Roblox Best Practices Skill — Security skill for Claude Code
Framework-agnostic Roblox/Luau best-practices skill for AI agents.
How to install Roblox Best Practices Skill
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open andrian-syh/roblox-best-practices-skill and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Roblox Best Practices Skill does
Framework-agnostic Roblox/Luau best-practices skill for AI agents. Performance, security, data, platform limits, Studio MCP safety, and 22 system blueprints. Installs to 63 agents including Claude Code, Cursor, and Windsurf.
Alternatives in Security
- T3mp3st — autonomous red teaming platform; multi-agent offensive-security meta-harness 5.7k ★
- ThinkWatch — Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII 817 ★
- Senior Engineering Partner — A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/A 148 ★
README
Roblox Best Practices Skill
**A working standard for Roblox and Luau, written for AI coding assistants.**
[](https://github.com/andrian-syh/roblox-best-practices-skill/releases) [](LICENSE) [](https://agentskills.io) [](roblox-best-practices/references/api-currency.md)
It covers how each script is written, how systems are assembled, and where the platform's real limits sit — without assuming anything about your framework, folder layout, or genre.
Works with Claude Code, Cursor, Codex, Gemini, Windsurf, Cline, Zed, and any other tool that reads the [Agent Skills](https://agentskills.io) standard.
irm https://raw.githubusercontent.com/andrian-syh/roblox-best-practices-skill/main/install.ps1 | iex
curl -fsSL https://raw.githubusercontent.com/andrian-syh/roblox-best-practices-skill/main/install.sh | bash
[Installation details](#installation) · [How the skill behaves](#how-the-skill-behaves) · [Reference map](#reference-map) · [Changelog](CHANGELOG.md)
Why this exists
Most coding standards tell an agent what good code looks like. That is the easy half. The hard half is everything an agent gets wrong *because it cannot see your game*: a remote handler that trusts the client, a connection nobody disconnects, a data store call with no answer for what happens after the last retry, an API recalled from training data that was deprecated two years ago.
This skill is the other half.
What it gives your agent
| 22 implementation blueprints | Player data, currency, inventory, trading, developer products, gacha, leaderboards, damage validation, abilities, projectiles, NPC AI at scale, round lifecycles, matchmaking, |
Related Skills
Lab Instrument Mcps
Open-source MCP servers that let AI agents operate real lab instruments, with safety limits, read-only modes,
Acs
ACS (Agnostic Config Suites) — AI coding agent skill system. 25+ auto-activating skills for Claude Code, Herme
Optimize Mac Skill
Claude Code skill: Full-system macOS performance audit and optimization. Kills memory hogs, installs watchdog,
Zscaler Vantagedata
AI-Powered Multi-Table Data Analyst Agent with deterministic Pandas execution, dual-pass grounding audit, inte
The Agency
Boîte à outils harness-agnostic de skills et agents IA pour solopreneurs belges : 22 skills audités (TVA, INAS
Android Audit
Android platform review — Kotlin/Compose correctness, lifecycle, performance
Related Agents
Roblox Asset UI
Builds Roblox GUI from a spec into .model.json instance files, a Luau builder and a PNG mockup, all written to
Roblox Reviewer
Read-only auditor for Roblox/Luau code. Reviews remote security, DataStore safety, memory/performance, and str
Guardian
Quality and safety gate: reviews the queue before publishing (duplicates, cross-account linkage, cadence, plat