Skip to content
Back to skills

Roblox Game Development

ASecurity

Use when building, fixing, testing, or reviewing any Roblox game or Roblox Studio work - Roblox, Roblox Studio, Luau, obby, tycoon, simulator, Roblox UI, Roblox combat, DataStore, RemoteEvent, Roblox multiplayer, Studio MCP. Router skill; load the matching reference for the task.

  • 5 stars
  • 0 votes
  • 43 copies
  • 287 views
  • Added September 3, 2026
ai-agentsrustgotestingdebuggingapisecurityperformancedocumentation

Works with

  • cli
  • api
  • mcp

Security analysis

A100/100

Pro scans all 15 files and shows the line behind each finding

Scanned September 3, 2026

npx -y skills add ShugokiFable/Ultimate-AI-Starter-Bundle --skill roblox-game-development --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Roblox Game Development?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Roblox Game Development
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/shugokifable-roblox-game-development-43107cd9/badge)](https://www.skillsdirectory.com/skills/shugokifable-roblox-game-development-43107cd9)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: roblox-game-development
description: Use when building, fixing, testing, or reviewing any Roblox game or Roblox Studio work - Roblox, Roblox Studio, Luau, obby, tycoon, simulator, Roblox UI, Roblox combat, DataStore, RemoteEvent, Roblox multiplayer, Studio MCP. Router skill; load the matching reference for the task.
---

# Roblox Game Development (RobloxForge)

You are working on a Roblox game through the **official Roblox Studio MCP**
(live engine) plus RobloxForge (knowledge + verification). Non-negotiables
first; references carry the detail.

## The loop (never skip steps)

```
rb_doctor / rb_capabilities   -> is Studio actually connected? (probe, don't assume)
inspect current place          -> search_game_tree / inspect_instance BEFORE writing anything
plan smallest vertical slice   -> one playable loop, not the whole game
implement                      -> server owns truth; client owns input/presentation
playtest via official MCP      -> start_stop_play, character_navigation, get_console_output
read console output            -> errors are data, fix them
screen_capture + INSPECT       -> only claim visual success if you actually looked
fix, re-run, THEN expand       -> vertical slice proven before adding systems
```

## Hard rules

1. **Vertical slices only.** Never build map + economy + UI + inventory + shop
   before anything is playtested. One loop, proven, then expand.
2. **Server owns truth.** Currency, damage, progression, inventory authority
   live in ServerScriptService. A client request is a *suggestion* the server
   validates. `RemoteEvent != authorization`.
3. **Probe, don't assume.** Tool surface and Studio state come from
   `list_roblox_studios` / `get_studio_state`, never from memory.
4. **"Scripts exist" is not "game works".** Completion requires playtest
   evidence: console clean, scenario exercised, screenshot captured AND looked at.
5. **Check `rb_capabilities` before playtesting.** If `autonomous_playtest` is
   not verified, say what you could NOT verify instead of claiming it.

## References (load only what the task needs)

- `references/studio-mcp.md` - tool map, argument quirks, subagent use
- `references/development-loop.md` - the vertical-slice method per genre
- `references/architecture.md` - services, script types, ownership boundaries
- `references/security-networking.md` - remotes, validation, exploit patterns
- `references/persistence.md` - DataStores, budgets, UpdateAsync, Studio safety
- `references/ui-mobile.md` - ScreenGui, safe area, input for touch
- `references/testing-debugging.md` - playtest scenarios, console triage
- `references/sharp-edges.md` - the traps that break AI-built games
- `references/game-design.md` - loop design: ACTION -> FEEDBACK -> REWARD -> REPEAT
- `references/performance.md` - MicroProfiler-first optimization, known traps
- `references/assets.md` - primitives first, Creator Store inspection rules
- `references/tooling.md` - Rojo/Rokit source-controlled workflow (optional)
- `references/assistant-skills.md` - routing to Roblox's built-in rbx-* skills

## When unsure about an API

Do not trust model memory. `rb_docs_search "TweenService:Create"` against the
official creator-docs cache, then `rb_docs_read` the hit. Current official
documentation beats your training data every time.

Files in this skill

  • SKILL.md3.2 KB
  • references/api-docs-lookup.md953 B
  • references/architecture.md2.2 KB
  • references/assets.md1.2 KB
  • references/assistant-skills.md1.4 KB
  • references/development-loop.md2 KB
  • references/game-design.md980 B
  • references/performance.md1.4 KB
  • references/persistence.md1.9 KB
  • references/security-networking.md2.4 KB
  • references/sharp-edges.md1.8 KB
  • references/studio-mcp.md2.8 KB
  • references/testing-debugging.md2.2 KB
  • references/tooling.md1.4 KB
  • references/ui-mobile.md1.6 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.