This skill should be used when the user asks about "MCP tools", "Unity MCP", "enable tool groups", "which MCP tools", "create GameObject", "add component", "run Unity tests", "check scene hierarchy", "spawn agent for Unity", "MCP not working", or needs to coordinate Unity Editor operations via MCP.
Coordinates Unity Editor operations via MCP tools. Use when users request GameObject creation, component management, test execution, or scene inspection. Triggered by queries about "MCP tools", "enable tool groups", "create GameObject", "run Unity tests", or "check scene hierarchy".
/plugin marketplace add jwmyers/vui-vux-plugins/plugin install zero-day-dev@vui-vuxThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/tool-groups.mdreferences/tool-reference.mdreferences/troubleshooting.mdExpert knowledge for coordinating Unity MCP operations, including tool enablement, agent orchestration, and direct MCP tool usage.
The MCP Resource is always enabled - no tool enablement needed:
/unity-mcp-scene-info {path}/unity-mcp-scene-info GameplayScene/TileManagerRun /unity-mcp-enable [groups] before spawning agents that need MCP.
Include unity-mcp-tools skill for agents doing MCP work:
| Task | Enable Groups | Spawn Agent |
|---|---|---|
| Create/modify GameObjects | gameobject, component | scene-builder |
| Add UI elements | gameobject, component | ui-ux-developer |
| Run tests | testing | test-engineer |
| Work with scripts | script | code-architect |
| Create prefabs | prefab, gameobject | scene-builder |
| Deploy build | (none) | deployment-specialist |
Run /unity-mcp-reset to disable tools and save context.
Spawn the mcp-advisor advisory agent when:
Example prompt: "What MCP tool groups do I need to add a health bar UI?"
The mcp-advisor returns recommendations - it does not execute commands.
When spawning agents, include these skills:
| Agent | Skills to Include |
|---|---|
| scene-builder | unity-mcp-tools, layout-sizing, visual-style-guide |
| test-engineer | unity-mcp-tools, unity-testing |
| ui-ux-developer | layout-sizing, visual-style-guide |
| input-developer | board-sdk, unity-mcp-tools |
| code-architect | project-architecture |
| game-designer | zero-day-rules |
| deployment-specialist | (none - uses Bash) |
| project-producer | documentation |
| mcp-advisor | unity-mcp-tools |
Subagents can use MCP tools directly when:
AI-Game-Developer-Config.jsontools: field in frontmatter)To give MCP access, omit the tools field:
---
name: scene-builder
skills: unity-mcp-tools, layout-sizing
# No tools field = inherits ALL including MCP
---
Use /unity-mcp-enable [group] to enable. Multiple: /unity-mcp-enable gameobject component
| Group | Tools | Use Case |
|---|---|---|
| scene-read | scene-get-data, scene-list-opened, console-get-logs | Inspect scene hierarchy |
| scene-write | scene-create, scene-save, scene-open, scene-set-active, scene-unload, console-get-logs | Modify scenes |
| gameobject | gameobject-create, gameobject-find, gameobject-modify, gameobject-destroy, gameobject-duplicate, gameobject-set-parent, scene-save, console-get-logs | GameObject operations |
| component | gameobject-component-add, gameobject-component-get, gameobject-component-modify, gameobject-component-destroy, component-list, scene-save, console-get-logs | Component operations |
| script | script-read, script-update-or-create, script-delete, script-execute, assets-refresh, editor-application-get-state, console-get-logs | Script operations |
| prefab | assets-prefab-create, assets-prefab-instantiate, assets-prefab-open, assets-prefab-save, assets-prefab-close, assets-refresh, editor-application-get-state, console-get-logs | Prefab operations |
| assets | assets-find, assets-create-folder, assets-copy, assets-move, assets-delete, assets-get-data, assets-modify, assets-refresh, assets-material-create, assets-shader-list-all, console-get-logs | Asset management |
| testing | tests-run, editor-application-get-state, console-get-logs | Run Unity tests |
| editor | editor-application-get-state, editor-application-set-state, console-get-logs, editor-selection-get, editor-selection-set | Full editor control |
| packages | package-list, package-add, package-remove, package-search, console-get-logs | Package management |
| reflection | reflection-method-find, reflection-method-call, console-get-logs | Advanced operations |
| Tool | Auto-included with |
|---|---|
| console-get-logs | ALL groups |
| editor-application-get-state | script, testing, prefab |
| assets-refresh | script, prefab |
| scene-save | gameobject, component |
/unity-mcp-enable gameobject componentgameobject-create to create objectgameobject-component-add to add componentsgameobject-component-modify to configure/unity-mcp-enable testingtests-run with testMode: "EditMode" or "PlayMode"Always use MCP Resource first (no enablement):
/unity-mcp-scene-info {path} to understand structureConfig file: Assets/Resources/AI-Game-Developer-Config.json
Structure:
{
"tools": [{ "name": "tool-name", "enabled": true/false }],
"resources": [{ "name": "GameObject from Current Scene by Path", "enabled": true }]
}
The MCP Resource is always enabled. Tools default to disabled.
| Command | Purpose |
|---|---|
/unity-mcp-status | Show enabled groups |
/unity-mcp-enable [groups] | Enable tool groups |
/unity-mcp-enable-all | Enable all tools |
/unity-mcp-reset | Disable all tools |
/unity-mcp-scene-info [path] | Query scene via Resource |
For complete tool documentation:
references/tool-reference.md - All 50 tools with parameters and examplesreferences/tool-groups.md - Tool group definitions with JSON arrays for each groupreferences/troubleshooting.md - Common issues and solutionsThis skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.