agentleFS
AshExplainedAshExplained/roblox-skills/roblox-mobile-playtest/SKILL.md

roblox-mobile-playtest

Skill5 starsChanged 5 months agoMITView on GitHub

Playtest and QA Roblox experiences for mobile and tablet. Use for device simulator checks, touch controls, safe areas, thumb zones, text readability, orientation, HUD overlap, first-action friction, and mobile performance verification through Studio MCP.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 3 are distinctive, and 3 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.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify that the Roblox experience works and feels good for phone-first players.

    line 10
  2. Very specific:

    When available, invoke rbx-device-simulator-lua before device-specific UI checks.

    line 14
  3. Very specific:

    Start play mode with start_stop_play.

    line 19
  4. Distinctive:

    Use device simulation when relevant.

    line 20
  5. Distinctive:

    No keyboard-only requirement exists for core play.

    line 33
  6. Very specific:

    Run the full first-session pass with roblox-playtest-qa, and send any defect to roblox-debugging-bugfix.

    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

Roblox Mobile Playtest

Goal

Verify that the Roblox experience works and feels good for phone-first players.

Use Device Simulator

When available, invoke rbx-device-simulator-lua before device-specific UI checks. Use it to test phone and tablet form factors, orientation, and layout behavior.

MCP Workflow

  1. Confirm Studio state with get_studio_state.
  2. Start play mode with start_stop_play.
  3. Use device simulation when relevant.
  4. Exercise controls with user_mouse_input, user_keyboard_input, and direct character movement through character_navigation.
  5. Capture evidence with screen_capture.
  6. Check get_console_output.

Mobile Checks

  • First core action is reachable in 10-30 seconds.
  • Tap targets are large and spaced apart.
  • Important buttons avoid thumb conflict and system gesture zones.
  • HUD does not block movement, combat, collection, or objectives.
  • Text is readable on phone and tablet sizes.
  • Objective markers and reward feedback are visible without opening menus.
  • No keyboard-only requirement exists for core play.
  • Menus scroll cleanly and do not hide primary actions.
  • Performance remains smooth in the first playable area.

Report Format

Return:

  • Devices or simulated form factors checked.
  • First-action time.
  • Control and HUD issues.
  • Readability issues.
  • Console or performance risks.
  • Highest-impact fixes before launch.

Next

Run the full first-session pass with roblox-playtest-qa, and send any defect to roblox-debugging-bugfix.

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.