Mode d’emploi
- Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
- Consultez le document original pour les outils, identifiants et environnements requis.
- Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/gamedev-skills/awesome-gamedev-agent-skills --skill roblox-studio-workflowAvant de commencer
- L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
- Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.
Roblox Studio workflow
Work as a collaborator inside an existing place, not as if it were a blank text repository. This skill owns how changes are made and proven; the domain skills own what the code does.
Workflow
- Establish the source of truth. Decide whether Studio, Rojo files, Script Sync, a package,
or a generated build owns each subtree (*.project.json mappings, PackageLink objects). Edit only the owner; a Studio edit to a Rojo-mapped script is overwritten by the next sync.
- Inventory before proposing structure. Search scripts, modules, remotes, tags and
Attributes for the feature's current owner (rg over the Rojo tree, or script_grep and search_game_tree over Studio MCP). Run once and record existing warnings, so new ones are yours.
- Plan the smallest compatible edit. Name the Instances and execution locations you will
change. Reuse existing remotes, components, cleanup utilities, tags, folders, and config patterns. State any ownership question you could not resolve.
- Create real, meaningful objects. Authored UI, folders, attachments, constraints, remotes and
configuration stay inspectable in Explorer. Scripts add behavior and genuinely dynamic repetition; they do not hide the whole feature in runtime construction.
- Respect execution and replication. Authoritative logic in server containers, persistent
client logic in StarterPlayerScripts, per-character logic in StarterCharacterScripts, UI templates in StarterGui, shared modules and remotes in ReplicatedStorage, secrets and server assets in server-only containers. Check each Script's RunContext.
- Test the actual risk with the smallest rung of the verification ladder that covers it.
- Clean the experiment. Remove temporary parts, test remotes, Command Bar fixtures, debug UI,
prints, disabled duplicate scripts, placeholder assets, and diagnostic tags or Attributes. Stop the session and confirm the edit-mode hierarchy is clean (search_game_tree or Explorer).
- Report evidence precisely. Changed Instances and files; modes and client counts; cases run;
observed Output; failures and fixes; and what was not run. Label each claim executed, statically checked, prepared but not run, or unverified. "Looks right" and static inspection are never "tested in Studio".
When Studio MCP is connected
If tools such as list_roblox_studios and execute_luau are available, drive the same ladder through them instead of asking the user to click: pick the place with list_roblox_studios, inventory, edit with multi_edit, run with start_stop_play and execute_luau, and collect evidence with get_console_output and screen_capture from both server and client. For live debugging, unit tests, device capture and profiling, call Studio's built-in skills (rbx-debug, rbx-unit-test, rbx-device-simulator-lua, rbx-perf-profiling) through the skill tool. Read references/studio-mcp.md for the tool map, limits, and safety rules.
When the tools are absent, the manual Studio and Rojo path is the full default; nothing here requires MCP. If the user wants it connected, Roblox's official roblox-get-started skill handles installation and connection.
Execution-location map
| Location | Typical role | Key constraint |
|---|---|---|
ServerScriptService | authoritative Scripts and modules | not replicated to clients |
ServerStorage | server-only assets and data | clients cannot access it |
ReplicatedStorage | shared modules, assets, remotes | visible to clients; no secrets |
StarterPlayerScripts | client systems across respawns | cloned into PlayerScripts |
StarterCharacterScripts | per-character client behavior | recreated each character |
StarterGui | authored UI templates | cloned into PlayerGui; lifecycle follows ResetOnSpawn |
Workspace | replicated world and live characters | streaming and ownership change what clients see |
Reuse before adding
Before creating a RemoteEvent, search by purpose and read both endpoints. Before adding a "manager" module, find the current feature owner. Before adding folders or tags, read the existing naming and lookup patterns. Duplicate systems that both run double-bind input, save twice, create two UI clones, or apply gameplay twice.
Attributes hold small typed designer-editable values on an Instance; CollectionService tags find sets of Instances across the hierarchy; folders express ownership and navigation. Validate Attributes at the system boundary:
local CollectionService = game:GetService("CollectionService")
local function setupDoor(instance: Instance)
if not instance:IsA("Model") then return end
local accessLevel = instance:GetAttribute("AccessLevel")
if type(accessLevel) ~= "number" then
warn(`Door {instance:GetFullName()} needs numeric AccessLevel`)
return
end
attachDoorBehavior(instance, accessLevel)
end
for _, door in CollectionService:GetTagged("Door") do setupDoor(door) end
CollectionService:GetInstanceAddedSignal("Door"):Connect(setupDoor)The owning system also tears behavior down when a tagged Instance is removed.
Verification ladder
- Static: project JSON and models build (
rojo build default.project.json -o check.rbxlx),
links resolve, selene and luau-lsp pass where the project uses them.
- Single session: right execution context and hierarchy, no new Output errors or warnings,
happy path and cleanup.
- Lifecycle: respawn, reset, rejoin, streaming, or character replacement as relevant.
- Server & Clients: at least two clients for remotes, replication, ownership, player
interaction, joins and leaves, and targeted state.
- Device and input: representative device profiles, orientation, touch, controller.
- Stress and failure: malformed input, spam, empty and full content, rapid transitions,
simultaneous actions, disconnects.
Use the smallest rungs that cover the change, and never report a lower rung as a higher one. Rungs 4-5 usually need the user: ask them to run the named mode and paste the server and client Output, or script it with StudioTestService from a plugin.
Gotchas
| Symptom | Likely cause | Remedy |
|---|---|---|
| Studio edit disappears after sync | generated or Rojo-mapped subtree edited | change the source files and resync |
| feature runs twice | duplicate Script, remote or controller | inspect first; consolidate under the existing owner |
| client cannot reach a module or object | wrong storage location | move shared content deliberately; keep secrets server-only |
| authored screen unreadable in Explorer | everything created by one LocalScript | named Instance shell plus small behavior modules |
| test passes only in solo Test | replication or lifecycle untested | Server & Clients and the relevant simulators |
| "clean" Output hides client errors | only server Output read | read each client and the server |
| shipped place has DebugFolder or prints | cleanup skipped | keep a cleanup list; inspect the hierarchy after the session |
list_roblox_studios is empty | Studio closed, no place open, or MCP setting off | ask the user to open a place and enable the server |
| MCP edit landed in the wrong place | several Studio windows open | pass the studio_id from list_roblox_studios |
| Attribute or tag behavior silently fails | schema or class not validated | validate at setup; warn with the full Instance path |
Resources
- Read
references/studio-verification.mdbefore reporting Studio validation, or when choosing
test modes, building a temporary harness, or documenting an automation gap.
- Read
references/studio-mcp.mdwhen Studio MCP tools are available or you plan to use them.
Related skills
roblox-luau: services, Instances, events, and the execution model.roblox-ui,roblox-networking,roblox-characters,roblox-physics,roblox-datastores:
feature work that uses this inspection and verification discipline.
Version notes
Last verified: 2026-11-11.
- Studio MCP tool names and the built-in
rbx-skills change with Studio releases; the dated list
is in references/studio-mcp.md.
- Server & Clients and
StudioTestService:ExecuteMultiplayerTestAsync()both allow up to eight
clients.
- The toolbar Device Simulator and the Network Simulator were a Studio beta (File → Beta Features
→ New Device Simulator).
- Rojo 7.7.1 is the current release.
- Roblox docs for agents: append
.mdto any Creator Hub URL; the index is
https://create.roblox.com/docs/llms.txt.
Sources: https://create.roblox.com/docs/studio/testing-modes, https://create.roblox.com/docs/studio/mcp, https://create.roblox.com/docs/assistant/skills, https://create.roblox.com/docs/reference/engine/classes/StudioTestService, https://github.com/Roblox/roblox-studio-agent-plugin.