front-end-design
Skill2 starsChanged 5 months agoMITView on GitHub
Use when designing a new UI, redesigning a screen, building a landing/marketing page, or making something look better. Orchestrates the visual-craft skills (tailwind-discipline, typography, animation-discipline, image-generation, creative-web). Round 9 C.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- kevinph4n/skillstheir own version, first seen Nov 8, 2026
- subhash-arabhi/saas-playbooktheir own version, first seen Nov 1, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- kevinph4n/skills★ 1same name
- subhash-arabhi/saas-playbook★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository60 other files it gives its agents.
- .claude/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- analyzeSkill
- animation-disciplineSkill
- api-versioningSkill
- autopilotSkill
- browser-e2eSkill
- characterizeSkill
- clarifySkill
- codemodSkill
- constitution-compactSkill
- constitutionSkill
- context-budgetSkill
- creative-webSkill
- db-migrationSkill
- debugSkill
- detect-stackSkill
- dispatch-criteriaSkill
- dreamSkill
- experimentSkill
- fastapiSkill
- flag-cleanupSkill
- flag-rolloutSkill
- flask-realtimeSkill
- framework-detectorSkill
- grill-meSkill
- handoffSkill
- image-generationSkill
- implementSkill
- initiativeSkill
- instinctSkill
- loopSkill
- nextjsSkill
- observabilitySkill
- okr-alignSkill
- parallel-swarmSkill
- pivotSkill
- planSkill
- pr-bodySkill
- prime-disciplineSkill
- prod-observabilitySkill
- react-nodeSkill
- react-viteSkill
- release-trainSkill
- researchSkill
- reviewSkill
- security-guardSkill
- self-healSkill
- shipSkill
- skill-creatorSkill
- specifySkill
- tailwind-disciplineSkill
- tasksSkill
- tdd-loopSkill
- token-budgetSkill
- typographySkill
- verify-loopSkill
- verifySkill
- wip-checkpointSkill
- <kebab-case-skill-name>Skill
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
- Distinctive: line 24
Sketch with components: before pixels. List the components and their hierarchy.
- Very specific: line 42
Design tokens from
tokens.ts: No magic hex codes, no inline arbitrary values without comment. - Very specific: line 44
Dark mode is default-on: Use Tailwind class strategy + semantic tokens (--surface-1, NOT gray-900).
- Distinctive: line 46
No AI-slop placeholders: Every visual choice ties to the spec's user story or concept.
- Distinctive: line 51
Default Tailwind blues + grays everywhere
- Very specific: line 59
If a spec explicitly says "high-artistic, modern, creative" or "stunning landing page" or similar, hand off to designer agent …
≈ “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.
Files
Front-End Design
Mandate
Force a CONCEPTUAL DIRECTION before styling. The output should look intentional, not "generated default Tailwind." Apply Anthropic's Artifact aesthetic: clean, opinionated, content-forward.
Procedure
- State the concept FIRST (one paragraph in the spec):
- Mood: editorial / brutalist / maximalist / retro-futuristic / minimalist / art-deco / playful
- Voice: serious / friendly / technical / approachable
- Hero archetype: dashboard / marketing / app / form / data / playground
- Reference site(s) for inspiration
- Read design tokens from
src/styles/tokens.ts(or Tailwind config). Add missing tokens to the file FIRST, then use them — no inline arbitrary values. - Sketch with components before pixels. List the components and their hierarchy.
- Required states per screen (no "lonely success state"):
- loading
- empty
- error
- partial-data
- success
- Responsive breakpoints: mobile-first; sm/md/lg/xl/2xl. Design at 375px AND 1440px minimum.
- Apply sister skills:
tailwind-discipline— utility class hygienetypography— type scale + measureanimation-discipline— motion designimage-generation— when raster/illustration neededcreative-web— when "wow factor" justified
Hard rules
- Concept BEFORE styling. "Modern minimal" is not a concept — that's a default.
- Design tokens from
tokens.ts. No magic hex codes, no inline arbitrary values without comment. - Required states. Loading / empty / error / success are non-negotiable.
- Dark mode is default-on. Use Tailwind
classstrategy + semantic tokens (--surface-1, NOTgray-900). - a11y is invariant. Axe-core in CI must pass (Round 8 audit proposed this).
- No AI-slop placeholders. Every visual choice ties to the spec's user story or concept.
Anti-patterns (immediate reject)
- Lorem ipsum in shipped UI
- Default Tailwind blues + grays everywhere
- 1000px-wide text lines (no
max-w-prose) - Fixed pixel font sizes everywhere (no responsive scale)
- Hover states without focus states (a11y fail)
- Animations without
prefers-reduced-motionopt-out
When to delegate to designer agent
If a spec explicitly says "high-artistic, modern, creative" or "stunning landing page" or similar, hand off to designer agent (.claude/agents/specialists/designer.md) — they own this skill family and can iterate.
Done means
- Concept statement documented in spec
- Required states all implemented
- Mobile + desktop both look intentional
- Axe + Lighthouse pass
- Reviewer signs off on visual craft, not just code correctness
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.

