How do I install Skills?

Copy the stdio config for Cursor, Claude Desktop, Claude Code, or VS Code on this page. It uses the publisher's install, not a PlugMCP proxy.

Does Skills need an API key?

No required environment variable is listed on this record.

What transport does Skills use?

Skills runs locally over stdio.

Skills MCP server

Q: When was Skills last checked?

Last checked 2026-10-27. Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

Power your agent

Add this server

Install from the publisher. Not a PlugMCP endpoint.

Run on PlugMCP

Host a copy with our keys and logs.

No packaged release in the registry yet. Follow the repository README.

RepositoryPublisher installStep-by-step: add this in Claude

Remote URL or a command on your machine? How the two installs differ

Run on PlugMCP

Host a copy with our keys and logs.

A new server you create. It is not this listing's official endpoint. Use the publisher install when you want their URL and their credentials.

Launch

Server facts

Local

Transport: stdio
License: MIT
Last checked: 2026-10-27

Overview

About Skills

Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plus expert teams that drive Blender, Maya, ZBrush, Unreal, and Unity.

Tools

No tool list yet. Remote servers get one after the first health check.

FAQ

Agent Skills that teach AI coding agents (Claude Code, Cursor, Codex, Copilot, and 70+ others) how to create production-ready content with Scenario through the Scenario MCP server: images, video, audio, textures, skyboxes, 3D assets, and custom-trained models, for games, entertainment, and any creative vertical.

The expert tools at the bottom of the list work differently: teams of skills that drive DCC (digital content creation) software and game engines installed on your machine (ZBrush, Blender, Maya, Unreal Engine, Unity, Godot, Roblox Studio), distilled from expert tutorials, conference talks, and official documentation. They need the application, not the Scenario MCP server, and each family folder's README records how it was built and how far it was verified.

Skills follow the Agent Skills format.

Install

Everything for Scenario. Every Scenario skill, without the expert tools: the default for working through the Scenario MCP.

# Every Scenario skill, without the expert tools
npx skills add scenario-labs/skills --skill scenario scenario-inspiration scenario-image scenario-multi-reference scenario-product-shots scenario-brand-kit scenario-image-editing scenario-text-overlay scenario-storyboards scenario-game-assets scenario-sprite-animation scenario-side-view-game-kit scenario-blender-2d-animation scenario-textures scenario-skyboxes scenario-3d scenario-video-to-motion scenario-blender scenario-patina-retexture scenario-orbit-views scenario-walkable-room scenario-video scenario-video-editing scenario-video-color-grade scenario-seedance-music-video scenario-kinetic-music-video scenario-chatgpt-pet-create scenario-chatgpt-pet-update scenario-seedance-storyboard scenario-seedance-drafts scenario-video-ads scenario-ugc scenario-fan-cam scenario-reel-recast scenario-audio scenario-video-assembly scenario-motion-loops scenario-caption-studio scenario-consistency scenario-identity-library scenario-model-training scenario-asset-analysis scenario-quality-gate scenario-refine-loop scenario-model-comparison scenario-formats scenario-workflows scenario-workflow-authoring scenario-moderation scenario-report scenario-team-admin scenario-admin-analytics scenario-gpt-image scenario-mai-image scenario-seedream scenario-gemini-image scenario-reve scenario-ideogram scenario-grok-imagine-image scenario-luma-image scenario-minimax-video scenario-gemini-omni scenario-grok-imagine-video scenario-veo scenario-seedance scenario-kling scenario-vidu scenario-wan scenario-runway scenario-luma-video scenario-minimax-music scenario-elevenlabs scenario-ace-step scenario-sonilo scenario-meshy scenario-rodin scenario-sparc3d scenario-3d-worlds scenario-ad-variants scenario-thumbnails

By role or goal. INSTALL.md groups the skills by job, from 2D artist to producer, and by outcome, from game art to ChatGPT pets, with one command each.

Expert tools. A family installs as one set, since its specialists import the lead skill's scripts: select its "Expert tools" group in the installer menu, or run the command in its family README (ZBrush, Blender, Maya, Unreal Engine, Unity, Godot, Roblox Studio).

Pick, or install one skill.

# Pick from the installer menu, grouped by topic (it opens with nothing preselected: select before pressing enter)
npx skills add scenario-labs/skills

# A single skill
npx skills add scenario-labs/skills --skill scenario

The menu's topic groups cannot be selected from the command line: the CLI matches --skill against exact skill names only, and a group flag is an open request upstream (vercel-labs/skills#992). From a script or CI, run the default command above or a role command from INSTALL.md with -y, which skips every prompt.

The Scenario skills need the Scenario MCP server connected:

claude mcp add --transport http scenario https://mcp.scenario.com/mcp

Or add https://mcp.scenario.com/mcp to any MCP client and sign in with a Scenario account (OAuth), or use an API key. Full setup lives in the scenario skill.

Staying up to date

Installs always fetch the latest copy of each skill from main; there is no version pinning. Releases are how changes become visible: every feature, fix, and documentation change merged to main lands in the next release, staged by release-please as an open release PR. Merging that PR tags a version, updates CHANGELOG.md in this repository, publishes a GitHub release, and posts the notes to the Scenario changelog.

To learn that a skill changed, watch this repository's releases (Watch, then Custom, then Releases on GitHub) or check any of the changelog pages above. An entry scoped to a single skill carries that skill's name; changes spanning several skills appear under broader scopes such as skills.
To pull the changes, run npx skills update where you installed, or re-run your original npx skills add command.

Skills

Getting started

Connect the Scenario MCP server and learn the core generation loop every other skill builds on.

Skill	Use it for
scenario	Connecting to the Scenario MCP and the core generation loop: discover, schema, run, wait, display, download

Finding a direction

Turn a blank brief into references, options someone can choose between, and a moodboard the next batch runs from.

Skill	Use it for
scenario-inspiration	Finding a direction before generating: serendipity, reference hunting, A/B/C/D concept options, moodboard collections

Images

Generate and edit images: model choice, sizing, references, masked edits, post-processing tools, and letter-perfect text overlay cards.

Skill	Use it for
scenario-image	Text-to-image and image editing: model choice, sizing fields, prompt limits, reference images, masked inpainting
scenario-multi-reference	One image composed from several references, each with one job (subject, place, pose, style, palette), leaks checked
scenario-product-shots	Product photography from a real photo: packshots, lifestyle scenes, relighting, label-fidelity gates
scenario-brand-kit	Visual identities: SVG logos and wordmarks, palette and type specs, gated variants and applications, the filed kit
scenario-image-editing	Tool-model image edits: 3D LUT grades, effects, expand and reframe, resize, slicing, layers, background removal
scenario-text-overlay	Letter-perfect text overlays: templated transparent PNG cards (taglines, CTAs, legal supers, rich cards) to composite
scenario-storyboards	Comic pages, storybooks, and pre-viz storyboards: script first, one run per panel, a locked cast, lettering in post
scenario-thumbnails	Finished video covers with character fidelity, exact copy and small-preview readability

Game art and 3D

Sprites, icons, tilesets, textures, skyboxes, 3D models, and walkable spaces for games, the web, and interactive scenes.

Skill	Use it for
scenario-game-assets	Sprites, icons, props, tilesets, pixel art, concept art, transparent backgrounds, style-consistent batches
scenario-sprite-animation	Walk cycles, idle loops, VFX sprites, and animation sheets from one prompt: GIF vs sprite sheet output, frame slicing, pixel cleanup
scenario-side-view-game-kit	Side-scroller and platformer art: side-view pixel sprite strips for a hero and enemies (run, walk, attack, hurt, poses), parallax layers, seamless wall texture, platform strip, props
scenario-blender-2d-animation	A side-scroller shot animated in Blender from Scenario pictures: a concept frame that locks the look, parallax layers, props and a hero run cycle on its reference, flat image cards with an orthographic camera, keyed jumps and rigid-body props, and a whole new look by swapping the pictures
scenario-textures	Seamless and tileable textures, PBR materials, tiling-safe upscaling, engine-ready sizing
scenario-skyboxes	360 equirectangular panoramas and skyboxes, seam-safe upscaling, engine export
scenario-3d	Text or image to 3D meshes, multi-view reconstruction, retexture and remesh, inline 3D preview, GLB/FBX download
scenario-video-to-motion	Motion capture from a reference or generated video: an uploaded character auto-rigged and animated, or motion alone on a Mixamo or MetaHuman skeleton, with in-place, looping, and engine-ready exports

Video and audio

Video generation, editing, and color grading, seamless motion loops, music, sound effects, voice, and speech.

Skill	Use it for
scenario-video	Text-to-video and image-to-video, motion prompting, lipsync, video editing, upscaling, cut/split/concat utilities
scenario-video-editing	Tool-model footage edits: LUT grades and effects, trim, split, resize, reverse, frames, masks, layers
scenario-video-color-grade	Code-written grades on existing footage: looks, relight, log to Rec.709, reference match, one kept color with masks, .cube LUTs, a showreel
scenario-seedance-music-video	Turning a song into a music video: beat-aligned shots, lyric transcription, shot sound under the master, assembly
scenario-seedance-storyboard	Movement that holds across cuts: timecoded shot scripts, character sheets and boards, pose-chained shots that play as one performance
scenario-seedance-drafts	Cheap 480p Seedance takes reviewed and ranked, only the picks finalized to 1080p, with the draft-versus-final cost math
scenario-video-ads	Producing a video ad from a product shot: brief, storyboard, cinematic grammar, fidelity gates, budget, delivery
scenario-ad-variants	Ordered independent campaign edits from existing footage, preserving original gameplay and audio
scenario-audio	Music, sound effects, voice and speech generation, video scoring, audio utilities

Socials

Made for social feeds and chat apps: UGC-style creator videos, fan-cam reactions from a photo, trend reels recast with your own character, kinetic-typography lyric videos, and animated ChatGPT and Codex pets, new or updated.

Skill	Use it for
scenario-ugc	UGC-style creator video: talking-head and avatar ads, demos, faceless voiceover, spoken-register scripts, claim safety
scenario-fan-cam	Personalized fan-cam clips: identity edit into a broadcast still, reaction beats to video, graphics composited in post
scenario-reel-recast	A trending reel performed again by your character: same moves, camera and song, outfit swaps, a redecorated room
scenario-kinetic-music-video	Kinetic-typography music video, landscape or 9:16: style frames and footage from Scenario, a JavaScript engine for lyric type on sung onsets, mattes, per-section agents
scenario-chatgpt-pet-create	ChatGPT or Codex pet from an idea or photos: a v2 sprite sheet with sixteen look directions, a v1 copy for web upload, pixel-perfect mode, GIFs, a Codex package
scenario-chatgpt-pet-update	Change an existing pet sheet: fix or redo a row, add look directions to a v1 sheet, a new outfit or color, a rename, a check and GIF preview

Consistency and custom models

Hold one character, product, or style across a whole set, and train custom models on your own art.

Skill	Use it for
scenario-consistency	Holding one character, product, or style across a set: baseline-plus-delta prompts, reference images, control maps
scenario-identity-library	Creating named characters and props as reusable identities: interview to brief, gated collections, Grid Maker sheets, reuse
scenario-model-training	Training custom models for style, character, or product consistency, and generating with them

Reviewing and organizing output

Read finished assets back: caption them, extract a style or a control map, check a batch against a brief or the Quality Gate, compare candidate models on one brief, and file the keepers.

Skill	Use it for
scenario-asset-analysis	Reading assets back: captions, style descriptions, batch review against a brief, control maps, collections, tags
scenario-quality-gate	Pass/warn/fail image verdicts from the Quality Gate: free stored reads, dry-run pricing, feeding suggestions back into the next run
scenario-refine-loop	Iterating until output matches the brief: rubric first, batched critique verdicts, cheapest targeted fix, round caps
scenario-model-comparison	Bake-offs between candidate models on one brief: normalized inputs, a dry-run cost matrix, billed cost and latency, contact sheets, pre-registered criteria

Formats and placements

Ship one approved master, image or video, to every placement: ratios, safe zones, and platform specs from social feeds to shops, storefronts, and print.

Skill	Use it for
scenario-formats	Deriving every placement from one master, image or video: crop vs resize vs expand vs reframe, platform specs and safe areas

Workflows and apps

Discover, run, build, and publish Scenario workflows (apps), and migrate graphs from Weavy, ComfyUI, or other node editors.

Skill	Use it for
scenario-workflows	Running saved workflows (apps): building the run inputs, dry-run pricing, unsticking approval gates
scenario-workflow-authoring	Creating and editing workflow graphs: editor_info grammar, node wiring, publishing apps, and migrating graphs from Weavy, ComfyUI, or other node editors

Troubleshooting

Get past a blocked generation, and turn a stuck session into a reproducible public issue.

Skill	Use it for
scenario-moderation	Recovering a blocked generation: provider-side filters, model switching, proportional wording, look-alike errors
scenario-report	Reporting a bug or change request as a reproducible, redacted issue on this repository's public tracker

Team administration

Govern a team from the agent: which models it can run, who is on it and in which projects, per-member spend caps, API key roles, and who spent what.

Skill	Use it for
scenario-team-admin	Model access control, team and project membership, per-member Creative Unit caps, API key roles, and spend attribution
scenario-admin-analytics	Cached MCP usage analytics, model and user rankings, CSV exports, adoption PDFs, and a local dashboard

Image model families

The top image families in depth: generation and editing modes, reference rules, and the caps that differ per member.

Skill	Use it for
scenario-gpt-image	GPT Image 2.5 Flare and Sunburst, GPT Image 2 and 1.5: member routing, the quality tiers up to max and their price ladder, alpha masks, transparent cutouts, in-image text, pixel sizing
scenario-mai-image	MAI Image: in-image typography, quoted copy prompts, instruction editing (preserve first, one change), per-editor source input shapes, edit cost split
scenario-seedream	Seedream images: member selection (Pro, Lite, 4.5, Layerize), per-member sizing contracts, in-image text, sequence sets, layer splits, cost
scenario-gemini-image	Gemini image (Nano Banana): member choice (Flash, Pro, Lite), instruction editing, reference roles, video stills, Search grounding, cost
scenario-reve	Reve image: v2.1 vs Remix selection, frame-tag reference wiring, maskless instruction edits, per-member caps and cost
scenario-ideogram	Ideogram images: member selection (4.5 typography and edits, Precise Edit, native transparency, layerize text, character, remove background), the 4.5 quality price ladder and sizes, edits that keep the exact canvas, expansion off for exact copy
scenario-grok-imagine-image	Grok Imagine images: text-to-image and instruction editing, exact in-image typography, quoted copy rules, aspect ratio traps, quality and cost tiers
scenario-luma-image	Luma Uni-1 images: create vs edit mode, role-labeled references, web search grounding, rendered text, cost

Video model families

The top video families in depth: conditioning modes, native audio, editing and extension, and per-member caps and costs.

Skill	Use it for
scenario-minimax-video	MiniMax Hailuo video: H3 keyframe vs reference modes, bracketed camera commands, native audio prompting, 2.3 duration coupling, cost
scenario-gemini-omni	Gemini Omni video: member selection (first frame, references, edit, extend), prompted native audio, identity from references, motion-locked restyles
scenario-grok-imagine-video	Grok Imagine video: one member per mode (first frame, @image references, edit, extend), prompted audio and dialogue, resolution and preprocessing caps
scenario-veo	Veo video: mode selection (first frame, transitions, references, extend), asset or style references, prompt-directed native audio, tier costs
scenario-seedance	Seedance video: mode selection (first frame, references, edit, extend), conditioning traps, native sound, cost
scenario-kling	Kling video: picking a member across V3, O1, and 2.6 (multi-shot, elements, editing, motion control, lipsync, avatar), audio exclusivity, tier cost
scenario-vidu	Vidu video: tier and mode selection (text, image, start/end frames, references), per-tier caps, two prompt shapes, music toggle traps
scenario-wan	Wan video: member-per-job selection (T2V, I2V, edit, Animate, reframe, outpainting), parameter drift across generations, multi-shot prompts, audio sources
scenario-runway

Audio model families

The top audio families in depth: music, covers and stems, sound effects, speech, dubbing, and video scoring.

Skill	Use it for
scenario-minimax-music	MiniMax music: vocal songs from a tagged lyric sheet, auto lyrics, instrumental mode, melody-keeping covers, character-count cost
scenario-elevenlabs	ElevenLabs audio: picking the member (TTS, music, SFX, dubbing, re-voicing, isolation), voice and tag rules, song section grammar, cost
scenario-ace-step	ACE-Step music: one member per mode, Turbo vs Quality lanes, lyric sheet tags, cover strength, repaint windows, stem edits
scenario-sonilo	Sonilo audio: SFX and music from text or video, standalone track vs muxed clip, segment prompts, keep-speech scoring, cost

3D model families

The top 3D families in depth: mesh generation, retexture and rigging toolchains, portraits, and explorable worlds and splats.

Skill	Use it for
scenario-meshy	Meshy 3D: generate from image, multi-view, or text, then retexture, remesh, UV unwrap, rig, or animate; texture precedence, Ultra mode, polycount traps
scenario-rodin	Rodin 3D: member selection (image-to-3D, text-to-3D, Fast lanes, Bang! mesh splitting), full versus Fast parameter dialects, topology and tier traps, cost
scenario-sparc3d	Sparc3D image-to-3D: ordered multi-view input, mesh vs textured output, per-member resolution spellings, face budgets, long-job waits
scenario-3d-worlds	3D worlds and splats: member choice by input (text, image, pano, multi-view, video, object), Marble draft-then-upgrade seed reuse, HY World skybox-to-splat pipeline, long-job patience

Expert tools: ZBrush

DCC software. A lead and eight specialists that drive Maxon ZBrush 2026 through its agent bridge: sculpting, characters and creatures, stylized work, hard surface, polypaint and renders, posing and 3D print, retopology and export, automation. The bridge was proven live; full live tests of every skill are still pending.

Skill	Use it for
scenario-zbrush-expert	ZBrush lead: the agent bridge (launch, scripted strokes, dialog-free export), ZBrush Python and ZScript, review renders, 2026 traps, handoffs to the specialists
scenario-zbrush-automation	ZBrush automation: batch jobs over OBJ or ZTL folders, ZBrush Python and ZScript, macros, UV Master, Decimation Master, Multi Map Exporter, GoZ round trips
scenario-zbrush-character-creature	Realistic heads, bodies, and creatures in ZBrush: anatomy and landmarks, skin, pores, wrinkles and scales, subdivision and HD Geometry planning
scenario-zbrush-hard-surface	Hard surface in ZBrush: ZModeler, Dynamic Subdivision and creasing, Live Boolean, Knife and Slice curves, IMM, ArrayMesh, NanoMesh, Panel Loops
scenario-zbrush-paint-render	Polypaint and renders in ZBrush: color zones, cavity and AO passes, Spotlight, baking to texture or vertex color, BPR or Redshift, turntables
scenario-zbrush-pose-print	Posing and 3D print in ZBrush: Transpose Master, Gizmo posing with masks, ZSphere rigs, print scale, hollowing, wall thickness, drain holes
scenario-zbrush-retopology-export	Sculpt, scan, or AI mesh to production topology and files in ZBrush: ZRemesher and guides, Retopo brush, Project All, UVs, normal and displacement maps, export
scenario-zbrush-sculpting	Organic sculpting in ZBrush: primary and secondary forms, DynaMesh, Sculptris Pro or subdivision levels, core brushes, masks and polygroups

Expert tools: Blender

DCC software. A lead and fourteen specialists that drive Blender 5.2 through Python, headless or in a live session: sculpting, retopology, UVs and baking, shading, hair, rigging, animation, previs, blockouts for render-to-real video, Geometry Nodes, lighting, Grease Pencil, hard surface, export to game engines. Twelve test suites pass headless on Blender 5.2.1.

Skill	Use it for
scenario-blender-expert	Blender lead: Python headless or through a live MCP bridge, the expert review loop, the shared review and mesh-audit toolkit, Blender 5.2 API traps
scenario-blender-animation	Blender animation: cycles, jumps, acting and lip sync, stepped blocking to spline and polish, timing and spacing, graph editor, slotted actions and NLA
scenario-blender-blockout	Blockouts that guide render-to-real video: color-coded proxies at metric scale, cameras locked to the timeline, framing audits, playblast and hand-off sheet
scenario-blender-export	Exports for game engines: FBX, GLB, USDZ and STL presets for Unity, Unreal, Godot, Roblox, three.js, round-trip checks, LODs, collision, batch
scenario-blender-geometry-nodes	Geometry Nodes: procedural modeling, scattering, curves and loops, simulation zones, 5.2 physics, closures and bundles, node-group assets
scenario-blender-grease-pencil	Grease Pencil in Blender 5.x: 2D and 2.5D illustration, frame-by-frame and cutout animation, fills, interpolation, Line Art, strokes on meshes
scenario-blender-hair	Hair and fur with hair curves: hairstyles, animal fur, Essentials hair nodes, density masks and partings, hair cards and mesh hair for games
scenario-blender-hard-surface	Hard surface in Blender: booleans and cutters, bevels, weighted normals, support loops and creases, fixing smeared or pinched shading

Expert tools: Maya

DCC software. A lead and ten specialists that drive Autodesk Maya 2027 through Python, batch or live: modeling, retopology and UVs, rigging, skinning, animation, groom, FX, look dev, Arnold lighting and rendering, pipeline scripting.

Skill	Use it for
scenario-maya-expert	Maya lead: maya.cmds and OpenMaya 2.0, mayapy batch jobs, a commandPort or MCP bridge into a live Maya, scene validation, Maya 2027 traps
scenario-maya-animation	Maya animation: cycles, jumps, heavy lifts, acting and lip sync, stepped blocking to spline and polish, Graph Editor, layers, mocap cleanup, game clips
scenario-maya-deformation	Skinning in Maya: binding and weight painting, Skin Tools or ngSkinTools layers, fixing pinching and volume loss, weights for Unreal or Unity
scenario-maya-fx	Maya FX: nCloth and Nucleus, nParticles, Bifrost smoke, fire, liquids, and MPM, MASH scattering
scenario-maya-groom	Grooming with XGen: scalp hair, brows, lashes, and fur, guides, clumps, and density maps, aiStandardHair, hair that moves
scenario-maya-lighting-rendering	Maya lighting and rendering with Arnold: hero, character, and sequence lighting, noise and fireflies, AOVs and light groups, denoising, color management
scenario-maya-lookdev	Look dev in Maya with Arnold: OpenPBR or aiStandardSurface, Substance and UDIM texture sets, color spaces, normal and displacement fixes, skin, metal, glass
scenario-maya-modeling	Maya modeling: hard-surface props and vehicles, game-ready or SubD models, base meshes, support loops vs bevels vs creases, scene cleanup
scenario-maya-pipeline-scripting

Expert tools: Unreal Engine

Game engine. A lead and nine specialists that drive Unreal Engine 5.8 on macOS through Editor Python, headless jobs, and Epic's Unreal MCP server: world building, materials, lighting and rendering, gameplay, animation, cinematics, VFX, pipeline automation, performance.

Skill	Use it for
scenario-unreal-expert	Unreal lead: Editor Python, headless UnrealEditor-Cmd jobs, Epic's Unreal MCP server, the Remote Control API, console commands, 5.8 traps
scenario-unreal-animation	Unreal animation: skeletal import, IK Rig and Retargeter, Motion Matching and Pose Search, root motion, foot IK, Control Rig
scenario-unreal-cinematics	Unreal cinematics with Sequencer: shot lists, master and shot sequences, cameras and lenses, per-shot lighting, Movie Render Graph output
scenario-unreal-gameplay	Unreal gameplay: characters and abilities, enemy AI, HUD, Blueprint vs C++, GAS, StateTree vs Behavior Tree, Enhanced Input, replication
scenario-unreal-lighting-rendering	Unreal lighting and rendering: physical units and exposure, Lumen, MegaLights, virtual shadow maps, sky and fog, post process, path tracer
scenario-unreal-materials	Unreal materials: master materials and instances, Substrate, glass and emissives, decals, landscape layers and RVT, toon shading, shader permutations
scenario-unreal-performance	Unreal performance: frame budgets, CPU vs GPU bound, hitches and PSO stutter, GC spikes, Lumen, Nanite, VSM, and Niagara cost, profiling
scenario-unreal-pipeline-automation	Unreal pipeline: bulk FBX, USD, OBJ, or glTF import from Maya, ZBrush, or Blender, Editor Python tools, Interchange, naming and validation, cook and package

Expert tools: Unity

Game engine. A lead and thirteen specialists that drive Unity 6.3 LTS on macOS through batch mode, a live editor, and command-line builds: architecture, gameplay, 2D, animation, UI, VFX, shaders, rendering and lighting, world building, performance, mobile, Web, pipeline automation. Every procedure was run live in Unity 6.3.

Skill	Use it for
scenario-unity-expert	Unity lead: batch mode and -executeMethod jobs, a live editor over the Unity CLI, MCP servers, the Test Framework, command-line builds, proof by capture
scenario-unity-2d	Unity 2D in URP: sprite import and PPU, atlases, Tilemaps and Rule Tiles, 2D lights, 2D animation, platformer and top-down controllers
scenario-unity-animation	Unity animation and cameras: humanoid import and retargeting, Animator Controllers and blend trees, root motion, Animation Rigging, Timeline, Cinemachine 3
scenario-unity-architecture	Unity C# architecture: ScriptableObject data, events and services, inventory, health, save and load, Input System, Awaitable, assembly definitions, Git and LFS
scenario-unity-gameplay	Unity gameplay: enemy AI, NavMesh and agents, state machines and behavior trees, projectile physics, collision layers, CharacterController vs Rigidbody
scenario-unity-mobile	Unity on Android and iOS: frame and thermal budgets, texture compression, touch controls and safe areas, startup time, AAB and signing
scenario-unity-performance	Unity performance: frame spikes and hitches, GC, draw and SetPass calls, CPU vs GPU bound, Profiler, Memory Profiler, Frame Debugger, GPU Resident Drawer
scenario-unity-pipeline-automation	Unity content pipeline: AssetPostprocessor import rules, prefab and scene generation from script, Addressables, content-validation tests, CI builds

Expert tools: Godot

Game engine. A lead and thirteen specialists that drive Godot 4.7 on macOS through headless jobs, windowed captures, GUT and gdUnit4 tests, and command-line exports: architecture, gameplay, 2D, 3D worlds, animation, UI, VFX, shaders, rendering and lighting, audio, multiplayer, performance and export, pipeline automation. Every procedure was run live in Godot 4.7.2.

Skill	Use it for
scenario-godot-expert	Godot lead: headless --script jobs, --import and --check-only, windowed captures, GUT tests, command-line exports, MCP into an editor, proof by capture
scenario-godot-2d	Godot 2D: platformer and top-down controllers, TileMapLayer and terrains, pixel-perfect stretch and cameras, 2D lights, y-sort, parallax, AI-generated sprites
scenario-godot-3d-world	Godot 3D levels: third-person and FPS controllers, CSG blockout, GridMap, terrain, MultiMesh scatter, streaming, Jolt physics, GLB imports
scenario-godot-animation	Godot animation: AnimationPlayer and RESET, AnimationTree state machines and blend spaces in code, Mixamo retargeting, root motion, IK, cutscenes
scenario-godot-architecture	Godot code structure: scenes and nodes, signals and event bus autoloads, custom Resources, components, save and load, InputMap rebinding, typed GDScript
scenario-godot-audio	Godot audio: buses and effects, volume sliders, combat with hundreds of enemies, 3D sound and reverb zones, adaptive and interactive music, SFX variation
scenario-godot-gameplay	Godot gameplay: enemy AI that patrols, chases, and attacks, state machines, behavior trees, NavigationAgent3D, hitbox combat, dialogue, procedural dungeons
scenario-godot-multiplayer	Godot multiplayer: ENet and WebSocket host and join, RPCs, MultiplayerSpawner and Synchronizer, authority, lag, lobbies, dedicated servers

Expert tools: Roblox Studio

Game engine. A lead and thirteen specialists that drive Roblox Studio on macOS through its built-in MCP server, playtests driven by code, offline Luau checks, and Rojo builds: architecture, Luau, networking and security, data, tooling, environment, VFX and audio, UI, animation, gameplay, assets and avatar items, performance, monetization. Procedures were run live in Roblox Studio 0.743.

Skill	Use it for
scenario-roblox-expert	Roblox lead: Studio's built-in MCP server, Luau run in Edit and in playtests, simulated input and captures, two-solver type checks, Rojo, RunScript, Open Cloud
scenario-roblox-animation	Roblox animation: priorities and blending, events and markers, Blender and FBX imports, custom and creature rigs, IKControl, FaceControls, Animate replacements, NPC animators
scenario-roblox-architecture	Roblox code structure: where scripts go, RunContext, module loaders, services and controllers, signals and attributes, CollectionService tags, cleanup, Rojo layout
scenario-roblox-assets	Roblox 3D assets and avatar items: Blender, GLB, and FBX imports, AI-generated meshes, scale in studs, triangle and texture budgets, PBR SurfaceAppearance, UGC validation
scenario-roblox-data	Roblox player data: DataStores and UpdateAsync, session locking with ProfileStore, schema migration, receipts granted once, trading, leaderboards, MemoryStore, teleports
scenario-roblox-environment	Roblox maps and lighting: graybox, terrain, parts vs unions, collision fidelity, MaterialVariants, Lighting and Atmosphere moods, foliage scatter, streaming, level of detail
scenario-roblox-gameplay	Roblox gameplay: NPC AI and pathfinding, hundreds of enemies, hitboxes and melee combos, raycasts and projectiles, knockback, physics movers, vehicles, round loops
scenario-roblox-luau

Example prompts

Once the skills are installed and the MCP server is connected, ask your agent things like:

"Generate four style-matched potion icons with transparent backgrounds for my RPG inventory"
"Make a seamless brick texture, then upscale it to 2048 without breaking the tiling"
"Turn this concept sketch into a 3D prop and let me preview it before I export the GLB"

What is an Agent Skill?

A skill is a SKILL.md file with procedural knowledge an agent loads on demand, defined by the open Agent Skills specification. The skills CLI installs these files into 70+ agents, and the ecosystem directory lives at skills.sh.

Contributing

See CONTRIBUTING.md for the contribution workflow, and AGENTS.md for the authoring contract, the public-content policy, validation, and the application-testing bar. One-time setup after cloning: install the prerequisites, uv included, then run pnpm install (installs commitlint, cspell, prettier, and the husky git hooks). pnpm run validate runs the same content checks CI runs; commit messages and the PR title are linted separately with commitlint. PRs welcome; PR titles follow Conventional Commits since they become the squash commit header on main.

Every script shipped with a skill has a test suite in tests/<name>/; pnpm test runs them all (CI does too). Suites need Python 3.11+, plus ffmpeg on PATH where a suite uses it. With uv installed, pnpm test gives each suite the dependencies in its tests/<name>/requirements.txt; without uv, install them into python3 first. Python suites use stdlib unittest, TypeScript suites use vitest.

License

MIT

Add this server

Host a copy with our keys and logs.

Server facts

About Skills

Tools

Questions

How do I install Skills?

Does Skills need an API key?

What transport does Skills use?

When was Skills last checked?

Documentation

Install

Staying up to date

Skills

Getting started

Finding a direction

Images

Game art and 3D

Video and audio

Socials

Consistency and custom models

Reviewing and organizing output

Formats and placements

Workflows and apps

Troubleshooting

Team administration

Image model families

Video model families

Audio model families

3D model families

Expert tools: ZBrush

Expert tools: Blender

Expert tools: Maya

Expert tools: Unreal Engine

Expert tools: Unity

Expert tools: Godot

Expert tools: Roblox Studio

Example prompts

What is an Agent Skill?

Contributing

License