **Centered paragraphs.** Centered body text destroys readability — the eye
  can't find the next
  line start. Center headlines only.
- - - **Widows and orphans.** Single words stranded on the last line, or single
  lines stranded at
  column tops. Fix with non-breaking spaces or subtle rewording — details
readers feel but never
  notice.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →