design
Skill0 starsChanged 13 days agoMITView on GitHub
The craft bar for UI work — tokens, layout, motion, states, and the design doc that must match the code. Use when building, editing, or reviewing any interface, or when deciding whether a UI change is finished.
197 other projects use a version of this.
Adopted by
Most recently taken up by
- dialog-db/dialog-dbtheir own version, first seen Nov 9, 2026
- BermanRoman/promt-seo-geotheir own version, first seen Nov 8, 2026
- anorth/agent-skillstheir own version, first seen Nov 8, 2026
- gspencergoog/skillstheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- Integralist/agent-skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use banner-design, ui-styling and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
seikaikyoSkillbanner-design
Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist, gradient, bold typography, photo-based, illustrated, geometric, retro, glassmorphism, 3D, neon, duotone, editorial, collage.
Also in 38 projects that use this
MicrosoftSkillui-styling
Guide for the visual style, structure, and shared building blocks used by Semantic Link Labs interactive UI tools (HTML widgets and anywidget-based widgets). Use this when adding a new interactive UI, modifying an existing one, or adding shared visual components.
Also in 39 projects that use this
seikaikyoSkillbrand
Brand voice, visual identity, messaging frameworks, asset management, brand consistency. Activate for branded content, tone of voice, marketing assets, brand compliance, style guides.
Also in 43 projects that use this
mayankjain1815-commitsSkillinfra-audit
Reads docker-compose, env files, ORM configs, and connection strings to map current infrastructure. Flags missing layers (cache, queue, analytics) based on observed access patterns. Outputs a structured infrastructure manifest.
Also in 3 projects that use this
JetBrainsSkillslides
Create and edit presentation slide decks (`.pptx`) with PptxGenJS and render/validation utilities. Use when tasks involve building a new PowerPoint deck, recreating slides from screenshots/PDFs/reference decks, modifying slide content while preserving editable output, adding charts/diagrams/visuals, or diagnosing layout issues such as overflow, overlaps, and font substitution.
Also in 42 projects that use this
AnthropicSkilldesign-system
Audit, document, or extend your design system. Use when checking for naming inconsistencies or hardcoded values across components, writing documentation for a component's variants, states, and accessibility notes, or designing a new pattern that fits the existing system.
Also in 49 projects that use this
Other versions197 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 197
- nextlevelbuilder/ui-ux-pro-max-skill★ 147ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- tokio-rs/toasty★ 3.3ksame name
- PaulWoitaschek/Voice★ 3.3ksame name
- joye61/pic-smaller★ 2.9ksame name
- oxsecurity/megalinter★ 2.6ksame name
- Infisical/agent-vault★ 2.5ksame name
- static-web-server/static-web-server★ 2.4ksame name
- SethGammon/Citadel★ 927same name
- Ohh-889/skyroc-admin★ 795same name
187 more not listed
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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-rulesSkill
- code-discoverySkill
- project-scaffoldSkill
- repo-alignSkill
- repo-auditSkill
- repo-initSkill
- skills-installSkill
- standardSkill
- verify-changeSkill
- workflowSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 174 edited versions we read keep these.
1
Distinctive
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
- Distinctive: line 23
What is the one thing on this screen?: If there are two, one is the page and one is a card.
- Very specific: line 96
When the project has no design system yet: create docs/design-system.md with the tokens, and put the first DESIGN.md beside the first real …
“Common” is measured: kept by at least 6 in 10 of the 174 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Design
What "finished" means for an interface, and the documents that keep it true. The bar is not taste — every item below is checkable.
This is the generic craft bar. A project with its own design system overrides the tokens; it does not override the states, the craft checks, or the design-doc rule.
The five questions before any UI code
Answer these in the reply, one line each. If any answer is "whatever looks fine", that is the decision to make first.
- Who is looking, and at what size? Phone at arm's length, laptop at a desk, a TV across a room. It changes the type scale, not just the breakpoints.
- What is the one thing on this screen? If there are two, one is the page and one is a card.
- What is the page's job in one verb? Browse, compare, confirm, edit, monitor. The verb picks the layout.
- What is the empty, loading, error, and done state? Four states per surface, not one.
- What existing component or token does this reuse? Copy the nearest existing surface. A new shape must earn itself.
The craft bar
Each row is verifiable by looking. Full explanations and the anti-pattern behind each:
CRAFT-BAR.md.
| Area | The bar | Fails when |
| Tokens | Every colour, radius, font size, and spacing value comes from the token layer | A hex code, a 13px, a magic 17px padding |
| Type | Three roles at most: display, body, mono. A deliberate scale | Five sizes between 14 and 18 |
| Spacing | One scale, applied on a rhythm | 4/6/8/10/12 all used for the same kind of gap |
| Hierarchy | Exactly one thing is loudest; the eye has a path | Everything bold, everything a card, everything accented |
| States | Empty, loading, error, success — designed, not defaulted | Bare "Loading…" text; an empty table with no explanation |
| Density | Rows and cards sized for their content, consistently | Mixed row heights in one list |
| Motion | Motion explains a change in state; 120–250ms; respects reduced-motion | Decorative animation, or a 600ms fade on every element |
| Interaction | Every clickable thing has hover, focus-visible, active, disabled | Focus ring removed with no replacement |
| Copy | Concrete, verb-first, sentence case, no filler | "Submit", "Oops!", "Something went wrong" |
| Responsive | Real content at 360/768/1280; no horizontal scroll; 44px touch targets | A desktop layout squeezed |
States are the work
Most unfinished UI is missing states, not missing polish. For every surface that fetches or mutates:
| State | Must show |
| Empty | Why it is empty and the one action that fills it |
| Loading | A skeleton matching the final layout, or a spinner in place — never bare text |
| Error | What failed, in the user's words, and a retry |
| Partial | What loaded and what did not, in that order |
| Success | The new state, not a toast that vanishes before it is read |
| Disabled | Why it is disabled, visible without hovering |
A loading state that changes the layout when it resolves is a bug, not a rough edge.
The design doc rule
A component is not done until its DESIGN.md matches. The doc is not a write-up after the
fact; it is the contract the next change checks against.
Per component or surface, DESIGN.md holds:
---
tokens: [surface-1, text-primary, accent, radius-md]
states: [empty, loading, error, success]
---
## Purpose
One sentence: what this is for and where it appears.
## Anatomy
The parts, and which are optional.
## Contract
Props, variants, and what each variant is for.
## Tokens consumed
The exact names, from the token layer.
## Not for
The adjacent case this should not be used for.Plus one row in the component index (map) so the doc is findable. A component whose tokens changed without its doc changing is a review finding, not a nit.
When the project has no design system yet: create docs/design-system.md with the tokens, and put
the first DESIGN.md beside the first real component. Do not write thirty design docs for zero
components.
Reviewing UI
Two axes, reported side by side:
- Craft — the table above, checked by looking at a rendered screen.
- Contract — the design doc and tokens match the code; states exist; the change did not invent a new pattern where one existed.
A review that never rendered the UI is a code review, and should say so.
Anti-patterns at a glance
- Accent colour used for more than one purpose on a screen.
- A card inside a card inside a card.
- Icons without labels where the icon is not universal.
- A toast as the only confirmation of a destructive action.
- Text contrast below 4.5:1 for body copy.
- A modal for something that could be inline.
- Three different border radii in one view.
- Motion on hover for every element, so nothing reads as interactive.
Related
- The full reasoning per area →
CRAFT-BAR.md - Design docs in a monorepo → skill
project-scaffold→targets/monorepo.md - Proving a UI change → skill
verify-change§ UI changes
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.

