agentleFS
Sign inStart free
AshExplainedAshExplained/roblox-skills/roblox-playtest-qa/SKILL.md

roblox-playtest-qa

Skill5 starsChanged 5 months agoMITView on GitHub

Playtest Roblox experiences through Studio MCP with attention to first-session fun, mobile UX, console errors, progression, social hooks, performance, and exploit-sensitive flows.

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. Distinctive:

    Use this skill to verify that a Roblox change works in Studio and supports player-facing quality.

    line 10
  2. Very specific:

    Use set_active_studio if needed.

    line 15
  3. Very specific:

    Start play mode with start_stop_play when verification requires live behavior.

    line 17
  4. Distinctive:

    No obvious frame drops or runaway instance/script growth.

    line 29
  5. Distinctive:

    Do not mark roadmap items complete without human approval, even after a passing playtest.

    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 Playtest QA

Purpose

Use this skill to verify that a Roblox change works in Studio and supports player-facing quality. A playtest should prove both behavior and feel.

Setup

  1. Run list_roblox_studios.
  2. Use set_active_studio if needed.
  3. Run get_studio_state.
  4. Start play mode with start_stop_play when verification requires live behavior.

Test Checklist

  • First action is reachable within 10-30 seconds.
  • Controls work without keyboard-only assumptions.
  • HUD text is readable and not blocking gameplay.
  • Rewards, currency, XP, or progress update correctly.
  • The next objective is visible after each loop.
  • Social features are visible early when relevant.
  • Monetization prompts are optional and do not interrupt first-session flow.
  • Server-side systems own valuable state.
  • No obvious frame drops or runaway instance/script growth.
  • get_console_output has no new errors.

MCP Tools To Use

  • character_navigation for movement and route checks.
  • user_keyboard_input and user_mouse_input for controls and UI.
  • screen_capture for visual verification.
  • get_console_output for errors and warnings.
  • inspect_instance or execute_luau for state checks after interaction.

Report Format

Return:

  • What was tested.
  • Evidence gathered, including screenshots or console results when available.
  • Pass/fail by area.
  • Bugs or risks ranked by player impact.
  • Recommended next verification step.

Do not mark roadmap items complete without human approval, even after a passing playtest.

Next

Send any bug to roblox-debugging-bugfix and any performance issue to roblox-performance-optimization. If the slice passes, mark it in roblox-triage / ROADMAP.md and prepare the build with roblox-release-operations.

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