New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Scenario Unity Expert

by scenario-labs in scenario-labs/skills

A skill your agent uses when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI…

MITAuto-check passedGame Development

Install Scenario Unity Expert

skills CLI
$ npx skills add scenario-labs/skills --skill scenario-unity-expert -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install scenario-labs/skills scenario-unity-expert --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/scenario-labs/skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/game-engines/unity/scenario-unity-expert .claude/skills/scenario-unity-expert && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
scenario-unity-expert
GitHub stars
946
Token cost
~5.2k tokens
SKILL.md length
2,099 words
Files
21 (incl. scripts, references)
Skills in repo
146
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI…

  • Works in 8 steps: One editor per project, and the live… → A job is only as honest as its result… → Numbers before pixels, milliseconds not… → …
  • An agent drives Unity 6.3 (6000.
  • SKILL.md covers Stance (the expert delta), Channels, Establish first and Workflow (the expert loop), plus 8 more sections
  • Runs C# and Python scripts from its folder; calls npx

What it does

Scenario Unity Expert is an agent skill from scenario-labs/skills. Use when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI and com.unity.pipeline, MCP servers, the Test Framework, command-line builds; when a batch run fails silently, 'Scripts have compiler errors', a capture comes back black or pink, or a result must be proven with numbers and a frame; or when a Unity brief must go to the right scenario-unity- specialist.

Its SKILL.md is about 5.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 23 other files, including scripts and reference files (for example `references/gui-paths.md`, `references/live-channels.md` and `references/procedures.md`).

It sits in Game Development, covering Game development and MCP servers. It works with Model Context Protocol. The repository describes itself as: 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 licence is MIT.

When your agent uses it

  • An agent drives Unity 6.3 (6000.
  • On a Mac for any task: batch mode and -executeMethod jobs
  • A running editor (the users GUI editor
  • A headless one)

Example prompts

  • “Scripts have compiler errors”
  • “/scenario-unity-expert”

Requirements

  • Python 3
  • Node.js

Workflow steps

8 steps, taken from the first numbered list in SKILL.md.

  1. One editor per project, and the live editor wins. "You can't open a project in batch mode while the Editor has the same project open" (6.3…
  2. A job is only as honest as its result line. Pass on the AGENT_RESULT envelope and the log scan, not on "it exited". A compile error in ANY…
  3. Numbers before pixels, milliseconds not fps. 16.67 ms at 60 fps, 33.33 at 30; mobile keeps about 65% for thermals (Unity profiling…
  4. Look AND check, and know the capture's lies. Every frame goes through ut_review.image_checks and a contact sheet you open. Epic's lighting…
  5. Fix the platform at launch. Target switches inside a batch job silently do nothing (6.3 Manual); -buildTarget/-activeBuildProfile at…
  6. Named jobs over eval. eval to explore, a named job for anything repeated: "A written command turns that workflow into something…
  7. Tests are the contract. Give work a failing test and a fence ("It can only touch the card data", DgNrgZeJOxQ [00:05:31]); -runTests never…
  8. Be honest about visual editors. Shader Graph, VFX Graph, the Animator window, UI Builder, Tile Palette painting and terrain sculpting have…

What it can do on your machine

Read from SKILL.md and the folder at commit f6f8ab7. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 9 files in scripts/ (C# and Python, from the files we listed), which the agent can run.

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Scenario Unity Expert loads about 5.2k tokens when it runs, and up to ~48k if it reads all its reference files. Until then it costs about 126 tokens; SKILL.md has 2,099 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~126
When it runs · the whole SKILL.md, loaded when a task matches
~5.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~48k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from scenario-labs/skills at commit f6f8ab7, republished under its MIT licence (© scenario-labs). 2,099 words, ~5,208 tokens.

Download SKILL.mdSave it as .claude/skills/scenario-unity-expert/SKILL.md (or your agent's skills folder). This skill also uses 20 other files; get the full folder from GitHub.
name
scenario-unity-expert
description
Use when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI and com.unity.pipeline, MCP servers, the Test Framework, command-line builds; when a batch run fails silently, 'Scripts have compiler errors', a capture comes back black or pink, or a result must be proven with numbers and a frame; or when a Unity brief must go to the right scenario-unity-* specialist.
license
MIT

Unity expert (technical director and agent protocol)

Expert Unity work is a loop run against numbers: set the budget, build one stage, measure it, look at it, fix it, then advance. An agent without a mouse gets there by choosing the right channel for each action, editing through serialization with explicit saves, and never trusting its own eyes alone. This skill is that protocol, the shared toolkit every scenario-unity-* skill imports (scripts/), and the map of the team. Target: Unity 6000.3.21f1 (6.3 LTS), URP 17.3, macOS Apple Silicon. If a sibling skill named here is missing from your available skills, ask the user to install it (npx skills add scenario-labs/skills --skill <name>); unattended, proceed from tool schemas and flag the gap.

Status (2026-09-24, after blind grading and the refactor): every toolkit function ran in Unity 6000.3.21f1 here (tests/code/unity-expert/run_all.sh --live --builds; results in archive/tests/unity-expert/live_results.jsonl). Every call from before the refactor is unchanged.

Stance (the expert delta)

  1. One editor per project, and the live editor wins. "You can't open a project in batch mode while the Editor has the same project open" (6.3 Manual). When an editor holds the project, drive it (ut_live), never hand-edit .unity/.prefab/.asset YAML: wrong fileIDs, invisible until reimport, easy to hit the wrong scene (Unity's unity-cli skill).
  2. A job is only as honest as its result line. Pass on the AGENT_RESULT envelope and the log scan, not on "it exited". A compile error in ANY assembly aborts every batch job with "Scripts have compiler errors" (observed; the live editor's twin is Safe Mode, which also blocks com.unity.pipeline).
  3. Numbers before pixels, milliseconds not fps. 16.67 ms at 60 fps, 33.33 at 30; mobile keeps about 65% for thermals (Unity profiling e-book). Editor Play mode is for iteration; the verdict comes from a development player on the lowest target device.
  4. Look AND check, and know the capture's lies. Every frame goes through ut_review.image_checks and a contact sheet you open. Epic's lighting agent approved an all-white frame (scenario-unreal-expert sources); here batch captures showed first-frame white materials, culled 2D lights, bind poses, no Overlay UI and black metals (observed by the team): anything wrong only in an Editor capture is re-checked in a player first. Agent-built levels come out "90%" done, a shelf in front of a door (Code Monkey, ppFshgFOgXU [00:10:52]).
  5. Fix the platform at launch. Target switches inside a batch job silently do nothing (6.3 Manual); -buildTarget/-activeBuildProfile at launch, one process per target. The editor reopens on the last active platform (observed): pin it.
  6. Named jobs over eval. eval to explore, a named job for anything repeated: "A written command turns that workflow into something deterministic and repeatable" (DgNrgZeJOxQ [00:07:41]); generic run-command tools drift (git-amend, VPjo-M6mPkE [00:03:54]).
  7. Tests are the contract. Give work a failing test and a fence ("It can only touch the card data", DgNrgZeJOxQ [00:05:31]); -runTests never with -quit.
  8. Be honest about visual editors. Shader Graph, VFX Graph, the Animator window, UI Builder, Tile Palette painting and terrain sculpting have no authoring API: use the substitute (HLSL, templates with exposed properties, AnimatorController API, UXML/USS text, TerrainData) or name the human path.

Channels

ChannelUse forCost (measured here)Rules
Batch job ut_run.run_methodanything when no editor holds the project6 to 13 s per job (editor boot included)-nographics by default; graphics=True for captures, bakes (never bake with -nographics), profiling; quit=False for async jobs; an editor that hangs after its result is ended by PID (grace, 10 s)
Resident headless editor + AgentKit bridge ut_live.start_headless, callmany calls in a rowboot 5 to 20 s once, then 0.1 to 0.5 s per callholds the project and a license seat; stop_headless
User's GUI editor + AgentKit bridge ut_live.call, evalthe user has the project opensame code path as headless (not run: no GUI windows during tests)the user may need to focus Unity once so it compiles AgentKit; never re-open the user's scene without asking; save what you change
Unity CLI + com.unity.pipeline ut_live.cli_*, eval (auto)fastest live channel: 151 commands, Roslyn eval with no domain reloadeval 0.03 to 0.15 s after a 0.5 to 1.1 s first callCLI 1.0.0-beta.11 (portable copy), package 0.7.0-exp.1 installed before the editor opens; blocked by Safe Mode, possibly by a sandbox
MCPonly unity mcp or a vetted community serverUnity's AI Assistant MCP server is deprecated ("Use the Unity CLI instead")
Test Framework ut_run.run_testsEditMode and PlayMode verdicts, content validationabout 14 s per platformNUnit XML parsed; exit 2 when a test failed (observed)

ut_live.channel(P) picks batch, bridge, pipeline, or blocked (ask the user). "Can't connect" does not prove the editor is closed: rule out Safe Mode and a sandboxed shell first (unity-cli skill).

Establish first

Ask once, then run: target platforms and device class; frame budget (default 60 fps desktop, 30 fps mobile at 65%); 2D or 3D; pipeline (default URP 17.3, HDRP only for high-end PC or console); quality tiers; art style; whether the user's editor has the project open; deliverable. Then ut_env.preflight(P) and AgentJob.Echo; write what they report (pipeline asset, color space, active target, quality level, Enter Play Mode setting, input handler, scripting backend) into the plan.

Workflow (the expert loop)

  1. Brief in numbers. Budgets per platform, resolution, scale, style. GATE: every later check has a number to compare with.
  2. Preflight. License days left, modules, lock state, compile health (one Echo job). GATE: ok, zero compile errors, zero new CS0618 warnings.
  3. Baseline. AgentAudit.AuditScene/AuditAssets; captures of fixed bookmarks (AgentCapture.SaveBookmark); a Play-mode profile if performance matters. GATE: audit errors fixed or listed; contact sheet opened.
  4. Build one stage with small idempotent jobs (references/writing-jobs.md): get-or-create, serialized edits, explicit saves. Route domain work to the owner (below).
  5. Measure. Re-run the audit, the tests, AgentProfile.PlayModeTimings + ut_stat.budget_check, or the build summary. GATE: numbers against the brief.
  6. Look AND check. Same bookmarks, ut_review.review_capture, open the sheet, judge with the domain skill's critique. GATE: no blank or magenta frame, saturation not collapsed, the change visible.
  7. Fix before advancing, one change at a time; ut_review.compare and ut_stat.compare_frames prove parity or gain.
  8. Deliver with evidence. Each step with its Unity call (references/toolkit-map.md), then Verified (what ran, job id, number or frame) and Assumed (not run, [verify], defaults). Never call a scene, shader, level or build done without numbers and a frame you looked at.

Numbers

ValueRelative toSource
16.67 / 33.33 msframe budget at 60 / 30 fpsprofiling e-book
x 0.65mobile sustained budget (10.8 ms at 60, 21.7 at 30)profiling and mobile e-books
6 to 13 sone batch job on this project, editor boot includedobserved
about 14 sone run_tests platform run (EditMode 2 tests, PlayMode 1 test)observed
60 s (12 s incremental), 114.7 MBmacOS Mono player build of the demo scene (universal)observed
259 s (25 s incremental), 12.2 MBWeb build (IL2CPP, Brotli) of the same sceneobserved
0.1 to 0.5 s / 0.03 to 0.15 slive call through the AgentKit bridge / Pipeline eval (two runs)observed
30 daysPersonal license offline window (license_ok() reads it)observed + Unity support FAQ
10 s / 120 sgrace before ut_run ends a silent editor after its result with / without a shutdown linetoolkit default
Show full SKILL.md (898 more words)Show less

Quality gates

  • Measurable: envelope ok plus compile_errors == []; audit counts.error == 0; NUnit failed == 0 and total > 0; budget_check verdict pass (warn needs a reason); gc_check in a development player; build_summary result Succeeded, size within budget; lock state recorded.
  • Visual: every capture passes image_checks (no all_white, all_black, uniform, magenta) and was opened; before/after from the same bookmarks.
  • Habits (references/routing-handoffs.md section 6): the same build_target on every stage; p95 AND worst frame, before and after as two captures of about 200 frames (YOtDVv5-0A4 [00:17:00]); the verdict from a development player on the target device class (ZkvK0mX-id4 [00:10:27]); one development-build run before code is done (only those catch off-main-thread Unity calls); size on the shipped output; the scene list checked before each build; expected errors LogAssert.Expected.

Common mistakes

MistakeWhat it looks likeFix
batch job on a project the GUI editor holdsrefused, or a corrupted Libraryut_live (the toolkit raises ProjectLockedError)
-quit with -runTestsno XML, no verdictut_run.run_tests (never passes it)
captures or bakes with -nographicsempty frames, "no graphics device", no lightmapsgraphics=True
switching platform or defines inside a job, or pinning the target only on the buildold target or defines; textures re-imported per stagebuild_target= on every stage, or two invocations
GetComponent<T>() ?? AddComponent<T>(), ?. on Unity objectsnothing added, MissingComponentException next (fake null, measured)explicit == null or TryGetComponent
AgentJob.List("k") ?? defaultsthe defaults never apply (empty list, not null)AgentJob.ListOrNull("k") ?? defaults, TryList, Has
sizing a build from BuildReport totalSizegigabytes: IL2CPP's do-not-ship folder countedbuild_summary (output on disk)
trusting "Access token is unavailable" as a license failurefalse alarmthe refusal line is "No valid Unity Editor license found"
hand-editing scene YAML while an editor is openchange invisible or lostlive job, then AgentBridge.SaveAll
killing Unity by nameother agents' editors diestop by PID only (stop_headless, the grace timeout)

Team routing and handoffs

Route by owner: scenario-unity-architecture (code, save data, input), scenario-unity-world-building (terrain, blockout, streaming), scenario-unity-rendering-lighting (pipeline, lighting, post), scenario-unity-shaders (HLSL, Shader Graph, renderer features), scenario-unity-vfx (VFX Graph, particles), scenario-unity-animation (Animator, Timeline, Cinemachine), scenario-unity-2d (sprites, tilemaps, 2D lights), scenario-unity-ui (uGUI, UI Toolkit), scenario-unity-gameplay (physics, AI, netcode, audio), scenario-unity-pipeline-automation (imports, Addressables, CI, builds), scenario-unity-performance (profiling, memory, batching), scenario-unity-mobile (Android, iOS, stores), scenario-unity-web (Web builds, servers, WebGPU). Full keyword table, persona chains and the handoff packet: references/routing-handoffs.md. Items that fell between two skills in blind grading (PSO warm-up, GPU Resident Drawer, VFX shaders, NavMesh through doors, foot sliding, uGUI over UI Toolkit, web fonts, stripping, Addressables duplication, static state) have ONE owner and a proof in its seams table: put both in the brief. Every packet carries project and channel, brief in numbers, what was done with its Unity calls, evidence (audit JSON, contact sheet with flags, CSV verdict, NUnit totals, build summary), Verified, Assumed, open issues, fence. The receiver reproduces one piece of evidence before building on it.

Unity 6.3 notes (full list: references/unity-6.3-traps.md)

  • Render Graph only (Compatibility Mode removed; the define dies in 6.4); _CLUSTER_LIGHT_LOOP replaces _FORWARD_PLUS.
  • FindObjectsByType<T>(FindObjectsSortMode.None); Rigidbody.linearVelocity/linearDamping; [SerializeField] only on fields; Lightmapping.TryGetLightingSettings (the getter throws when unassigned, observed).
  • Templates run the Input System only; entering Play mode reloads the domain (6.6 flips the default: reset statics in SubsystemRegistration, unsubscribe on ExitingPlayMode); -createProject without a template is Built-in.
  • Object.Destroy already calls OnDisable on every level of the hierarchy on 6000.3.21f1 (observed; the deltas say direct children only before 6.4): unregister in OnDisable and, idempotently, in OnDestroy.
  • Build Profiles replace Build Settings; no public API creates a profile before 6.5; IPreprocessBuildWithContext over ...WithReport; an EditorUserBuildSettings change on an active platform profile hits all platform profiles; profile texture compression lives in Library/.
  • Pin package versions: the manifest lists Cinemachine 2.10.7 yet a bare Client.Add installed 3.1.7 (observed); IAP 4.15.1 and LevelPlay 8.10.1 lag the docs (IAP 5, LevelPlay 9).
  • Web: the URP template ships Brotli, not the Manual's gzip (observed); WebGPU experimental (opt-in production from 6.6). Built-in RP deprecated from 6.5.

macOS specifics

  • Editor /Applications/Unity/Hub/Editor/6000.3.21f1/Unity.app/Contents/MacOS/Unity; Hub modules (Web, iOS, Android) in .../6000.3.21f1/PlaybackEngines/; Xcode 26.6 meets the App Store rule.
  • Metal only; no CPU lightmapper on Apple Silicon (GPU lightmapper needs graphics); no GPU timings in the VFX Graph panel; GPU Frame Time reads 0 on most Editor frames: measure GPU in a player.
  • Personal license: sign in to Unity Hub every 30 days (ut_env.license_ok()); the toolkit uses a portable, checksum-verified CLI (references/live-channels.md).
  • Paths with spaces worked; quote every path. Never ship <Product>_BurstDebugInformation_DoNotShip. Never kill an editor you did not start.

Shared toolkit (scripts/; exact API in references/toolkit-map.md)

import sys; sys.path.insert(0, "<scenario-unity-expert>/scripts").

  • ut_env (editor, license, base_project, install_agentkit, lock rule, preflight); ut_run (run_method(project, method, args=None, timeout=1800, graphics=False, quit=True, build_target=None, grace=None, result_grace=None), run_tests, build, scan_log); ut_live (bridge, headless editor, CLI, Pipeline eval); ut_review (image_checks, compare, contact_sheet, review_capture); ut_stat (budget_check, summarize_csv, compare_frames, build_summary).
  • C# AgentKit (scripts/AgentKit/): AgentJob (List/Dict never null; TryList, ListOrNull for missing keys), AgentCapture (warms materials and 2D lights), AgentAudit, AgentBuild, AgentProfile, AgentBridge, AgentJson.

References

  • references/toolkit-map.md: the Unity call behind every toolkit function; the report format (Verified, Assumed).
  • references/writing-jobs.md: how domain skills write AgentKit jobs (skeleton, rules, async jobs, findings).
  • references/live-channels.md: bridge, headless editor, Unity CLI and com.unity.pipeline, MCP, sandbox and Safe Mode.
  • references/unity-6.3-traps.md: traps observed by the lead and the writers, documented 6.3 facts, deltas corrections, first-run checklist.
  • references/routing-handoffs.md: routing, seams, persona chains, handoff packet, acceptance checks, verification habits.
  • references/procedures.md: the lead's nine procedures, each with its live test and result.
  • references/gui-paths.md: windows and menus for the same tasks.
  • references/sources.md: every source with credentials, URLs, timestamps; revision history.

© scenario-labs, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 20 other files (scripts, references) in skills/game-engines/unity/scenario-unity-expert of scenario-labs/skills.

  • SKILL.md
  • references/gui-paths.md
  • references/live-channels.md
  • references/procedures.md
  • references/routing-handoffs.md
  • references/sources.md
  • references/toolkit-map.md
  • references/unity-6.3-traps.md
  • references/writing-jobs.md
  • scripts/AgentKit/AgentAudit.cs
  • scripts/AgentKit/AgentBridge.cs
  • scripts/AgentKit/AgentBuild.cs
  • scripts/AgentKit/AgentCapture.cs
  • scripts/AgentKit/AgentJob.cs
  • scripts/AgentKit/AgentJson.cs
  • scripts/AgentKit/AgentProfile.cs
  • scripts/ut_env.py
  • scripts/ut_live.py
  • … and 3 more

Open the folder on GitHubat commit f6f8ab7

Compare with similar skills

Scenario Unity Expert next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Scenario Unity Expert compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Scenario Unity Expert this skillscenario-labs/skills946—~5.2kAutomated safety check: PassMIT
Unreal Blueprint Authoringflopperam/unreal-engine-mcp1.1k—~1.6kAutomated safety check: PassNone
MCP DriverRandallLiuXin/GodotMaker5501 repos~1.1kAutomated safety check: PassCustom licence
Unity PluginTomLeeLive/openclaw-unity-plugin107—~5.1kAutomated safety check: PassApache-2.0
Roblox Gamebrockmartin/roblox-game-skill203—~1.3kAutomated safety check: PassNone
Unreal Engine MCPEpicGames/unreal-engine-skills-for-claude-code-plugin338—~1.8kAutomated safety check: PassMIT

Similar skills

  • Unreal Blueprint Authoring

    flopperam/unreal-engine-mcp

    Walks an agent through creating and editing Unreal Engine Blueprints with the Flopperam MCP's bp_* tools, from inspection to commit and verification.

    1.1k GitHub stars~1.6k tokensUpdated 3 mo ago
    Game DevelopmentAuto-check passed

  • MCP Driver

    RandallLiuXin/GodotMaker

    Runtime debugging and live project inspection via godot-mcp.

    550 GitHub starsUsed in 1 repo~1.1k tokens
    Game DevelopmentAuto-check passed

  • Unity Plugin

    TomLeeLive/openclaw-unity-plugin

    Control Unity Editor via OpenClaw Unity Plugin. An agent skill from TomLeeLive/openclaw-unity-plugin.

    107 GitHub stars~5.1k tokensUpdated 1 mo ago
    Game DevelopmentAuto-check passed

  • Roblox Game

    brockmartin/roblox-game-skill

    Expert Roblox game development companion — Luau, Roblox Studio, MCP integration, simulator, tycoon, obby, RPG, horror, battle royale, game design, security, performance.

    203 GitHub stars~1.3k tokensUpdated 7 mo ago
    Game DevelopmentAuto-check passed

  • Unreal Engine MCP

    EpicGames/unreal-engine-skills-for-claude-code-plugin

    Drives a live Unreal Editor through the unreal-mcp server: spawn actors, edit Blueprints, materials and sequences, change properties and trigger Live Coding.

    338 GitHub stars~1.8k tokensUpdated 23 days ago
    Game DevelopmentAuto-check passed

  • Unreal Scene Building

    flopperam/unreal-engine-mcp

    Guides scene and world building in Unreal Engine through the Flopperam MCP: placing actors, sculpting landscapes, scattering foliage, editing materials and verifying the level.

    1.1k GitHub stars~1.4k tokensUpdated 3 mo ago
    Game DevelopmentAuto-check passed

More from scenario-labs/skills

All 146 skills in this repo

  • Scenario Blender Grease Pencil

    scenario-labs/skills

    A skill your agent uses when drawing or animating with Grease Pencil in Blender 5.x from Python: 2D or 2.5D illustration, frame-by-frame animation, a cutout or part-based 2D character, strokes with…

    946 GitHub stars~4.5k tokensUpdated today
    Auto-check passed

  • Scenario Blender Hair

    scenario-labs/skills

    A skill your agent uses when grooming hair or fur in Blender with hair curves, such as a character hairstyle, animal fur, procedural fur in geometry nodes, or hair cards and mesh hair for games.

    946 GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • Scenario Blender Lighting Rendering

    scenario-labs/skills

    A skill your agent uses when lighting, rendering or compositing in Blender: light a character, product or hero shot, interior at dusk or night, three-point or motivated lighting, sun and sky, HDRI…

    946 GitHub stars~5k tokensUpdated today
    Auto-check passed

  • Scenario Chatgpt Pet Create

    scenario-labs/skills

    A skill your agent uses when creating a ChatGPT pet or Codex pet with Scenario: hatching an animated companion from a text idea, a character, mascot or brand cue, or reference photos and art; making…

    946 GitHub stars~3.6k tokensUpdated today
    Auto-check passed

  • Scenario Godot Animation

    scenario-labs/skills

    A skill your agent uses when animating characters or scenes in Godot 4.7: AnimationPlayer clips and RESET, AnimationTree state machines and blend spaces built in code, Mixamo or glTF import, loop…

    946 GitHub stars~4.7k tokensUpdated today
    Auto-check passed

  • Scenario Godot Audio

    scenario-labs/skills

    A skill your agent uses when adding or fixing sound in Godot 4.7: audio buses and effects, volume sliders, 'too many sounds', combat audio with hundreds of enemies, sounds clipping or distorting, 3D…

    946 GitHub stars~4.7k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Scenario Unity Expert

What does Scenario Unity Expert do?

A skill your agent uses when an agent drives Unity 6.3 (6000.3) on a Mac for any task: batch mode and -executeMethod jobs, a running editor (the user's GUI editor or a headless one), the Unity CLI…. Scenario Unity Expert is an agent skill from scenario-labs/skills.pipeline, MCP servers, the Test Framework, command-line builds; when a batch run fails silently, 'Scripts have compiler errors', a capture comes back black or pink, or a result must be proven with numbers and a frame; or when a Unity brief must go to the right scenario-unity- specialist.

When should I use Scenario Unity Expert?

Scenario Unity Expert fits situations like: an agent drives Unity 6.3 (6000; on a Mac for any task: batch mode and -executeMethod jobs; A running editor (the users GUI editor; A headless one).

How do I install Scenario Unity Expert in Claude Code?

Run `npx skills add scenario-labs/skills --skill scenario-unity-expert -a claude-code`. Or copy the skill folder (skills/game-engines/unity/scenario-unity-expert in scenario-labs/skills) into .claude/skills/scenario-unity-expert in your project. Claude Code loads it when a task matches its description.

How do I install Scenario Unity Expert in Codex?

Run `npx skills add scenario-labs/skills --skill scenario-unity-expert -a codex`. Or copy the skill folder (skills/game-engines/unity/scenario-unity-expert in scenario-labs/skills) into .agents/skills/scenario-unity-expert in your project. Codex loads it when a task matches its description.

Can I use Scenario Unity Expert in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add scenario-labs/skills --skill scenario-unity-expert -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/scenario-unity-expert, .gemini/skills/scenario-unity-expert, .github/skills/scenario-unity-expert and .opencode/skills/scenario-unity-expert in your project.

What does Scenario Unity Expert need to run?

Going by SKILL.md and its folder, Scenario Unity Expert needs C# and Python for the scripts in its folder and the command-line tools its instructions call (npx). Our summary lists: Python 3; Node.js.

Does Scenario Unity Expert access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Scenario Unity Expert safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Scenario Unity Expert use?

Scenario Unity Expert is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Scenario Unity Expert use?

About 5.2k tokens (SKILL.md is roughly 21k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 43k tokens, read only when the agent opens those files.

What are the alternatives to Scenario Unity Expert?

Skills that share tags, products or a category with Scenario Unity Expert: Unreal Blueprint Authoring (flopperam/unreal-engine-mcp, 1.1k stars), MCP Driver (RandallLiuXin/GodotMaker, 550 stars), Unity Plugin (TomLeeLive/openclaw-unity-plugin, 107 stars) and Roblox Game (brockmartin/roblox-game-skill, 203 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Scenario Unity Expert?

scenario-labs (a GitHub organization) maintains it in scenario-labs/skills, which has 946 GitHub stars. The repository holds 146 skills in this directory. The repository was last updated on October 10, 2026.

Source: scenario-labs/skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.