Decentraland SDK7 Scene Development
Runtime constraint: Decentraland runs in a QuickJS sandbox. No Node.js APIs (
,
,
,
). Use
+
for async work.
Agent Behavioral Guidelines
Before taking any significant action, check whether it falls into one of the three categories below and confirm with the user first.
How to ask: Phrase the question in plain, non-technical language that describes what will happen to the scene, not the underlying command.
Good:
"Should I download this tree model into your scene assets?"
Bad:
"Run curl https://… -o assets/Models/tree.glb
?"
1. Changing parcel count or layout
Any modification to
in scene.json changes the scene's coordinate space. Entities near the current boundary may end up outside (invisible) or inside the wrong parcel. The user may also have a deployment slot in mind and parcel count needs to match it. Describe the change and its effect before acting:
"To fit the scene you described, I'd need to expand from 1 parcel (16×16 m) to a 2×1 layout (32×16 m). This changes the coordinate bounds for every entity. Should I go ahead?"
2. Fetching assets from external sources
Downloading any file not already in the project — 3D models (.glb), images, audio, video. The user may have their own assets in mind, may not want new files added, or may be targeting a specific visual style. Confirm before downloading:
"I'd like to download a [description] model from [source] and add it to your scene. Should I go ahead?"
For streaming references (
,
): these don't download files but do add an external URL dependency. Confirm if the URL wasn't provided by the user:
"I'd set up a video stream from [source]. Is that the one you want to use?"
3. Adding a Multiplayer Server
Introduces
,
,
,
, or switches to
. This feature requires switching to an alternative SDK branch (
). Many users who want "multiplayer" only need the simpler
skill (no server). Confirm before implementing:
"To handle multiplayer this way I'd need to add the Multiplayer Server — that requires switching to the
SDK branch instead of the standard one. Is that what you're after, or would simpler peer-to-peer sync work for your use case?"
General principle
These aren't things the agent should refuse to do — they're things it should communicate about before doing them. If the user confirms, proceed confidently. The goal is transparency, not gatekeeping.
CRITICAL RULE — Composite-first scene authoring
All static entities (models, lights, spawn points) MUST be defined in
assets/scene/main.composite
, NOT created in TypeScript via
.
TypeScript (
) is ONLY for:
- Dynamic behavior (systems, event handlers, state changes)
- Referencing composite entities via
getEntityOrNullByName('name')
or
- Entities that are truly runtime-only (spawned/despawned during gameplay)
CRITICAL RULE — Editing an existing composite
Before modifying
assets/scene/main.composite
, scan it for
. If present, the user has opened the scene in the Creator Hub at least once and the file is in
edit mode: every new entity you add MUST be registered in
, or it will render in-world but be
invisible and un-selectable in the Creator Hub entity tree. See the "Editing an existing composite (edit mode)" section of
{baseDir}/../composites/composite-reference.md
for the exact procedure.
The scene must NOT be open in the Creator Hub while you edit the composite. The inspector autosaves by default and regenerates the whole
from its in-memory engine, overwriting the file wholesale — it never re-reads it from disk. Your edits will silently vanish. Ask the user to close the scene first, then reopen it when you are done.
Individual Skills
This skill is the entry point. The detailed implementation guidance lives in individual topic skills, each installable separately. Install specific ones or use
for all.
Scene Setup & Configuration
Skill: — Scaffolding,
schema, multi-parcel layouts, composite vs TypeScript entity rules.
3D Models
Skill: — Loading
/
with
, positioning, colliders, and browsing the free asset catalogs (8,800+ models).
Animations & Tweens
Skill: — GLTF animation clips with
, programmatic
and
, easing functions.
Materials & Rendering
Skill: — PBR materials,
,
,
, texture modes.
Lighting & Environment
Skill: — Point/spot lights, shadows,
(day/night cycle), emissive materials.
Particle Systems
Skill: —
component for fire, smoke, sparks, snow, rain, magic, fireworks. Emitter shapes (Point/Sphere/Cone/Box), continuous rate vs Burst emission, gravity, sprite-sheet animation, blend modes.
Click & Proximity Interactivity
Skill: —
, trigger areas, raycasting. For polling-based input see
.
Advanced Input & Movement Control
Skill: —
polling, WASD-controlled entities,
,
,
.
Player & Avatar
Skill: — Player position/profile, emotes, wearables,
,
.
NPCs
Skill: —
NPCs and the NPC Toolkit library for GLB-based NPCs with dialogue and state machines.
Player Physics
Skill: — Impulse forces, knockback, repulsion fields.
Camera
Skill: — Camera state,
,
for cinematic shots.
Screen-Space UI
Skill: — React ECS components for 2D screen-space UI overlays: layout, text, images, buttons, inputs.
Audio & Video
Skill: —
,
,
, media permissions.
Audio Analysis (Reactive Visualizers)
Skill: —
component for real-time amplitude + 8-band frequency data from any
/
/
. Drive scale, color, lights, and particles from music. Unity-explorer only.
Blockchain & NFTs
Skill: —
, wallet checks, token gating, signed requests, smart contracts.
Multiplayer (CRDT, no server)
Skill: —
for peer-to-peer sync,
, parent-child sync.
Multiplayer Server
Skill: — Headless server,
,
,
,
. Requires
.
Script Components (Creator Hub)
Skill: — Writing
script files for the Creator Hub Script component, constructor parameters,
JSDoc tags (never decorator syntax).
Async, HTTP, WebSocket, Timers
Skill: —
,
,
, WebSocket, timers, realm/scene info, restricted actions.
Scene Optimization
Skill: — Scene limits, object pooling, LOD, texture optimization, system throttling.
Game Design
Skill: — DCL design philosophy, state management, UX guidelines, game loop archetypes, MVP planning.
Deployment
- Skill: — Genesis City deployment, , troubleshooting.
- Skill: — Personal Worlds, , ENS/DCL NAME requirements.
SDK6 → SDK7 Migration
Skill: — Port legacy
scenes to SDK7. Conceptual ECS shift (entities as IDs, data-only components, mutable/immutable access), full API mapping (
→
,
→
,
→
,
classes → free functions,
→
, etc.), and an annotated before/after example.
Shared References
These reference files are used across multiple skills. Load them when you need detailed component APIs, validation rules, or asset catalogs.
Components Reference
Reference: {baseDir}/references/components-reference.md
Quick-reference of key fields, types, and defaults for the SDK7 components you'll commonly use. For a component's complete field list, consult its dedicated skill or the SDK typings.
Entity Validation Rules
Reference: {baseDir}/../create-scene/references/entity-validation-rules.md
Rules for validating entity component combinations — which components require each other, mutual exclusions, and common misconfigurations. Apply to both composite and TypeScript entities.
Free Asset Catalogs
- 3D Models (8,800+ models):
{baseDir}/../add-3d-models/references/model-catalog.md
— optimized 3D models with descriptions, dimensions, animations, and download URLs
- Audio (50 sounds):
{baseDir}/../audio-video/references/audio-catalog.md
— Music, Ambient, SFX, Game Mechanics, UI sounds
Composites
Reference: {baseDir}/../composites/composite-reference.md
The
JSON format for declaring initial scene entities. Includes
and
patterns for fetching composite entities in TypeScript.
Library References
- NPC Toolkit:
{baseDir}/../npcs/references/npc-library.mdc
— GLB-based NPCs with dialogue, movement, state machines
- Blockchain/NFT patterns:
{baseDir}/../nft-blockchain/references/blockchain-patterns.md
— NFT display, wallet checks, MANA operations, currency/NFT transactions, marketplace integration (dcl-crypto-toolkit)
How to use
- Identify the topic from the user's request
- Load the corresponding skill — it contains the full API, code patterns, and rules
- For broad requests spanning multiple topics, load each relevant skill
- For asset discovery, load the relevant catalog and suggest specific assets before fetching any