agentleFS
Sign inStart free
XinvtechXinvtech/mobile-design-os/skills/mobile-wireframe/SKILL.md

mobile-wireframe

Skill3 starsChanged 3 months agoMITView on GitHub

Convert a validated mobile UX architecture into low-fidelity screen and interaction structure before visual styling. Use when Codex needs wireframes, layout hierarchy, content priority, task-state coverage, overlay behavior, or a visual-agnostic handoff between UX architecture and UI design.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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
  1. Very specific:

    Prefer ux-architecture.json plus product-brief.json.

    line 12
  2. Distinctive:

    Use neutral boxes and labels in visual artifacts.

    line 25
  3. Distinctive:

    Read references/wireframe-rules.md before finalizing regions and references/wireframe-schema.md before creating JSON.

    line 31
  4. Very specific:

    Run python3 scripts/validate_wireframe.py <path-to-wireframe.json> and fix every error.

    line 40
  5. Distinctive:

    Do not finish with a styled mockup disguised as a wireframe or with a screen inventory that omits states and recovery.

    line 50

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mobile Wireframe

Define the screen skeleton and interaction hierarchy without choosing colors, typography, imagery, or decorative style.

Establish the input contract

Prefer ux-architecture.json plus product-brief.json. Validate upstream artifacts when validators exist. Preserve upstream Requirement, Flow, Screen, and State IDs. If the architecture is incomplete, record the gap rather than inventing a polished screen.

Build the wireframe

For each screen:

  1. State the single user question and primary task.
  2. Order the safe-area, navigation, context, content, action, and feedback regions.
  3. Assign each region a semantic role, content pressure, component role, and state behavior.
  4. Mark fixed, scrollable, sticky, keyboard-avoiding, sheet, dialog, and system-handoff behavior.
  5. Map entry, exit, primary action, secondary actions, and interruption recovery.
  6. Cover every upstream state; distinguish state changes from new screens.

Use neutral boxes and labels in visual artifacts. A wireframe may specify hierarchy, density, copy length, and interaction intent, but must not pretend to establish final tokens or visual direction.

Check the core flow

Trace at least one critical before/during/after path and one failure or interruption path. Verify that the primary action remains reachable, content identity survives errors, destructive actions have a consequence boundary, and system surfaces have in-app fallbacks.

Read references/wireframe-rules.md before finalizing regions and references/wireframe-schema.md before creating JSON.

Produce and validate

Create:

  • wireframe.md using assets/wireframe-template.md.
  • wireframe.json using assets/wireframe-template.json.

Run python3 scripts/validate_wireframe.py <path-to-wireframe.json> and fix every error. When an upstream UX file is available, also run python3 scripts/validate_wireframe.py <path-to-wireframe.json> --source-ux <path-to-ux-architecture.json> to check screen and state coverage.

Enforce the output order

  1. Source contract and assumptions.
  2. Navigation and flow skeleton.
  3. Screen inventory and region contracts.
  4. State, overlay, keyboard, and system-surface behavior.
  5. Traceability and unresolved decisions.

Do not finish with a styled mockup disguised as a wireframe or with a screen inventory that omits states and recovery.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free