Not in the top 1,000 by GitHub stars
EL4CTEO/roblox-skills
Open source list of roblox skills for AI agents
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
skills/roblox-analytics-liveops/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-architecture/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-audio/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-characters-animation/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-code-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-data-stores/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-game-systems/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-input/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-luau/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-monetization/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-networking/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-npc-ai/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-open-cloud/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-performance/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-physics/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-security/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-studio-mcp/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-teleport-matchmaking/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-testing/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-text-chat/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-tooling/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-ui/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
skills/roblox-world-building/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → a7538bc9a435
No earlier version was observed for comparison.
Verified commit a7538bc9a4355ab08ea141bd9d48670195078188
git clone --filter=blob:none --no-checkout https://github.com/EL4CTEO/roblox-skills.git .hotskills/el4cteo-roblox-skills && git -C .hotskills/el4cteo-roblox-skills checkout --detach a7538bc9a4355ab08ea141bd9d48670195078188
# Copy each selected skill directory from .hotskills/el4cteo-roblox-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/EL4CTEO/roblox-skills.git .hotskills/el4cteo-roblox-skills && git -C .hotskills/el4cteo-roblox-skills checkout --detach a7538bc9a4355ab08ea141bd9d48670195078188
# Copy each selected skill directory from .hotskills/el4cteo-roblox-skills into .agents/skills/<skill-name>/Heat
7.6- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- roblox-analytics-liveops
skills/roblox-analytics-liveops - roblox-architecture
skills/roblox-architecture - roblox-audio
skills/roblox-audio - roblox-characters-animation
skills/roblox-characters-animation - roblox-code-review
skills/roblox-code-review - roblox-data-stores
skills/roblox-data-stores - roblox-game-systems
skills/roblox-game-systems - roblox-input
skills/roblox-input - roblox-luau
skills/roblox-luau - roblox-monetization
skills/roblox-monetization - roblox-networking
skills/roblox-networking - roblox-npc-ai
skills/roblox-npc-ai - roblox-open-cloud
skills/roblox-open-cloud - roblox-performance
skills/roblox-performance - roblox-physics
skills/roblox-physics - roblox-security
skills/roblox-security - roblox-studio-mcp
skills/roblox-studio-mcp - roblox-teleport-matchmaking
skills/roblox-teleport-matchmaking - roblox-testing
skills/roblox-testing - roblox-text-chat
skills/roblox-text-chat - roblox-tooling
skills/roblox-tooling - roblox-ui
skills/roblox-ui - roblox-world-building
skills/roblox-world-building
How it works
roblox-analytics-liveops
When your agent uses it
Analytics and live ops - AnalyticsService economy/funnel/onboarding/progression/custom events, player segments, experience configs via ConfigService, A/B experiments, badges, experience notifications, timed events, daily rewards, season passes. Use when instrumenting a game, tuning economy or onboarding, running A/B tests or feature flags, or planning live events and re-engagement.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,663 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Analytics events (server-side, `AnalyticsService`)
- Experience configs (live values without republishing)
- Badges
- Experience notifications (re-engagement)
- Live-ops patterns
- Related skills
Files
../../.claude-plugin/marketplace.jsonasset487 bytes../../.claude-plugin/plugin.jsonasset661 bytesSKILL.mdcore7,028 bytesSKILL.mdcore7,028 bytesSKILL.mdcore7,028 bytes
Read SKILL.md
# Analytics and live operations
## Analytics events (server-side, `AnalyticsService`)
Standard events feed the Creator Hub dashboards automatically (economy, funnels, progression,
custom). The `Fire*` methods are deprecated; use the `Log*` family.
```luau
--!strict
local AnalyticsService = game:GetService("AnalyticsService")
local Analytics = {}
-- Currency sources and sinks → Economy dashboard.View the complete source on GitHubroblox-architecture
When your agent uses it
Roblox project structure and client/server model - replication, where code and assets belong (ServerScriptService, ReplicatedStorage, StarterPlayer), RunContext, service/controller bootstrapping, player/character lifecycle, CollectionService components, attributes, streaming-safe client code, library choices. Use when starting a project, deciding where code goes, or fixing replication/streaming bugs.
What it loads into context
Frontmatter
83 tokensAlways available to the agent
SKILL.md
2,331 tokensWhen the skill is activated
Reference documents
2,016 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The model in one paragraph
- Where things go
- Project layout (Rojo-style, recommended)
- Bootstrapping services (no framework needed)
- Player and character lifecycle
- Components with CollectionService tags
- Sharing state
- Streaming (on by default for new places)
- Anti-patterns
- Related skills
Files
SKILL.mdcore10,096 bytesreferences/ecosystem.mddoc2,653 bytesreferences/streaming.mddoc5,717 bytes
Read SKILL.md
# Roblox game architecture
## The model in one paragraph
Every Roblox game is a **server** (authoritative, runs `Script`s, sees everything, owns DataStores)
plus one **client** per player (runs `LocalScript`s / client `Script`s, renders, reads input).
The server's DataModel **replicates** to clients automatically. Client changes do **not** replicate
back, except: physics of parts the client has network ownership of (its character by default),
its own `Humanoid` state/animations, and remote calls. Assume every client is compromised
(see `roblox-security`). Design every feature as: *client requests → server validates and
decides → state replicates → clients render*.
## Where things go
View the complete source on GitHubroblox-audio
When your agent uses it
Sound and music - the Audio API (AudioPlayer, AudioEmitter, AudioListener, AudioDeviceOutput, Wire, effects, faders), classic Sound/SoundGroup, 2D vs 3D audio, music and SFX volume, client vs server playback, asset permissions, streaming caveats, voice routing, text-to-speech. Use when adding music, sound effects, spatial audio, mixing, or fixing sounds that don't play.
What it loads into context
Frontmatter
98 tokensAlways available to the agent
SKILL.md
1,382 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 2D audio (music, UI) with the Audio API
- 3D audio with the Audio API
- Classic Sound quick reference
- Where to play
- Assets and permissions
- Extras
- Related skills
Files
SKILL.mdcore5,648 bytesSKILL.mdcore5,648 bytes
Read SKILL.md
# Roblox audio
Two systems coexist:
- **Audio API** (modular, current): `AudioPlayer` → `Wire` → (`AudioEmitter` … `AudioListener`) → `Wire`
→ `AudioDeviceOutput`, with effect objects inserted in the chain. Required for voice-chat processing,
mixing graphs, analyzers, text-to-speech/speech-to-text.
- **`Sound`** (classic, still supported): one object, parented to a part for 3D or to `SoundService`/UI for 2D;
routed through `SoundGroup`s with `SoundEffect` children. Fine for simple games and existing code.
Don't mix both for the same feature; follow what the project uses.
## 2D audio (music, UI) with the Audio API
```luauView the complete source on GitHubroblox-characters-animation
When your agent uses it
Characters and animation - Humanoid properties/states, spawning (LoadCharacterAsync), health and damage, HumanoidDescription appearance, Animator/AnimationTrack playback, priorities and markers, default animation replacement, Tools, TweenService, IKControl, Character Controller Library (beta). Use when changing movement, abilities, damage, respawn, avatars, animations, tweens, or tools/weapons.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,867 tokensWhen the skill is activated
Reference documents
854 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Character basics
- Health and damage (server)
- Appearance
- Animation playback
- Tweening
- Tools
- Character Controller Library (beta)
- Related skills
Files
SKILL.mdcore7,584 bytesSKILL.mdcore7,584 bytesreferences/character-controller-library.mddoc3,493 bytes
Read SKILL.md
# Characters and animation
## Character basics
- A player character is a `Model` with a `Humanoid`, `HumanoidRootPart` (the root; move the character
with `character:PivotTo(cframe)`), R15 body parts, and an `Animate` LocalScript.
- Defaults (walk speed, jump, health, R6/R15, collisions, body scaling) are configured in Studio's
**Avatar Settings** window and `StarterPlayer` (`CharacterWalkSpeed`, `CharacterJumpHeight` or
`CharacterUseJumpPower` + `CharacterJumpPower`).
- Custom character: put a `Model` named `StarterCharacter` in `StarterPlayer`. Custom per-player
spawns: `Players.CharacterAutoLoads = false`, then `player:LoadCharacterAsync()` when ready
(e.g. after data loads). `LoadCharacter` (non-Async) is deprecated.
- Characters are destroyed and recreated on death/respawn: bind per-character logic in `CharacterAdded`.
- Client-set `WalkSpeed`/`JumpHeight` are trivially exploitable; enforce limits on the server or useView the complete source on GitHubroblox-code-review
When your agent uses it
Review Roblox/Luau code for exploits, data loss, memory leaks, performance problems, lifecycle bugs, policy issues, and deprecated or superseded APIs, using a severity-ranked checklist and the full 2026 deprecation map. Use when reviewing a PR or script, auditing a game before launch, modernizing legacy code, or asked what is wrong with some Roblox code.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
1,186 tokensWhen the skill is activated
Reference documents
3,120 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Severity guide
- Checklist
- Output format
Files
SKILL.mdcore5,027 bytesreferences/deprecated-apis.mddoc11,401 bytes
Read SKILL.md
# Roblox code review
Review in severity order. Report each finding with **file:line, severity, what breaks, and the fix**.
Verify claims against the code (and the engine reference when unsure) — don't pattern-match blindly.
## Severity guide
| Severity | Examples |
| --- | --- |
| **Critical** | Client-authoritative rewards/damage/currency; unvalidated remote args (NaN, instance spoofing); purchases granted outside `ProcessReceipt` or non-idempotent; data saved with `SetAsync` from multiple servers without session locking; secrets/API keys in replicated code; unfiltered player text shown to others. |
| **High** | Data loss paths (no `BindToClose`, saving default data after a failed load, no retry); memory leaks (connections, player-keyed tables); `InvokeClient`; per-frame remotes; infinite yields (`WaitForChild` without timeout on optional instances, `RemoteFunction` handlers that can yield forever); streaming-unsafe client indexing. |
| **Medium** | Deprecated/superseded APIs; `wait`/`spawn`/`delay`; polling loops; server-side tweens; missing `pcall` on network/yielding APIs; missing late-joiner handling; race conditions on `CharacterAdded`. |
| **Low** | Style, naming, missing types, magic numbers, dead code, minor inefficiencies. |
View the complete source on GitHubroblox-data-stores
When your agent uses it
Persistence and cross-server data - DataStoreService (UpdateAsync, retries, budgets, limits), session locking with ProfileStore, schema migrations, OrderedDataStore leaderboards, MemoryStore queues/sorted maps/hash maps, MessagingService, right-to-be-forgotten. Use when saving player data, building leaderboards or queues, or fixing data loss, duplication, or throttling.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
2,352 tokensWhen the skill is activated
Reference documents
2,219 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Choose the service
- Player data: use session locking
- Raw DataStoreService rules (when not using a wrapper)
- Budgets and limits (2026)
- Schema versioning and migrations
- Leaderboards (OrderedDataStore)
- MemoryStore essentials
- MessagingService essentials
- Right to be forgotten
- Related skills
Files
SKILL.mdcore9,712 bytesSKILL.mdcore9,712 bytesSKILL.mdcore9,712 bytesreferences/memory-and-messaging.mddoc4,030 bytesreferences/raw-datastore.mddoc4,748 bytes
Read SKILL.md
# Roblox data stores and cloud services
## Choose the service
| Need | Service | Notes |
| --- | --- | --- |
| Player progress, inventory, settings | **DataStore** via ProfileStore (session-locked) | One key per player (`User_{UserId}`), ≤ 4 MB. |
| Global leaderboards | `OrderedDataStore` | Integer values only; periodic updates, cached reads. |
| Fast, temporary, cross-server state | `MemoryStoreService` | Sorted maps, queues, hash maps; everything expires (TTL ≤ 45 days). |
| Matchmaking queues, live events, server lists | MemoryStore queue / sorted map | Not durable — never the only copy of valuable data. |
| Broadcast to all servers | `MessagingService` | ≤ 1 kB per message, best effort, no delivery guarantee. |
| Values changed by live-ops without publishing | Experience configs (`ConfigService`) | See `roblox-analytics-liveops`. |
## Player data: use session lockingView the complete source on GitHubroblox-game-systems
When your agent uses it
Recipes for common systems built on server authority - currency service and leaderstats, XP/levels, round loops with intermission and teams, validated melee/ranged combat, inventory and tools, soft-currency shops, obby checkpoints, daily rewards, pets. Use when implementing or reviewing gameplay systems such as rounds, combat, weapons, inventories, shops, currencies, or progression.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
976 tokensWhen the skill is activated
Reference documents
4,921 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Currency service (the pattern every economy uses)
- Design checklist for any new system
- Related skills
Files
SKILL.mdcore4,200 bytesreferences/combat.mddoc5,290 bytesreferences/inventory-shop.mddoc5,583 bytesreferences/progression.mddoc4,047 bytesreferences/round-system.mddoc4,764 bytes
Read SKILL.md
# Game systems recipes
Every recipe follows the same contract:
1. **State lives on the server** in a service module; persistent parts go through the data layer
(`roblox-data-stores`).
2. **Clients send intents** through validated, rate-limited remotes (`roblox-security`,
`roblox-networking`) and render state they receive (attributes, snapshots/deltas).
3. **Config is data**: tunables in a shared/server config module (or live `ConfigService` configs).
4. **Lifecycle-safe**: handles late joiners, respawns, leaving mid-action, and server shutdown.
| System | Reference |
| --- | --- |
| Leaderstats, currency service, XP/levels, daily rewards, obby checkpoints | [references/progression.md](references/progression.md) |
| Round loop (intermission → match → results), teams, spawning | [references/round-system.md](references/round-system.md) |View the complete source on GitHubroblox-input
When your agent uses it
Player input and cameras across keyboard/mouse, touch, gamepad, VR - Input Action System (InputContext, InputAction, InputBinding), UserInputService (PreferredInput, gameProcessedEvent, mouse lock), ContextActionService, reserved keys, custom cameras with BindToRenderStep. Use when adding controls, keybinds, abilities, vehicles, on-screen buttons, or custom cameras.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
1,929 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Choose an approach
- Input Action System
- UserInputService essentials
- ContextActionService (legacy-compatible)
- Custom cameras
- Cross-platform checklist
- Related skills
Files
SKILL.mdcore7,969 bytes
Read SKILL.md
# Roblox input and camera
## Choose an approach
| Approach | Use when |
| --- | --- |
| **Input Action System** (`InputContext` → `InputAction` → `InputBinding`) | New gameplay controls. Cross-device bindings configured as instances, contexts you enable/disable, built-in on-screen button binding, prompt display. Recommended. |
| `UserInputService` events | Raw input, text-free hotkeys, mouse position/delta, touch gestures, device detection. |
| `ContextActionService:BindAction` | Legacy/simple bind-with-mobile-button; existing code. |
All input handling is **client-side**. Send *intent* to the server via remotes; the server validates.
## Input Action System
View the complete source on GitHubroblox-luau
When your agent uses it
Modern, type-safe Luau for Roblox, covering --!strict and the new type solver, generics, string interpolation, if-expressions, task library, require-by-string, module/OOP patterns, error handling with retries, buffer/vector, and legacy APIs to avoid. Use when writing, refactoring, or explaining any Roblox script, fixing type errors, or modernizing old Lua code.
What it loads into context
Frontmatter
89 tokensAlways available to the agent
SKILL.md
3,094 tokensWhen the skill is activated
Reference documents
3,237 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Defaults for all generated code
- Modern syntax cheat sheet
- Types (new type solver)
- Modules and require
- Errors and retries
- Concurrency: the task library
- Cleanup (memory leaks are the #1 Roblox bug)
- Buffers and vectors (performance-sensitive data)
- Legacy → current (most common mistakes)
- Performance idioms (only where it matters)
- Related skills
Files
SKILL.mdcore12,057 bytesreferences/stdlib-cheatsheet.mddoc4,449 bytesreferences/type-system.mddoc7,025 bytes
Read SKILL.md
# Modern Luau for Roblox
Luau is Roblox's gradually-typed Lua 5.1 derivative. Engine and language move fast; many
patterns from older tutorials (and older training data) are deprecated. Apply these defaults
to **every** script you write unless the project clearly uses another convention.
## Defaults for all generated code
1. `--!strict` at the top of new ModuleScripts (and Scripts when practical). Type public functions.
2. Get services with `game:GetService("Name")` at the top of the file, never `game.Name`.
3. Use the `task` library: `task.wait`, `task.spawn`, `task.defer`, `task.delay`, `task.cancel`.
Never `wait`, `spawn`, `delay` (deprecated, throttled, imprecise).
4. Yielding engine calls that can fail (DataStore, HTTP, Marketplace, Teleport, `*Async`) go inside `pcall`.
5. Prefer the `*Async` variants of APIs; Roblox renamed most yielding methodsView the complete source on GitHubroblox-monetization
When your agent uses it
Robux monetization - developer products with idempotent ProcessReceipt, passes, subscriptions, rewarded video ads, personalized shops, regional pricing and trade arbitrage, paid random item policy (PolicyService), commerce products, private servers, Roblox Plus, refunds, age checks and the US 18+ rate. Use when adding purchases, shops, game passes, subscriptions, ads, or loot boxes, or debugging lost/duplicated purchases.
What it loads into context
Frontmatter
97 tokensAlways available to the agent
SKILL.md
2,041 tokensWhen the skill is activated
Reference documents
1,012 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Product types
- Developer products: ProcessReceipt
- Passes
- Subscriptions
- Shops that sell
- Refunds and chargebacks
- Compliance
- Related skills
Files
SKILL.mdcore8,867 bytesreferences/ads-and-extras.mddoc4,425 bytes
Read SKILL.md
# Roblox monetization
## Product types
| Type | Buy | Use for | Grant via |
| --- | --- | --- | --- |
| Developer product | Repeatedly | Currency, consumables, boosts, revives | `MarketplaceService.ProcessReceipt` (server) |
| Pass | Once, permanent | VIP, permanent perks, extra slots | `UserOwnsGamePassAsync` check on join + purchase-finished event |
| Subscription | Monthly, revocable | Recurring perks (daily currency, VIP) | `GetUserSubscriptionStatusAsync` + `UserSubscriptionStatusChanged` |
| Rewarded video ad | Free (watch ad) | Small rewards (≈3–10 Robux value) | Developer product granted through `ProcessReceipt` |
| Commerce product | Real money (physical goods) | Merch with bundled digital benefits | `CommerceService`; digital benefits via `ProcessReceipt` |
| Private server | Monthly | Paid private servers | Configured in Creator Dashboard |
All granting happens on the **server**. Never grant from client events likeView the complete source on GitHubroblox-networking
When your agent uses it
Client-server communication - RemoteEvent, UnreliableRemoteEvent, RemoteFunction, what survives serialization, typed remote modules, server validation and rate limiting, bandwidth (deltas, buffers, batching), synced time, Zap/Blink. Use when adding remotes, syncing state to clients, debugging nil/lost remote arguments, or reducing lag and bandwidth.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
1,805 tokensWhen the skill is activated
Reference documents
1,304 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pick the right channel
- Defining remotes once (typed)
- Server handler template
- What survives the wire
- Bandwidth and CPU
- Time and latency
- Related skills
Files
SKILL.mdcore7,282 bytesreferences/patterns.mddoc5,407 bytes
Read SKILL.md
# Roblox networking
## Pick the right channel
| Channel | Delivery | Use for |
| --- | --- | --- |
| `RemoteEvent` | Reliable, ordered | Requests (client→server), game events, UI updates. The default. |
| `UnreliableRemoteEvent` | May drop or reorder; payload ≤ **1000 bytes** (larger payloads are dropped) | Continuous, superseded-by-next data: aim direction, cosmetic VFX, positions of non-physics objects. |
| `RemoteFunction` | Request/response, yields caller | Client→server queries that need an answer (e.g. "can I buy X?"). |
| Attributes / properties | Automatic replication server→client | Persistent state clients read (health, team, round state). |
| Physics replication | Automatic for owned assemblies | Moving parts; see `roblox-physics`. |
Never use `RemoteFunction:InvokeClient`: if the client errors, disconnects, or never returns, the server
throws or **yields forever**. Use a `RemoteEvent` to the client and another back if you need a reply.View the complete source on GitHubroblox-npc-ai
When your agent uses it
NPCs and enemy AI - PathfindingService (CreatePath, ComputeAsync, costs, modifiers, links, blocked paths), chase/follow loops, state machines, perception and line of sight, spawning/pooling, scaling to many NPCs. Use when creating enemies, pets, followers, shopkeepers, wave spawners, or fixing NPCs that get stuck, jitter, or lag the server.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
1,781 tokensWhen the skill is activated
Reference documents
647 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Architecture
- Pathfinding
- Behavior: state machine
- Perception tips
- Related skills
Files
SKILL.mdcore6,801 bytesSKILL.mdcore6,801 bytesreferences/scaling-npcs.mddoc2,666 bytes
Read SKILL.md
# NPCs and AI
## Architecture
- NPC **logic runs on the server** (authoritative targets, damage, drops). Visual extras (idle
animations, nameplates, effects) can run on clients.
- One NPC service drives all NPCs from a single loop (e.g. 5–10 Hz "think" rate, staggered), not one
script + `while true` per NPC. Tag NPC models (`CollectionService`) and keep per-NPC state in a table.
- Server-owned physics: `npc.PrimaryPart:SetNetworkOwner(nil)` after spawning, so NPCs don't stutter
when ownership moves between nearby players (and exploiters can't push them).
- Use `Humanoid` for NPCs that need walking/jumping/climbing; for simple movers (turrets, floating
enemies, crowds) use an `AnimationController` + `Animator` and move with constraints or CFrames.
## PathfindingView the complete source on GitHubroblox-open-cloud
When your agent uses it
Open Cloud REST APIs and HttpService - API keys/OAuth, v2 patterns, data/memory stores from outside, publishMessage, place publishing, server restarts, Luau execution, bans, configs/experiments, notifications, webhooks with roblox-signature verification, rate limits, Secrets. Use when building external tools, dashboards, bots, CI/CD, admin panels, or calling web APIs from a game.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
2,010 tokensWhen the skill is activated
Reference documents
866 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Authentication
- Common endpoints (v2 unless noted)
- Patterns
- HttpService inside games
- Webhooks (Roblox → your server)
- Related skills
Files
SKILL.mdcore7,768 bytesSKILL.mdcore7,768 bytesreferences/webhooks.mddoc3,522 bytes
Read SKILL.md
# Roblox Open Cloud and HttpService
Base URL: `https://apis.roblox.com`. Prefer **Open Cloud** endpoints (API key or OAuth 2.0, stable).
Legacy cookie-authenticated `*.roblox.com` web APIs can break without notice — don't build on them.
## Authentication
- **API keys** (Creator Dashboard → Open Cloud → API Keys): for your own/your group's resources and
automation. Grant the minimum scopes per universe, set an **IP allowlist** (CIDR) and **expiration**,
[Credential-related source omitted]
key created under the group. Introspect a key with `POST /api-keys/v1/introspect`.
- **OAuth 2.0** (authorization code + PKCE): apps acting on behalf of other users (third-party tools).
- Never ship keys in game scripts, attributes, or client code.
View the complete source on GitHubroblox-performance
When your agent uses it
Performance diagnosis and optimization - MicroProfiler, Script Profiler, Developer Console, Scene Analysis, Luau heap and memory categories, memory leaks, network/replication cost, rendering and physics cost, streaming, native codegen, Parallel Luau with Actors. Use when a game lags, stutters, drops FPS, crashes on mobile, has high ping, or before optimizing hot code.
What it loads into context
Frontmatter
86 tokensAlways available to the agent
SKILL.md
1,773 tokensWhen the skill is activated
Reference documents
722 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Tools
- Targets
- Most common problems → fixes
- Luau hot paths
- Rendering and assets
- Physics
- Parallel Luau
- Related skills
Files
SKILL.mdcore7,392 bytesreferences/profiling.mddoc2,935 bytes
Read SKILL.md
# Roblox performance
**Measure before optimizing.** Identify whether the bottleneck is server compute, client compute
(CPU/GPU), memory, network, or load time, then use the matching tool.
## Tools
| Tool | Open | Use for |
| --- | --- | --- |
| Developer Console | F9 (in game) | Errors, server/client memory by category, network, script activity. Works in live servers. |
| MicroProfiler | Ctrl+Alt+F6 (⌘⌥F6); Dev Console for server | Per-frame timing; spikes; dump a frame for detail. |
| Script Profiler | Studio / Dev Console | Which functions consume Luau time (sampling). |
| Luau heap snapshots | Dev Console → Memory → Luau Heap | What tables/closures/instances are held and by what (leaks). |
| Scene Analysis | Studio | Script memory, unparented instances (leaks), instance composition, audio/animation memory, triangles. Also `SceneAnalysisService` via Studio MCP. |View the complete source on GitHubroblox-physics
When your agent uses it
Physics and spatial queries - Raycast/Blockcast/Spherecast, overlap queries, collision groups, Touched pitfalls, collision summaries (impact point/normal/speed), assemblies and welds, mover constraints replacing BodyMovers, mechanical constraints, network ownership, CFrame math, vehicles/projectiles, and server authority (BindToSimulation, prediction, rollback). Use when moving parts, detecting hits, building vehicles or projectiles, or fixing jitter, flinging, or ownership bugs.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
2,457 tokensWhen the skill is activated
Reference documents
2,358 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Spatial queries (use these, not Touched, for gameplay decisions)
- Touched: know its limits
- Collision summaries (impact data)
- Collision groups
- Assemblies and joints
- Mover constraints (replace BodyMovers)
- Network ownership
- Server authority (competitive games)
- Stability tips
- Related skills
Files
SKILL.mdcore10,069 bytesreferences/recipes.mddoc4,947 bytesreferences/server-authority.mddoc4,602 bytes
Read SKILL.md
# Roblox physics and spatial queries
## Spatial queries (use these, not Touched, for gameplay decisions)
```luau
--!strict
local params = RaycastParams.new()
params.FilterType = Enum.RaycastFilterType.Exclude
params.FilterDescendantsInstances = {} -- e.g. { character } of the shooter
params.IgnoreWater = true
local function castRay(origin: Vector3, direction: Vector3): RaycastResult?
-- direction's length is the max distance
return workspace:Raycast(origin, direction, params)View the complete source on GitHubroblox-security
When your agent uses it
Anti-exploit design - never trust the client, validate every remote argument (NaN, spoofed instances, strings), rate limiting, ProximityPrompt/ClickDetector abuse, network ownership, movement and hit validation, economy/trade duplication, code confidentiality, secure teleports, heuristics, Ban API. Use when writing server handlers for client input, combat/economy/trading, or reviewing for exploits.
What it loads into context
Frontmatter
90 tokensAlways available to the agent
SKILL.md
2,277 tokensWhen the skill is activated
Reference documents
962 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Core rules
- Argument validation toolkit
- Rate limiting (token bucket)
- Client-triggered instances are not safe
- Network ownership and movement
- Combat validation (hit reports)
- Economy, trading, purchases
- Confidentiality
- Detection and consequences
- Related skills
Files
SKILL.mdcore9,723 bytesreferences/checklist.mddoc4,092 bytes
Read SKILL.md
# Roblox security
**Exploiters fully control their client**: they can run any Luau, read every replicated script
(decompiled), fire any remote with any arguments at any rate, edit any local property (WalkSpeed,
prompt `Enabled`, `MaxActivationDistance`), and move anything they have network ownership of.
Client-side anti-cheat is at best a speed bump. Security comes from server design.
## Core rules
1. **The server decides.** Clients send *intent* ("I pressed attack aiming here"), never *results*
("I dealt 50 damage", "give me 100 coins").
2. **Validate every argument** of every `OnServerEvent`/`OnServerInvoke`: type, structure, range, finiteness.
3. **Validate context**: is the player alive, in range, not on cooldown, owns the item, allowed to act?
4. **Rate limit** everything a client can trigger (remotes, prompts, touches, clicks).View the complete source on GitHubroblox-studio-mcp
When your agent uses it
Drive Roblox Studio from an AI agent via the built-in Studio MCP server - connecting Claude Code, Codex, Cursor, OpenCode, Gemini CLI; tools to explore the DataModel, read/edit scripts, run Luau in edit/server/client, playtest, read output, capture screenshots, simulate input, insert assets. Use when an agent should inspect, modify, or playtest an open Studio place, or to set up the connection.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
1,657 tokensWhen the skill is activated
Reference documents
628 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Setup
- Tools
- The working loop
- Rules of thumb
- Roblox-authored skills and conversions
- Related skills
Files
SKILL.mdcore6,595 bytesSKILL.mdcore6,595 bytesSKILL.mdcore6,595 bytesreferences/client-setup.mddoc2,228 bytes
Read SKILL.md
# Working in Roblox Studio through MCP
Roblox Studio ships a **built-in MCP server** (stdio). With it, an agent can explore the open place,
edit scripts, run Luau in edit/server/client contexts, playtest, read the Output, capture the viewport,
and simulate player input. It is the fastest way to **verify** Roblox changes instead of guessing.
## Setup
1. Latest Studio → open **Assistant** → **…** → **Manage MCP Servers** → enable **Enable Studio as MCP server**.
2. Use **Quick connect** (Claude Code, Claude Desktop, Codex CLI, Cursor, Gemini CLI, VS Code, Antigravity)
or configure the client manually:
| OS | Command |
| --- | --- |View the complete source on GitHubroblox-teleport-matchmaking
When your agent uses it
Multi-place and multi-server games - universes and places, TeleportAsync with TeleportOptions (reserved/specific servers, teleport data), retrying failed teleports, secure access control, lobby-to-match flows, parties and queues, Roblox matchmaking with custom signals, server type detection, data handoff. Use when adding lobbies, match servers, dungeons, parties, server browsers, or customizing server selection.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,495 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Structure
- Teleporting (server)
- Data handoff between places
- Detecting server type
- Lobby → match flow
- Roblox matchmaking (which server a joining player gets)
- Server lifecycle
- Related skills
Files
SKILL.mdcore6,354 bytes
Read SKILL.md
# Teleports, places, and matchmaking
## Structure
- A **universe** (experience) contains a start place plus sub-places. All places share DataStores,
MemoryStores, MessagingService, developer products, and passes.
- Typical layouts: Lobby (start place) → Match place (reserved servers) → back to Lobby; or a hub with
separate world places. Keep shared code in packages or a shared Rojo tree.
- **Access Control for Places** (Creator Dashboard): `Fully open`, `Limited to same universe`, or
**`Secure within universe only`** (only server-initiated teleports into non-start places — recommended
for progression gates and test places). Clients can otherwise teleport themselves anywhere in the universe.
## Teleporting (server)
View the complete source on GitHubroblox-testing
When your agent uses it
Testing Roblox code - testable modules with dependency injection, Jest Lua (runCLI, .spec files), legacy TestEZ, running tests in Studio, via Studio MCP, run-in-roblox, or CI with Open Cloud Luau Execution, Lune for pure Luau, multi-client playtests, QA checklist. Use when adding tests, setting up a test runner or CI, or verifying a gameplay change works.
What it loads into context
Frontmatter
92 tokensAlways available to the agent
SKILL.md
1,671 tokensWhen the skill is activated
Reference documents
787 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Make code testable first
- Jest Lua (recommended framework)
- Where tests run
- Playtesting in Studio
- QA checklist before shipping a feature
- Related skills
Files
SKILL.mdcore6,474 bytesreferences/cloud-test-runner.mddoc2,797 bytes
Read SKILL.md
# Testing Roblox games
## Make code testable first
- Keep game rules in **pure ModuleScripts** (inputs → outputs, no services, no yields): damage formulas,
inventory operations, shop pricing, state machines, serialization, validation. These are trivially testable.
- Services take their dependencies as parameters (**dependency injection**) so tests can pass fakes
instead of real DataStores, remotes, or `Players`.
```luau
--!strict
-- ReplicatedStorage/Shared/Inventory.luau — pure logic, no Roblox services.
export type Inventory = { [string]: number }
View the complete source on GitHubroblox-text-chat
When your agent uses it
Chat and text safety - TextChatService (channels, SendAsync, ShouldDeliverCallback, OnIncomingMessage, commands, bubbles, custom UI), mandatory TextService filtering of any player-authored text, rate limits, privacy checks, PolicyService restrictions, legacy Chat migration. Use when adding chat features or commands, or any feature that shows one player's text to others (names, signs, notes).
What it loads into context
Frontmatter
88 tokensAlways available to the agent
SKILL.md
1,456 tokensWhen the skill is activated
Reference documents
961 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Non-negotiable rules (Roblox Community Standards)
- Filtering player-authored text
- TextChatService essentials
- PolicyService (per-user restrictions)
- Related skills
Files
SKILL.mdcore6,218 bytesSKILL.mdcore6,218 bytesSKILL.mdcore6,218 bytesreferences/chat-recipes.mddoc3,944 bytes
Read SKILL.md
# Chat and text safety
## Non-negotiable rules (Roblox Community Standards)
1. Player-to-player conversation must go through **TextChatService** `TextChannel`s (handles filtering,
privacy/parental settings, and abuse reporting). The legacy `Chat` service/`ChatService` Lua modules
are gone — `TextChatService` is the only chat system.
2. **Any text authored by one player and shown to another** (pet names, signs, guild names, trade notes,
custom UI) must be filtered with `TextService:FilterStringAsync` on the server before display — and
re-filtered when loaded from a DataStore later.
3. Editable text others can see (signs, bulletin boards) needs a rate limit of at least 1 minute.
4. Respect privacy settings with `CanUserChatAsync`/`CanUsersChatAsync`/`CanUsersDirectChatAsync` and mark
direct-message channels with `TextChannel:SetDirectChatRequester()`.
View the complete source on GitHubroblox-tooling
When your agent uses it
Professional Roblox toolchain - Studio Script Sync vs Rojo, Rokit, Wally/pesde packages, luau-lsp with sourcemaps, StyLua, selene, darklua, Lune, roblox-ts, .luaurc, git, GitHub Actions CI and Open Cloud publishing. Use when creating a Roblox repo, configuring VS Code/Cursor, adding packages, fixing sourcemap/require typing, or automating builds and deploys.
What it loads into context
Frontmatter
104 tokensAlways available to the agent
SKILL.md
1,691 tokensWhen the skill is activated
Reference documents
772 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Pick a sync model
- Rokit: pinned toolchain
- Rojo project
- Packages
- Code quality
- Lune
- roblox-ts
- Git and CI
- Related skills
Scripts executed separately
../../scripts/install.sh
Files
../../scripts/install.shruns3,928 bytesSKILL.mdcore5,722 bytesSKILL.mdcore5,722 bytesSKILL.mdcore5,722 bytesreferences/ci-workflow.mddoc2,888 bytes
Read SKILL.md
# Roblox tooling
## Pick a sync model
| Need | Use |
| --- | --- |
| Edit scripts in an external editor / git for code only; keep Studio as source of truth; Team Create | **Studio Script Sync** (built in: right-click a folder → **Sync to…**) |
| Whole project as files, file system is the source of truth, CI builds, packages | **Rojo** (`rojo serve` + Studio plugin) |
Script Sync syncs only `Script`/`LocalScript`/`ModuleScript`/`Folder` (≤ 10,000 scripts per synced
root, ≤ 128 roots); don't sync scripts that carry attributes/tags (they're not written to disk).
Pair either with the **Luau Language Server** VS Code extension + its **Luau Language Server Companion**
Studio plugin (sends the DataModel tree so requires and instance paths type-check).
View the complete source on GitHubroblox-ui
When your agent uses it
Responsive cross-platform UI - ScreenGui and safe areas (ScreenInsets), Scale vs Offset, UIListLayout flex/UIFlexItem, constraints, StyleSheets/tokens/themes, RichText, gamepad/touch navigation, UIDragDetector, CanvasGroup, tweens, BillboardGui/SurfaceGui, React-lua/Fusion/Vide. Use when building HUDs, menus, shops, inventories, or fixing UI that breaks on mobile, console, or other screen sizes.
What it loads into context
Frontmatter
102 tokensAlways available to the agent
SKILL.md
2,046 tokensWhen the skill is activated
Reference documents
1,080 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Foundations
- Layout
- Styling: StyleSheets (CSS-like)
- Cross-platform input in UI
- Text
- Animation and feel
- World-space UI
- Frameworks
- Performance
- Related skills
Files
SKILL.mdcore7,843 bytesreferences/styling-and-frameworks.mddoc4,198 bytes
Read SKILL.md
# Roblox UI
## Foundations
- Put UI in `StarterGui` as `ScreenGui`s (copied to each player's `PlayerGui`), or create it from a
client controller. UI code is client-only; the server never touches `PlayerGui` in normal designs.
- `ScreenGui` defaults to set: `ResetOnSpawn = false` (keep UI across deaths), `ZIndexBehavior = Sibling`,
`IgnoreGuiInset` per design, `ScreenInsets = CoreUISafeInsets` for interactive UI (clears notches and
the Roblox top bar); `DeviceSafeInsets`/`None` only for full-bleed backgrounds.
- **Size and position with Scale** (`UDim2.fromScale`) plus constraints; use Offset only for fixed
details (padding, strokes, icons). Pure-Offset UI breaks on phones and 4K screens.
- `AnchorPoint = Vector2.new(0.5, 0.5)` + `Position = UDim2.fromScale(0.5, 0.5)` centers an element.
- `UIAspectRatioConstraint` keeps shapes square/consistent; `UISizeConstraint` caps sizes;
`UITextSizeConstraint` with `TextScaled` bounds text size (prefer fixed `TextSize` + `AutomaticSize`View the complete source on GitHubroblox-world-building
When your agent uses it
Building worlds with code - parts, models and pivots, materials, Lighting (LightingStyle, Atmosphere, post-processing), day/night, Terrain API, in-game CSG and destruction (GeometryService Subtract/Union/Fragment), ProceduralModel, EditableMesh/EditableImage, particles/beams/trails/highlights. Use when creating maps, environments, lighting, destructible objects, procedural levels, or visual effects.
What it loads into context
Frontmatter
94 tokensAlways available to the agent
SKILL.md
1,837 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Parts and models
- Lighting
- Terrain
- In-game solid modeling and destruction (GeometryService)
- ProceduralModel (parameter-driven models)
- Runtime meshes and images
- Effects
- Related skills
Files
SKILL.mdcore7,131 bytes
Read SKILL.md
# World building with code
## Parts and models
```luau
--!strict
local function makePart(size: Vector3, cframe: CFrame, props: { [string]: any }?): Part
local part = Instance.new("Part")
part.Anchored = true
part.Size = size
part.CFrame = cframe
part.TopSurface = Enum.SurfaceType.Smooth
part.BottomSurface = Enum.SurfaceType.Smooth
for key, value in props or {} doView the complete source on GitHubSkills included
- roblox-analytics-liveops
- roblox-architecture
- roblox-audio
- roblox-characters-animation
- roblox-code-review
- roblox-data-stores
- roblox-game-systems
- roblox-input
- roblox-luau
- roblox-monetization
- roblox-networking
- roblox-npc-ai
- roblox-open-cloud
- roblox-performance
- roblox-physics
- roblox-security
- roblox-studio-mcp
- roblox-teleport-matchmaking
- roblox-testing
- roblox-text-chat
- roblox-tooling
- roblox-ui
- roblox-world-building
Repository facts
- License
- MIT
- Created
- Sep 28, 2026
- Last pushed
- Nov 3, 2026
- Forks
- 7
- Open issues
- 1
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 14 notes
skills/roblox-analytics-liveops/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-analytics-liveops/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-audio/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-characters-animation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-data-stores/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-data-stores/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-npc-ai/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-open-cloud/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-studio-mcp/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-studio-mcp/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-text-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-text-chat/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-tooling/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/roblox-tooling/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 3 dangerous shell commandsin 3 files: scripts/install.sh:107 roblox-tooling/SKILL.md:34 roblox-tooling/references/ci-workflow.md:22
- 43 network referencesin 7 files: roblox-testing/references/cloud-test-runner.md:34 roblox-tooling/references/ci-workflow.md:20 roblox-open-cloud/SKILL.md:8 and 4 more
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: scripts/install.sh:1
- 15 references to secretsin 4 files: roblox-testing/references/cloud-test-runner.md:39 roblox-open-cloud/SKILL.md:58 roblox-open-cloud/references/webhooks.md:15 and 1 more
- No requests to vote in Hot
Show all 62 signals by file
.claude-plugin/plugin.json
- Network accessline 6
"name": "EL4CTEO" }, "homepage": "https://github.com/EL4CTEO/roblox-skills", - Network accessline 7
}, "homepage": "https://github.com/EL4CTEO/roblox-skills", "repository": "https://github.com/EL4CTEO/roblox-skills", - Network accessline 8
"homepage": "https://github.com/EL4CTEO/roblox-skills", - Network accessline 9
"repository": "https://github.com/EL4CTEO/roblox-skills",
scripts/install.sh
skills/roblox-luau/references/type-system.md
- Network accessline 3
Authoritative spec: <https://luau.org/typecheck>. Everything here type-checks under the new solver in `--!strict`.
skills/roblox-open-cloud/SKILL.md
- Network accessline 8
Base URL: `https://apis.roblox.com`. Prefer **Open Cloud** endpoints (API key or OAuth 2.0, stable). - Network accessline 57
# Read one player's data store entry curl -s "https://apis.roblox.com/cloud/v2/universes/$UNIVERSE_ID/data-stores/PlayerData/entries/User_$USER_ID" \ - Network accessline 58
[Credential-related source omitted] - Access to secretsline 58
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Network accessline 61
# Announce to all live servers (the game subscribes to the "Announcements" topic) curl -s -X POST "https://apis.roblox.com/cloud/v2/universes/$UNIVERSE_ID:publishMessage" \ - Network accessline 62
[Credential-related source omitted] - Access to secretsline 62
[Credential-related source omitted] - Access to secretsline 63
[Credential-related source omitted] - Network accessline 102
local ok, response = pcall(function() return HttpService:RequestAsync({ Url = `https://apis.roblox.com/cloud/v2/universes/{universeId}/user-restrictions/{userId}?updateMask=gameJoinRestriction`, - Network accessline 103
return HttpService:RequestAsync({ Url = `https://apis.roblox.com/cloud/v2/universes/{universeId}/user-restrictions/{userId}?updateMask=gameJoinRestriction`, Method = "PATCH", - Network accessline 104
Url = `https://apis.roblox.com/cloud/v2/universes/{universeId}/user-restrictions/{userId}?updateMask=gameJoinRestriction`,
skills/roblox-open-cloud/references/webhooks.md
skills/roblox-studio-mcp/references/client-setup.md
skills/roblox-testing/references/cloud-test-runner.md
- Network accessline 34
## Driver (bash + curl + jq) - Network accessline 38
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Network accessline 40
API=https://apis.roblox.com - Network accessline 42
# 1. Upload the built test place as a new saved version. VERSION=$(curl -sf -X POST \ - Network accessline 43
[Credential-related source omitted] - Access to secretsline 43
[Credential-related source omitted] - Access to secretsline 45
[Credential-related source omitted] - Network accessline 48
# 2. Start the task. TASK=$(jq -n --rawfile script scripts/run-tests.luau '{script: $script, timeout: "300s"}' | curl -sf -X POST \ - Network accessline 49
TASK=$(jq -n --rawfile script scripts/run-tests.luau '{script: $script, timeout: "300s"}' | curl -sf -X POST \ "$API/cloud/v2/universes/$UNIVERSE_ID/places/$PLACE_ID/versions/$VERSION/luau-execution-session-tasks" \ - Network accessline 50
[Credential-related source omitted] - Access to secretsline 50
[Credential-related source omitted] - Access to secretsline 52
[Credential-related source omitted] - Network accessline 54
[Credential-related source omitted] - Network accessline 55
[Credential-related source omitted] - Network accessline 56
[Credential-related source omitted] - Access to secretsline 56
[Credential-related source omitted] - Network accessline 65
[Credential-related source omitted] - Network accessline 66
[Credential-related source omitted] - Access to secretsline 66
[Credential-related source omitted]
skills/roblox-tooling/SKILL.md
- Dangerous shell operationline 34
Install Rokit: `curl -sSf https://raw.githubusercontent.com/rojo-rbx/rokit/main/scripts/install.sh | bash` - Network accessline 34
Install Rokit: `curl -sSf https://raw.githubusercontent.com/rojo-rbx/rokit/main/scripts/install.sh | bash` - Network accessline 89
- **luau-lsp** (editor + CLI) — type checking against Roblox definitions. CLI: `luau-lsp analyze --definitions=@roblox=globalTypes.d.luau --sourcemap=sourcemap.json --base-luaurc=.luaurc src/` (definitions: `https://raw.githubuserconten - Network accessline 90
`luau-lsp analyze --definitions=@roblox=globalTypes.d.luau --sourcemap=sourcemap.json --base-luaurc=.luaurc src/` (definitions: `https://raw.githubusercontent.com/JohnnyMorganz/luau-lsp/main/scripts/globalTypes.d.luau`). Enable the new - Network accessline 91
(definitions: `https://raw.githubusercontent.com/JohnnyMorganz/luau-lsp/main/scripts/globalTypes.d.luau`).
skills/roblox-tooling/references/ci-workflow.md
- Network accessline 20
- name: Install Rokit and tools run: | curl -sSf https://raw.githubusercontent.com/rojo-rbx/rokit/main/scripts/install.sh | bash - Network accessline 21
run: | curl -sSf https://raw.githubusercontent.com/rojo-rbx/rokit/main/scripts/install.sh | bash echo "$HOME/.rokit/bin" >> "$GITHUB_PATH" - Dangerous shell operationline 22
curl -sSf https://raw.githubusercontent.com/rojo-rbx/rokit/main/scripts/install.sh | bash - Network accessline 22
curl -sSf https://raw.githubusercontent.com/rojo-rbx/rokit/main/scripts/install.sh | bash - Network accessline 40
- name: Type check run: | curl -fsSL -o globalTypes.d.luau \ - Network accessline 41
run: | curl -fsSL -o globalTypes.d.luau \ https://raw.githubusercontent.com/JohnnyMorganz/luau-lsp/main/scripts/globalTypes.d.luau - Network accessline 42
curl -fsSL -o globalTypes.d.luau \ - Network accessline 43
https://raw.githubusercontent.com/JohnnyMorganz/luau-lsp/main/scripts/globalTypes.d.luau - Access to secretsline 67
[Credential-related source omitted] - Network accessline 78
- name: Publish place version run: | curl --fail -X POST \ - Network accessline 79
run: | curl --fail -X POST \ "https://apis.roblox.com/universes/v1/${{ vars.UNIVERSE_ID }}/places/${{ vars.PLACE_ID }}/versions?versionType=Published" \ - Network accessline 80
curl --fail -X POST \ - Network accessline 81
"https://apis.roblox.com/universes/v1/${{ vars.UNIVERSE_ID }}/places/${{ vars.PLACE_ID }}/versions?versionType=Published" \ - Access to secretsline 82
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 58 facts
- Executable script in code of a file that runsscripts/install.sh:1High confidence
- Dangerous shell operation in code of a file that runsscripts/install.sh:107High confidence
- Network access in prose of documentationroblox-luau/references/type-system.md:3Low confidence
- Network access in prose of the SKILL.mdroblox-open-cloud/SKILL.md:8Low confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:57High confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:58High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueroblox-open-cloud/SKILL.md:58Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueroblox-open-cloud/SKILL.md:59Low confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:61High confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:62High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueroblox-open-cloud/SKILL.md:62Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueroblox-open-cloud/SKILL.md:63Low confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:102High confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:103High confidence
- Network access in code of the SKILL.mdroblox-open-cloud/SKILL.md:104High confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-open-cloud/references/webhooks.md:15Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-open-cloud/references/webhooks.md:52Low confidence
- Network access in code of documentationroblox-studio-mcp/references/client-setup.md:55Low confidence
- Network access in code of documentationroblox-studio-mcp/references/client-setup.md:56Low confidence
- Network access in prose of documentationroblox-testing/references/cloud-test-runner.md:34Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:38Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-testing/references/cloud-test-runner.md:39Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:40Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:42Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:43Low confidence
- Access to secrets in code of documentationroblox-testing/references/cloud-test-runner.md:43Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-testing/references/cloud-test-runner.md:45Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:48Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:49Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:50Low confidence
- Access to secrets in code of documentationroblox-testing/references/cloud-test-runner.md:50Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-testing/references/cloud-test-runner.md:52Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:54Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:55Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:56Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-testing/references/cloud-test-runner.md:56Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:65Low confidence
- Network access in code of documentationroblox-testing/references/cloud-test-runner.md:66Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valueroblox-testing/references/cloud-test-runner.md:66Low confidence
- Dangerous shell operation in prose of the SKILL.mdroblox-tooling/SKILL.md:34Low confidence
- Network access in prose of the SKILL.mdroblox-tooling/SKILL.md:34Low confidence
- Network access in prose of the SKILL.mdroblox-tooling/SKILL.md:89Low confidence
- Network access in prose of the SKILL.mdroblox-tooling/SKILL.md:90Low confidence
- Network access in prose of the SKILL.mdroblox-tooling/SKILL.md:91Low confidence
- Network access in code of documentationroblox-tooling/references/ci-workflow.md:20Low confidence
- Network access in code of documentationroblox-tooling/references/ci-workflow.md:21Low confidence
- Dangerous shell operation in code of documentationroblox-tooling/references/ci-workflow.md:22Low confidence
- Network access in code of documentationroblox-tooling/references/ci-workflow.md:22Low confidence
- Network access in code of documentationroblox-tooling/references/ci-workflow.md:40Low confidence
- Network access in code of documentationroblox-tooling/references/ci-workflow.md:41Low confidence
and 8 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/roblox-analytics-liveops/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md skills/roblox-analytics-liveops/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/roblox-analytics-liveops/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md skills/roblox-analytics-liveops/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.