Roblox Studio workflow

Work as a collaborator inside an existing place, not as if it were a blank text repository. Targets current Roblox Studio and rolling platform APIs.

When to use

• Use before invasive edits to a Roblox place, Studio DataModel, or Rojo-backed project.
• Use to plan execution location, find/reuse systems, create editable Instances, and gather honest Studio verification evidence.

When not to use: this skill owns project operation, not the domain implementation. Compose it with roblox-ui, roblox-networking, roblox-characters, roblox-physics, roblox-luau, or roblox-datastores as appropriate.

Workflow

1. Establish source of truth. Determine whether Studio, Rojo files, a package manager, or a generated build owns each subtree. Do not hand-edit generated output or create Studio-only changes that the next sync overwrites.
2. Inventory before proposing structure. Inspect Explorer, search scripts/modules/remotes/tags, read project mapping and naming conventions, and run once to observe existing warnings. Locate the feature's current owner and dependencies.
3. Plan the smallest compatible edit. Name the Instances and execution locations you will change. Reuse existing remotes, component modules, cleanup utilities, tags, Attributes, folders, and configuration patterns. State any unresolved ownership boundary.
4. Create real, meaningful objects. Normal authored UI, folders, attachments, constraints, remotes, and configuration remain inspectable in Explorer. Use scripts for behavior and truly dynamic repetition—not to hide the entire feature in runtime construction.
5. Respect execution and replication. Put authoritative logic in server containers, persistent client logic in StarterPlayerScripts, per-character client logic in StarterCharacterScripts, UI templates in StarterGui, shared assets/modules/remotes in ReplicatedStorage, and secrets/server assets in server-only containers.
6. Test the actual risk. Choose Test, Test Here, Run, Server & Clients, Device Simulator, Controller Emulator, Network Simulator, or scripted Studio testing based on the behavior. Inspect server and client Output, not only the viewport.
7. Clean the experiment. Remove temporary parts, test remotes, command-bar scripts, debug UI, prints, disabled duplicate scripts, placeholder assets, and tags/Attributes created only for diagnosis. Stop the session and confirm edit-mode hierarchy is clean.
8. Report evidence precisely. List changed Instances/files, modes and client counts, cases executed, observed Output, failures and fixes, and anything not run. Never translate “looks plausible” or static inspection into “tested in Studio.”

Execution-location map

Verify actual Script RunContext and project conventions; class/location shorthand does not excuse inspection of an existing custom setup.

Reuse before adding

Before creating a RemoteEvent, search by purpose and inspect both endpoints. Before adding a “manager” or service module, identify the current feature owner. Before introducing folders/tags, inspect naming and retrieval patterns. Duplicate systems are especially dangerous when both run: they double-bind input, save twice, create two UI clones, or apply gameplay twice.

Use Attributes for small typed designer-editable metadata that belongs on an Instance. Use CollectionService tags for discovering sets of Instances across hierarchy. Use folders for ownership/navigation, not as a substitute for semantic tags. Preserve established schemas and validate missing/malformed Attributes at system boundaries.

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 must also clean behavior when a tagged Instance is removed/destroyed.

Studio MCP server (optional agent path)

Roblox Studio has a built-in MCP server. When it is connected to your AI client, drive the same inspect -> edit -> run/verify -> playtest ladder through its tools instead of manual clicking. This is OPTIONAL: when it is not connected, the manual Studio + Rojo workflow above and below is the full default path, and nothing in this skill requires MCP, Assistant, or any other tool. Enable it in Studio under Assistant, then Manage MCP Servers, then "Enable Studio as MCP server" (it speaks MCP over stdio to the client).

Map the workflow onto the documented tools. Every call also takes a studio_id; use list_roblox_studios to pick the target when several Studio windows are open.

The discipline does not change with MCP: multi_edit still writes normal, inspectable Scripts (not a feature hidden in runtime construction), the server stays authoritative, you still edit source-of-truth files rather than generated output, and you still clean up experiments. Treat get_console_output and screen_capture as the agent-native evidence for the verification ladder, and still inspect BOTH server and client output. An inserted Creator Store model can carry its own Scripts: inspect its descendants before keeping it, as you would any third-party code. start_stop_play runs a single solo session; multi-client checks still need Server & Clients or StudioTestService (see the verification reference). Connected clients can read and modify every open place, so connect only trusted ones. MCP is a transport for the same workflow, not a licence to skip it.

Roblox also ships agent-readable docs independent of MCP: an index at https://create.roblox.com/docs/llms.txt and a .md twin of every docs page (append .md to its URL). A connected client can reach these through http_get/skill; an offline agent reads the .md pages directly.

Verification ladder

1. Static: project mapping/JSON/XML parses; links resolve; Luau diagnostics/lint if available.
2. Single session: correct execution context, hierarchy, no new Output errors/warnings, basic happy path and cleanup.
3. Lifecycle: respawn, reset, reopen/rejoin, streaming or character replacement as relevant.
4. Server & Clients: at least two clients for remotes, replication, ownership, player interaction, joins/leaves, and targeted state.
5. Device/input: representative device profiles, orientation, touch, controller navigation.
6. Stress/failure: malformed input, spam, empty/full content, rapid transitions, simultaneous actions, disconnects, and cleanup.

Use the smallest rungs that cover the change, but never substitute a lower rung for a claimed higher-rung result.

Common failures

Resources

• Read references/studio-verification.md before reporting Studio validation or when choosing test modes, constructing a temporary harness, or documenting an automation gap.

Related skills

• roblox-luau — services, Instances, events, and basic execution model.
• roblox-ui, roblox-networking, roblox-characters, roblox-physics — focused production workflows that use this inspection and verification discipline.

Primary references

• https://create.roblox.com/docs/studio/testing-modes
• https://create.roblox.com/docs/projects/data-model
• https://create.roblox.com/docs/scripting/services
• https://create.roblox.com/docs/studio/mcp