mobile-ux-foundations
Skill0 starsChanged 22 days agoMITView on GitHub
Use when starting or scoping a mobile app or responsive product, deciding what to build first, writing a design brief, planning user research, reducing clutter, designing onboarding, or asking how people use phones in real life. Covers research first, one primary action, feature prioritisation, mobile constraints (interruptions, one hand, weak signal) and onboarding. Do not use for screen layout (adaptive-layout-and-spacing), navigation choice (navigation-and-flows) or reviewing an existing UI (ux-review-and-testing).
1 other project uses a version of this.
Adopted by
Most recently taken up by
- felvieira/claude-skills-fvtheir own version, first seen Sep 2, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- felvieira/claude-skills-fv★ 28same 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 repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessible-designSkill
- adaptive-layout-and-spacingSkill
- ai-interface-designSkill
- interaction-feedback-and-formsSkill
- navigation-and-flowsSkill
- ui-ux-designerSkill
- ux-documentation-and-handoffSkill
- ux-review-and-testingSkill
- visual-design-systemSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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 21
Remove before adding. Mechanism: clutter hides the core task.
- Distinctive: line 23
Ask for permissions and set-up in context, not on first launch.
- Distinctive: line 25
Do not quote old usage statistics as current.
- Distinctive: line 39
Frame: Write the user, the task, the context (one hand, outdoors, queue) and the success measure in two sentences.
- Distinctive: line 43
Onboard lightly: Default to no tutorial. If needed: short, skippable, interactive, with later access in help.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Mobile UX Foundations
Stance: frozen are the user's task, real-world constraints and the habit of researching before designing. Flexible are the methods, chosen to fit time and budget.
Hard rules
- Research or observe real users before mockups. Mechanism: symptom is a polished screen nobody uses; cause is designing from the designer's own habits; fix is even a small round of interviews or a prototype test.
- One primary action per screen. Mechanism: each extra competing element on a small screen raises the effort to find the main thing; make one action visually dominant and demote the rest.
- Remove before adding. Mechanism: clutter hides the core task; cut every element that does not help the main goal, but never hide something users need to finish the task.
- Preserve state across interruptions. Mechanism: phone use is interrupted by calls, lost signal and app switching; losing a half-filled form forces a restart. Save drafts and restore position.
- Ask for permissions and set-up in context, not on first launch. Mechanism: people agree when they see why; a cold prompt gets a refusal that is hard to undo (Apple HIG onboarding).
- Design onboarding to earn trust in under two minutes. Mechanism: a 2017 Clutch study found most users judge whether to keep an app within about two minutes of starting onboarding; Hick's Law holds that decision time rises with the number of choices offered, so a long or choice-heavy first run loses people before the product has shown its value.
- Do not quote old usage statistics as current. They show scale, not today's numbers.
- Act only on what the user asked. Before answering or changing anything, open the relevant files and check what is already done; report only what you checked, never guess, and do not redo finished work. Reason: guesses and repeated work waste the user's credit.
Gate
| Situation | Action |
| Users and task are unknown | Ask who, doing what, where, on which device |
| Feature request with no evidence of need | Ask what problem it solves and how it will be measured |
| Existing product with usage data | Prioritise by the most used flows first |
| Onboarding is requested | Ask whether the app can be learned by use; if so propose tips in context instead |
Steps
- Frame. Write the user, the task, the context (one hand, outdoors, queue) and the success measure in two sentences.
- Research. Pick the lightest method that answers the open question: interviews, observation, a competitor walk-through, or a clickable prototype test. Record findings as short personas and a main user flow.
- Prioritise. List features, mark which serve the core task, cut or defer the rest. Refine the most used first.
- Design for constraints. For each flow ask: what if the signal drops, the user is interrupted, uses one thumb, or has the text size increased? Add draft saving, offline messages and a way back.
- Onboard lightly. Default to no tutorial. If needed: short, skippable, interactive, with later access in help. Postpone non-essential set-up and give sensible defaults.
- Record decisions and reasons using ux-documentation-and-handoff.
Checklist (copy into the reply and tick as you go)
- [ ] User, task, context and success measure stated
- [ ] Research method chosen to fit the open question
- [ ] Features ranked; core task protected; extras deferred
- [ ] One primary action per screen
- [ ] Interruption, weak signal and one-hand cases handled
- [ ] Onboarding optional, short and in contextExamples
Example 1: scoping a new app User says: "We're building a household budgeting app. What should the first version include?" Actions: ask who uses it and when; frame the core task (record spending in seconds, see what is left); rank features; propose three interviews and a prototype test; flag draft saving for half-entered transactions. Result: a short brief with the core flow, deferred features and a research plan.
Example 2: a five-screen tutorial User says: "Add a five-screen tutorial on first launch explaining everything." Actions: explain that long tutorials are skipped and forgotten; propose a skippable single screen at most, plus context tips on first use of each feature, plus a help entry. Result: onboarding that teaches by doing, without blocking first use.
Common issues
- Stakeholders keep adding features. Cause: no stated core task. Fix: write the core task first and score every request against it.
- Research is skipped for time. Cause: it seems slow. Fix: test a rough prototype with three people; it still beats none.
- The home screen has five equal buttons. Cause: no priority. Fix: pick the main action, make it dominant and group the rest.
Next
navigation-and-flows once the core flow is known; ux-review-and-testing to check the result.
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.

