roblox-map
Skill0 starsChanged 29 days agoNo licenceView on GitHub
Build and PROVE Roblox maps, levels and arenas headlessly from a JSON spec - greybox decks, cover, ledges, ramps, stairs, spawns, kill planes, and organic smooth-voxel terrain with beaches, cliffs, roads, caves and tides - emitting an annotated plan PNG, a physics-checked verification report, and either a Luau builder or an .rbxmx, all from ONE resolved tree so the plan cannot drift from what ships. The point of the skill is the PROVER: it answers "can a player actually reach that, and can they reach somewhere they should not" from raycasts and the game's real movement numbers, catching floating platforms, unreachable high ground, pockets with no way out, blocked sightlines, uneven rings, interpenetrating parts, flat or boxy terrain, zones the tide cuts off, buried spawns and ring-out windows shorter than a ragdoll. Use whenever the user wants a Roblox map, arena, level, greybox, blockout, island or map layout generated rather than dragged together in Studio, wants a map checked for playability before building it, or asks why a jump does not reach, why a ledge cannot be climbed back out of, why a ramp or staircase is unclimbable, why a map sits on the Studio grid, or why players can get somewhere they should not.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- SyphoDev-yt/roblox-ai-skillsword for word, first seen Oct 9, 2026
Other versions1 project uses a version of this.
Word for word · 1
- SyphoDev-yt/roblox-ai-skills★ 128100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository47 other files it gives its agents.
- agent-self-evaluationSkill
- architecture-decision-recordsSkill
- blender-robloxSkill
- blueprintSkill
- brand-discoverySkill
- competitive-platform-analysisSkill
- content-engineSkill
- context-budgetSkill
- continuous-agent-loopSkill
- councilSkill
- create-roblox-gameSkill
- dev-teamSkill
- eval-harnessSkill
- gan-style-harnessSkill
- growth-logSkill
- improve-skillSkill
- intent-driven-developmentSkill
- loop-design-checkSkill
- luau-reviewSkill
- marketing-campaignSkill
- market-researchSkill
- product-lensSkill
- prompt-optimizerSkill
- researchSkill
- roblox-3d-modelSkill
- roblox-animationSkill
- roblox-buildingSkill
- roblox-build-orchestratorSkill
- roblox-codeSkill
- roblox-game-devSkill
- roblox-gameSkill
- roblox-ideationSkill
- roblox-launch-marketingSkill
- roblox-qa-loopSkill
- roblox-sfxSkill
- roblox-skills-setupSkill
- roblox-texture-genSkill
- roblox-uiSkill
- roblox-vfxSkill
- rojoSkill
- santa-methodSkill
- search-firstSkill
- stable3dgenSkill
- strategic-compactSkill
- ui-mockupSkill
- verification-loopSkill
- watchSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 4 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
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
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.

