agentleFS
szlayszlay/roblox-base/.claude/skills/roblox-code-review/SKILL.md

roblox-code-review

Skill1 starsChanged 4 months agoMITView on GitHub

Use when reviewing Roblox or Luau code for security, performance, monetization, data persistence, or architecture risks.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

Files
SKILL.md

Code Review

Review Roblox projects with security, performance, and monetization lenses. Apply relevant lenses based on what changed — not all every time.

When to Load

  • User asks for code review on Roblox/Luau code
  • User asks to audit security, performance, networking, monetization, or data persistence
  • User asks about Roblox best practices for remotes, data saving, or code organization

Quick Reference

8-Step Review

  1. Project Scan — scripts, folders, naming, Rojo/Wally/Studio
  2. Organization — correct services, PascalCase modules, no orphans
  3. Code Quality — wait()→task.wait(), spawn()→task.spawn(), globals
  4. Architecture — single responsibility, no circular requires, server/client split
  5. Security — validate remotes server-side, no client-trusted state, rate-limit
  6. Performance — consolidate Heartbeat, cache services, disconnect events
  7. Report — Grade A-F. Severity: Critical/High/Medium/Low
  8. Refactor — Immediate → Short-term → Long-term

Routing — Load These Skills for Each Lens

LensLoad
Gotchas & footgunsroblox-sharp-edges
Security auditroblox-security
Remote validationroblox-networking
Data persistenceroblox-data
Monetizationroblox-monetization
Performanceroblox-performance
Luau correctnessroblox-luau-core, roblox-luau-types

Output Format

  1. READY / NOT READY
  2. Critical blockers
  3. Warnings
  4. Pass count/%
  5. Failed items + fixes

📖 Full reference: references/full.md

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.