ui-taste
Skill1 starsChanged 6 days agoMITView on GitHub
Give your coding agent better UI taste. Build and polish web and iOS interfaces with Uizze's anti-ui-slop playbooks and optional real-product references. Use for UI design, implementation, redesign, critique, or a final visual review in Claude Code, Codex, Cursor, or Copilot.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- Lu1sDV/skillsmdword for word, first seen Nov 8, 2026
- milad-ahmd/agent-skillstheir own version, first seen Nov 8, 2026
Other versions2 projects use a version of this.
Word for word · 1
- Lu1sDV/skillsmd★ 2100% same
Edited · 0
None found.
Wrote their own version · 1
- milad-ahmd/agent-skills★ 5same 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- angular-developerSkill
- cavemanSkill
- find-animation-opportunitiesSkill
- frontend-designSkill
- grillingSkill
- grill-meSkill
- impeccableSkill
- improve-animationsSkill
- web-design-guidelinesSkill
- angular-doctorSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 90
Keep the handoff concise: what changed, what was actually tested, and any remaining limitation.
≈ “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
Image: Stop Making UI Slop with UIZZE
UI Taste by Uizze
Stop shipping the same AI slop.
“Make it look better” gets old after the tenth prompt. Give your agent a workflow for choosing layouts, fixing visual hierarchy, and polishing the details you notice when you use the app.
Built on Uizze's anti-ui-slop workflow. Focused design playbooks for web and iOS, including native audits, with optional real-product references, fonts and icons through Uizze MCP.
Free skill. No account required. Agent-connected references and materials use the optional paid MCP.
Prerequisites
- A screen or component to build, redesign, or review — a file path or a short description.
- Existing components, design tokens, and visual language, when available. For a new project, establish a small coherent system from the brief rather than requiring an existing one.
- Optional access to the paid Uizze MCP for focused references and hosted materials.
Authentication
- The free skill and public catalogue work without an account, token, MCP connection, dependency, script, or executable.
- The optional full UIZZE MCP may use the host's normal connection and authentication flow. Never claim it is connected without an actual host result.
Work from the product
Read the brief, existing UI, components, tokens, assets, and any PRODUCT.md or DESIGN.md before designing. The user's request and project constraints outrank this skill. Preserve an established visual system for extensions and polish; replace it only for an approved redesign. A new project does not require those files.
Identify the audience, primary task, important states, and intended result. Ask only about missing choices that would materially change the work. A precise request is enough to proceed; do not turn a small fix into a discovery workshop.
Research before choosing the target
For a new design, an approved redesign or a substantive improvement, use the research playbook: the agent discovers and inspects relevant screens and flow steps, selects useful examples, and turns their lessons into a checkable specification. Do this automatically before generating a new target; do not require manual browsing, a saved collection or shortlist approval. Supplied references and existing product constraints retain authority when present; small technical fixes need no research ceremony.
Apply anti-slop craft for visual consistency and, when relevant, navigation and motion. Preserve deliberate brand exceptions and native platform behavior.
Load these supporting playbooks only when the task needs them:
- Native inputs, sheets and menus: mobile controls.
- Data-backed flows, recovery, typing or measured latency: state and performance.
- New or revised illustrations and imagery: image assets.
- Native screen, gesture and full-flow checks: native verification.
Image first, then implement
Follow Uizze's image-to-UI workflow before visual implementation. When an authorized image-generation tool is available, new visual work and approved redesigns start with a realistic UI image, inspected before code. An approved supplied image takes precedence. Save its actual dimensions and build the target 1:1 with semantic components and real controls, not a screenshot background.
Render at that viewport once assets and fonts load, compare with the stable target, correct visible mismatches and inspect again. Preserve the approved identity at other sizes. A small technical fix or read-only audit does not need a new image; if image tools are unavailable, explain that and use an existing target or the project's conventions without pretending generation or visual verification succeeded.
Select the workflow
Load the playbook for the requested action, plus the platform and craft guidance needed to execute it:
- New interface or major redesign: new-work
- Product or dashboard work: operate
- Refinement and polish: polish
- Simplification: distill
- Explicit web audit: audit, read-only unless fixes were requested
- Native iOS: iOS, alongside the action's playbook; for an audit, use native audit instead of a DOM scan
- Explicit
/overdrive, “Uizze Overdrive”, or a request for exceptional interaction work: Overdrive
For implementation, use craft after the direction is settled. Load only relevant files; multiple complementary playbooks are allowed. Overdrive is opt-in, not the default for ordinary UI work. It requires a chosen direction before implementation.
“Use Uizze Overdrive on this screen” works through this router; a native slash command depends on the host. These are self-contained Markdown playbooks, not an installer, background service, or executable engine.
Optional Uizze evidence
Read the reference policy before using find_ui_references or find_ui_materials. Inspect relevant visual evidence when it can inform the layout, state, interaction, or assets. Use the host's available tools, not invented calls or connections. Paid retrieval is optional; missing access does not block local design work.
Distinguish an exact reference, a related example, no match, and a service error. Briefly disclose a limitation that affected the result. Never claim an image was inspected or a state was found without evidence.
Finish
Build the requested scope and exercise its important states. Render and inspect the real result at representative desktop/mobile sizes or native device classes, including the user's reported failing size. Compare it with the chosen direction or supplied reference, not just with the absence of runtime errors.
Fix material problems in a batch, then render and inspect again. Stop once the requested result is verified; do not keep inventing work. If a bounded pass cannot resolve an issue, report it instead of claiming a pass. When rendering is unavailable, distinguish code checks from visual verification.
Save the actual captures, tested states and source hashes using visual verification. Its optional local integrity check rejects missing or stale evidence; it does not judge aesthetics or replace inspection. Link the receipt in the handoff and keep blocked checks explicit.
Keep the handoff concise: what changed, what was actually tested, and any remaining limitation. A skill does not authorize publishing, purchases, new dependencies, account changes, or destructive actions.
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.

