studio-test
Skill9 starsChanged 7 months agoMITView on GitHub
Run a play test in Roblox Studio via MCP and verify the game works. Starts play mode, checks console for errors, captures a screenshot, executes verification Luau, stops play mode, and reports results.
In this repository51 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- asset-auditSkill
- asset-from-imageSkill
- balance-checkSkill
- brainstormSkill
- bug-reportSkill
- changelogSkill
- code-reviewSkill
- datastore-reviewSkill
- design-reviewSkill
- design-systemSkill
- doctorSkill
- economy-auditSkill
- estimateSkill
- exploit-checkSkill
- gate-checkSkill
- gddSkill
- generate-assetSkill
- hotfixSkill
- launch-checklistSkill
- luau-lintSkill
- map-systemsSkill
- milestone-reviewSkill
- monetization-modelSkill
- onboardSkill
- patch-notesSkill
- perf-profileSkill
- project-stage-detectSkill
- prototypeSkill
- publish-reviewSkill
- release-checklistSkill
- remotes-auditSkill
- retention-analysisSkill
- retrospectiveSkill
- reverse-documentSkill
- scope-checkSkill
- sprint-planSkill
- startSkill
- studio-inspectSkill
- studio-screenshotSkill
- team-combatSkill
- team-economySkill
- team-polishSkill
- team-releaseSkill
- team-uiSkill
- tech-debtSkill
- wiki-ingestSkill
- wiki-lintSkill
- wiki-querySkill
- wiki-seedSkill
- wiki-updateSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
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 22
Wait 3-5 seconds for game initialization
- Distinctive: line 27
Do expected RemoteEvents exist in ReplicatedStorage?
≈ “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.
Files
/studio-test — Automated Play Test
Delegate to: studio-mcp-operator
Steps
1. Connect to Studio
mcp__roblox-studio__list_roblox_studios— verify Studio is openmcp__roblox-studio__set_active_studio— select the correct instance
2. Pre-Test Check
mcp__roblox-studio__search_game_tree— verify key services exist (ServerScriptService, ReplicatedStorage)mcp__roblox-studio__get_console_output— clear/note any pre-existing errors
3. Start Play Test
mcp__roblox-studio__start_stop_play— start play mode- Wait 3-5 seconds for game initialization
4. Verify Runtime State
mcp__roblox-studio__execute_luau— run verification checks:- Are core services initialized?
- Do expected RemoteEvents exist in ReplicatedStorage?
- Is player data loading without errors?
- Are any scripts erroring?
5. Capture Visual State
mcp__roblox-studio__screen_capture— screenshot the game- Analyze: Is the UI rendering? Is the world visible? Any obvious visual issues?
6. Check Console
mcp__roblox-studio__get_console_output— read all output since play started- Flag: errors (red), warnings (yellow), unexpected prints
- Categorize: script errors, DataStore errors, remote errors, asset loading errors
7. Stop Play Test
mcp__roblox-studio__start_stop_play— stop play mode
8. Report Results
# Play Test Report
**Status**: [PASS / FAIL / WARNINGS]
**Duration**: X seconds
**Studio**: [instance name]
## Console Output
- Errors: [count]
- Warnings: [count]
- [List each error with source script and message]
## Runtime Verification
- [x] Core services loaded
- [x] Remotes exist
- [ ] Player data initialized (FAILED: DataStore timeout)
## Visual Check
- [Screenshot attached]
- [Any visual issues noted]
## Recommendations
1. [Fix needed]
2. [Investigation needed]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.

