roblox-debug
installsforks
How to install roblox-debug?
tabooharmony/roblox-brain/roblox-debug
$npx -y skills add TabooHarmony/roblox-brain --skill roblox-debugUse when diagnosing Roblox or Luau errors, crashes, or unexpected behavior with an iterative reproduce, inspect, fix, and verify loop.
SKILL.md
| 1 | ## When to Load |
| 2 | |
| 3 | Load when diagnosing errors, crashes, or unexpected behavior in Roblox/Luau code. Provides a structured 7-step iterative debug loop with a max of 5 iterations before escalating. Works in both file-sync and MCP modes. |
| 4 | |
| 5 | ## Quick Reference |
| 6 | |
| 7 | ### 7-Step Debug Loop (max 5 iterations) |
| 8 | |
| 9 | **1. Error Gathering** — Get exact error message, stack trace (script + line), trigger condition (join/action/timer). Use MCP for console output if available. |
| 10 | |
| 11 | **2. Code Discovery** — Read relevant script(s). Search for error text, function names, or script from stack trace. |
| 12 | |
| 13 | **3. Root Cause Analysis** — Categorize: Syntax (missing `end`) · Runtime (nil, destroyed Instance) · Logic (wrong calc/condition) · Security (client-side logic) · Performance (timeout, memory). Load `roblox-sharp-edges` for known gotchas. Find the exact line + true root cause. |
| 14 | |
| 15 | **4. Generate Fix** — Produce corrected Luau. Explain what was wrong, why fix works, related code to check. Flag architectural changes. |
| 16 | |
| 17 | **5. Apply & Test** — Write fix to file. MCP verify if available. In offline mode: before/after diff + manual test instructions. |
| 18 | |
| 19 | **MCP evidence:** discover/select Studio, inspect before editing, read back the fix, run playtest when relevant, and report console/screenshot limitations explicitly. |
| 20 | |
| 21 | **6. Verify** — Resolved → Step 7. New errors → back to Step 1. Same error → new hypothesis, back to Step 3. Iteration 5 → escalate with full diagnosis. |
| 22 | |
| 23 | **7. Summary** — Document: bug description · root cause · fix applied · verification · related risks · prevention pattern. If systemic, recommend `/code-review`. |
| 24 | |
| 25 | ### Escalation (at iteration 5) |
| 26 | Output: all attempted fixes + why rejected, remaining hypotheses, recommended next steps (manual investigation, DevForum search, etc.). |
| 27 | |
| 28 | 📖 Full reference: `references/full.md` |
People who liked this also viewed
6 picksType
- hyperframes-cliUse the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, SkillsJul 2026
- request-refactor-planSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- analyze-projectRigor Analyze / Rigor Audit read-only skill for deep learning research repositories. Use when the user wants to read and understand a repository, inspect model structure and training or inference entrSkillsMay 2026
- explore-codeRigor Improve implementation leaf skill for auditable candidate implementation in deep learning research repositories. Use when the researcher explicitly authorizes exploratory work on an isolated braSkillsMay 2026
- ubiquitous-languageSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
- scaffold-exercisesSkills for Real Engineers. Straight from my .agents directory.SkillsJul 2026
