design-ui
Skill1 starsChanged 5 months agoMITView on GitHub
For each screen in flows.md, select shadcn/ui components and layout, note empty/loading/error states, and document basic accessibility. Drafts ui.md then awaits approval.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- lohi-ai/babysittheir own version, first seen Nov 8, 2026
- cachewraith/cachewraith-skillstheir own version, first seen Oct 25, 2026
- melconcoast/code-ideatheir own version, first seen Oct 13, 2026
- kdy1/kdy1-scriptstheir own version, first seen Oct 13, 2026
- NachikethReddyY/skillstheir own version, first seen Oct 13, 2026
- mae616/ai-templatetheir own version, first seen Aug 22, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- ThisIsSadeghi/KMPilot★ 56same name
- kdy1/kdy1-scripts★ 33same name
- mae616/ai-template★ 9same name
- melconcoast/code-idea★ 4same name
- shreyas-makes/agent-skills★ 2same name
- leolionart/claude-skills★ 1same name
- NachikethReddyY/skills★ 1same name
- ThisIsSadeghi/Loupe★ 1same name
- vasu-devs/Forge★ 1same name
- cachewraith/cachewraith-skills★ 0same name
1 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 repository22 other files it gives its agents.
- build-featureSkill
- code-reviewSkill
- compliance-checkSkill
- design-architectureSkill
- design-pricingSkill
- design-schemaSkill
- helpSkill
- launch-checklistSkill
- map-flowsSkill
- qa-planSkill
- scope-checkSkill
- security-auditSkill
- setup-billingSkill
- setup-deploySkill
- setup-stackSkill
- startSkill
- studio-statusSkill
- test-setupSkill
- threat-modelSkill
- validate-ideaSkill
- write-prdSkill
- write-testsSkill
The file
Files
Define the component-level UI specification for every screen in the approved screen list, grounded in shadcn/ui and Tailwind conventions, so that frontend-engineer can build with minimal back-and-forth. Non-autonomous: component choices are proposed and confirmed before the spec is written.
Phases
- Load flows — read
docs/specs/flows.md. If missing, stop and direct to/map-flows. If a specific screen name was passed as an argument, scope this run to that screen only; otherwise process all screens. - Propose layout and components — for each screen, suggest: overall layout pattern (full-page, split-panel, modal, drawer), the primary shadcn/ui components (
Card,DataTable,Form,Dialog, etc.), and any Tailwind utility patterns. Reference shadcn/ui component names exactly so the frontend-engineer can look them up directly. - Specify interaction states — for every screen, explicitly call out: empty state (what the user sees before any data), loading state (skeleton or spinner approach), and error state (inline error, toast, or full-page). Missing these is a common source of rework — do not skip.
- Note accessibility — for each screen note the required ARIA landmarks, focus-trap requirements (for modals/drawers), and any keyboard navigation considerations. Flag any component where shadcn defaults need augmentation.
- Approval gate — under
fullreview, walk through each screen's spec with the user; underleanorsolo, present a summary table and ask for a single sign-off. Do not write until approved. - Write the spec — write
docs/specs/ui.mdwith the approved component decisions. Next step: point to/setup-stack(if scaffold not yet created) or/build-feature.
Output
docs/specs/ui.md — per-screen component spec. Writes nothing else without approval.
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.