ui-spec
Skill71 starsChanged 7 months agoMITView on GitHub
Use this skill when moving from a PRD (Requirements) to a technical UI design. This skill bridges the gap between wireframes and code. Save UI spec to design/specs/ui-[feature-name].md: \\\`markdown # UI Spec: [Feature Name]
4 other projects use a version of this.
Adopted by
Most recently taken up by
- idaibin/skillstheir own version, first seen Nov 8, 2026
- AlpayC/claude-skill-settheir own version, first seen Sep 14, 2026
- almax000/claude-skillstheir own version, first seen Apr 19, 2026
- sparktech-ai/skillstheir own version, first seen Mar 3, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- idaibin/skills★ 6same name
- almax000/claude-skills★ 1same name
- sparktech-ai/skills★ 1same name
- AlpayC/claude-skill-set★ 0same 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 repository117 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- agent-healthSkill
- agent-styleSkill
- angular-best-practicesSkill
- annotateSkill
- api-designSkill
- architecture-decision-recordsSkill
- aws-serverlessSkill
- backend-architectSkill
- backend-patternsSkill
- brainstormSkill
- bug-reportSkill
- changelogSkill
- claude-apiSkill
- cloud-architectSkill
- cloud-run-puppeteerSkill
- code-review-checklistSkill
- code-reviewSkill
- code-simplificationSkill
- codex-sddSkill
- commitSkill
- context-engineeringSkill
- database-architectSkill
- db-reviewSkill
- deep-interviewSkill
- design-reviewSkill
- design-systemSkill
- devops-deploySkill
- diagnoseSkill
- django-patternsSkill
- docker-patternsSkill
- dotnet-backend-patternsSkill
- dreamSkill
- drizzle-orm-expertSkill
- estimateSkill
- event-sourcing-architectSkill
- fastapi-proSkill
- fork-joinSkill
- freezeSkill
- frontend-designSkill
- frontend-patternsSkill
- frontend-ui-dark-tsSkill
- gate-checkSkill
- gemini-api-integrationSkill
- gitlab-ci-patternsSkill
- guardSkill
- handoffSkill
- hotfixSkill
- hybrid-cloud-architectSkill
- kubernetes-architectSkill
- laravel-patternsSkill
- launch-checklistSkill
- learnerSkill
- llm-app-patternsSkill
- localizeSkill
- map-systemsSkill
- map-workflowSkill
- markdown-injection-scannerSkill
- microservices-patternsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use this skill when moving from a PRD (Requirements) to a technical UI design.
- Very specific: line 20
Prototype Ingestion: If prototype code exists (e.g., from prototyper), read it to understand components and states.
- Distinctive: line 29
Interactions: Use EARS format (Condition-Trigger-Response) for all interactive elements.
- Very specific: line 33
Use the UI Spec as the checklist for the frontend-developer.
- Distinctive: line 36
Every component MUST define behavior for these 5 states:
- Distinctive: line 44
Every interaction must have a keyboard equivalent.
- Distinctive: line 45
Every interactive element must have an ARIA role and label.
“Common” is measured: kept by at least 6 in 10 of the 4 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
Skill: /ui-spec
Use this skill when moving from a PRD (Requirements) to a technical UI design. This skill bridges the gap between wireframes and code.
The UI Spec Lifecycle
1. Analysis Phase
- Map ACs: Map every Acceptance Criterion from the PRD to a UI screen or interaction.
- Prototype Ingestion: If prototype code exists (e.g., from
prototyper), read it to understand components and states.
2. Decomposition Phase
- Define the Component Tree.
- Identify which components can be reused from the existing codebase vs. which need to be new.
3. Specification Phase
Fill out the ui-spec-template including:
- State Matrix: Explicitly define what the user sees during
Loading,Error, andEmptystates. - Interactions: Use EARS format (Condition-Trigger-Response) for all interactive elements.
4. Integration Phase
- Link the UI Spec in the feature's [Design Doc].
- Use the UI Spec as the checklist for the
frontend-developer.
The State x Display Matrix
Every component MUST define behavior for these 5 states:
- Default: The "Happy Path".
- Loading: Bone skeletal screens or spinners.
- Empty: Context-aware messages when no data exists.
- Error: User-friendly error messages with recovery actions (Retry/Reset).
- Partial: Behavior when some data is missing or loading.
Accessibility (A11y) Rules
- Every interaction must have a keyboard equivalent.
- Every interactive element must have an ARIA role and label.
- Color contrast ratios must meet WCAG 2.1 Level AA (4.5:1 for normal text).
Output
Save UI spec to design/specs/ui-[feature-name].md:
```markdown
UI Spec: [Feature Name]
Component Tree
[Hierarchical list of components]
State Matrix
| Component | Default | Loading | Empty | Error | Partial |
Interactions
[Component] -> [Trigger] -> [Response]
Responsive Behavior
[Breakpoint-specific layout changes]
Accessibility
[Keyboard nav, ARIA labels, contrast requirements]
Open Questions
[Items needing design decision] ```
Related Skills
design-review— review implemented UI against specfrontend-design— aesthetic direction and design systemdesign-system— reusable component libraryreview-spec— general spec review workflow
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.

