design-skills
CLAUDE.md94 starsChanged 3 months agoMITView on GitHub
A collection of 10 UX/design skills for AI coding agents (Claude Code, Cursor, Codex, and others). Each skill is a set of markdown files that give AI tools deep knowledge of established design frameworks, heuristics, and methodologies. There is no build system, no tests, and no application code — this is a pure content repository. The repo ships through two distribution channels at once, from one copy of the content: Every skill lives under skills/ and follows the same structure:
In this repository10 other files it gives its agents.
- accessibility-auditSkill
- design-critiqueSkill
- design-elevationSkill
- design-opsSkill
- design-systemsSkill
- interaction-designSkill
- journey-mappingSkill
- ux-researchSkill
- ux-strategySkill
- ux-writingSkill
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 16
Every skill lives under skills/ and follows the same structure:
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md 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.
Files
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
What This Repo Is
A collection of 10 UX/design skills for AI coding agents (Claude Code, Cursor, Codex, and others). Each skill is a set of markdown files that give AI tools deep knowledge of established design frameworks, heuristics, and methodologies. There is no build system, no tests, and no application code — this is a pure content repository.
The repo ships through two distribution channels at once, from one copy of the content:
npx skills add cuellarfr/design-skills— the Vercel skills CLI, which walks the repo forSKILL.mdfiles. Works with Claude Code, Cursor, Codex, and 40+ other agents.- Claude Code plugin —
/plugin marketplace add cuellarfr/design-skills, then/plugin install design-skills@design-skills.
Skill Architecture
Every skill lives under skills/ and follows the same structure:
skills/skill-name/
├── SKILL.md # Main file (200-350 lines), standalone
├── references/ # Deep reference material, loaded on demand
├── templates/ # Fillable deliverable templates
└── examples/ # End-to-end walkthroughs and scenariosSKILL.md files use YAML frontmatter with name and description fields. The description is what agents use to decide when to load the skill.
name must be kebab-case and match the directory name. The skills CLI slugifies the frontmatter name to decide the installed directory, so a mismatch installs the skill under a different folder than the one it lives in here.
Plugin Packaging
.claude-plugin/ holds both manifests, and nothing else — per Claude Code's rules, skills/ must stay at the repo root, never inside .claude-plugin/.
.claude-plugin/plugin.json— plugin manifest.name: design-skillsis the namespace, so skills resolve as/design-skills:accessibility-audit..claude-plugin/marketplace.json— makes the repo its own single-plugin marketplace via"source": "./", so users can install without waiting on the community catalog.
Bump version in both files together when publishing; Claude Code only offers users an update when it changes.
Validate packaging changes with claude plugin validate . --strict, and confirm the CLI path still resolves all ten skills with npx skills add . --list.
The 10 Skills
ux-research, design-critique, accessibility-audit, journey-mapping, design-systems, ux-strategy, interaction-design, design-ops, ux-writing, design-elevation
Content Conventions
- Opinionated defaults — Specific numbers, benchmarks, and rubrics; not "consider..." language
- Actionable over theoretical — Every principle includes a concrete recommendation
- Before/after examples — Show what bad and good look like, with scoring
- Progressive depth — SKILL.md is comprehensive standalone; reference files go deeper
- Grounded in sources — Built from established books and frameworks, not invented heuristics
Other Files
index.html— GitHub Pages landing page (single-file, self-contained HTML/CSS/JS with dark mode support)README.md— Full skill descriptions and installation instructions.claude-plugin/— Plugin and marketplace manifests (see Plugin Packaging above)LICENSE— MIT
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
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.

