Edit Scene Agent Skill

Creates and modifies Unity scene and prefab files.

Context cost
8.9k tokensestimated from the bundle, loaded when it triggers
Bundle
4 files · 36.8 kB1 script among them — read before you run
Licence
Unlicensethe author’s own terms
Last change
—no release on file
Servers it uses
Noneruns standalone

What it does

Creates and modifies Unity scene and prefab files. Use this skill whenever creating, editing, or modifying .unity scene files or .prefab prefab files. This includes adding GameObjects, building uGUI hierarchies, wiring up components, and any task that results in changes to .unity or .prefab files.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

gamedev

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md7.3 kB · preview
--- name: edit-scene context: fork license: Unlicense metadata: author: Koji Hasegawa ---
14Guide for creating and editing Unity scene files in Unity projects.
15
16## Rules
17
18- Do not directly Edit or Write .unity or .prefab files. Instead, write an editor script under Assets/UnityCodingSkills/Editor/ and execute it in Unity to create or update the scene or prefab — those carry GameObject/Prefab-instance structure that is unsafe to author by hand.
19- **Editor scripts must always end with EditorSceneManager.SaveScene (or PrefabUtility.SaveAsPrefabAsset for prefabs).** Treat "no dirty scenes/assets at script exit" as a hard postcondition.
20 - Scene: EditorSceneManager.SaveScene(scene, path) (new) or EditorSceneManager.SaveScene(scene) (existing). The return value is true on success.
21 - Prefab: PrefabUtility.SaveAsPrefabAsset(go, path). When editing via LoadPrefabContents, always pair with SaveAsPrefabAsset → UnloadPrefabContents.
22 - When the script also creates side-effect assets (Materials, ScriptableObjects, etc.), call AssetDatabase.SaveAssets() after the per-object saves to flush pending writes.
23- Before running an editor script, check if the editor is in Play Mode using the unity_play_control tool. If it is, stop it first — Play Mode may skip recompilation, leaving stale code active.
24- After modifying code, confirm compilation success using the get_unity_compilation_result tool before running.
25- **To determine which assembly an editor script belongs to**, run ${CLAUDE_SKILL_DIR}/scripts/resolve-assembly.sh <cs-file-path>. It walks up directories to find the nearest .asmdef; if none is found, it falls back to Assembly-CSharp-Editor (path contains /Editor/) or Assembly-CSharp.
26- **Prefer the run_method_in_unity tool (MCP Server Extension for Unity) for execution.** Define a public static method in the script (applying [MenuItem("Tools/...")] is optional) and invoke it directly via run_method_in_unity. Only fall back to execute_run_configuration or other alternatives when run_method_in_unity is unavailable.
27- **Delete the editor script (and its .meta) immediately after a successful run — do not leave it for manual removal.** Delete both from the filesystem after the run returns; never have the script delete itself — AssetDatabase.DeleteAsset on its own file triggers a domain reload mid-call (see the Troubleshooting resource below).
28 - Treat a run as successful only when the response carries no "type": "Error" entry in logs. success: true alone means only that the method was invoked, not that it completed without throwing.
29 - Confirm the change landed: git diff for an existing scene/prefab; for a newly created one (untracked, so no diff) confirm the file exists and its saved hierarchy matches the intent.
30 - If the run failed, or the change did not fully land, keep the script until a fix succeeds — don't delete a script you may still need to correct and re-run.
31 - The same applies when a fallback runner (execute_run_configuration, etc.) was used instead of run_method_in_unity.
32- For uGUI buttons and text, use the **legacy variants** (UnityEngine.UI.Button / UnityEngine.UI.Text). Do not use TextMeshPro unless the user explicitly requests it.
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md949 words
Files4
LicenceUnlicense
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈100
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
8,850
on trigger
The instruction body and 3 supporting files, read only when the skill fires.
4.5%
of a 200k window
Ten skills this size would take about 45% of the window before you open a file.
050k100k150k200k context window

8.9k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for
Writes filesnot declared
Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

4 files, 36.8 kB on disk. Mostly text — the instructions the model reads — with 1 script in it that your client would run only if the instructions tell it to.

  • SKILL.md7.3 kB
  • resources/troubleshooting-run-method-in-unity.md10.5 kB
  • resources/ugui.md18.0 kB
  • scripts/resolve-assembly.sh1.0 kB
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 1 script beside the text, so the bundle is 4 files you can review in full before installing. The Unlicense licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Edit Scene · 8.9k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/edit-scene/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/edit-scene" ] && { [ ! -e .claude/skills/edit-scene ] || { mv .claude/skills/edit-scene "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/edit-scene" .claude/skills/ && echo "Installed .claude/skills/edit-scene"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add nowsprinting/edit-scene

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/edit-scene/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/edit-scene/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/edit-scene" ] && { [ ! -e ~/.claude/skills/edit-scene ] || { mv ~/.claude/skills/edit-scene "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/edit-scene" ~/.claude/skills/ && echo "Installed ~/.claude/skills/edit-scene" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/edit-scene/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Versionnot versioned
Publishedno release date on file
PriceFree
Referencenowsprinting/edit-scene

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Publisher
Servers0
Claim this skill