Unity Validation logo

Unity Validation

CommunityPopular
Besty0728
unity-validation

Validate project and scene health plus cleanup

Overview

PublisherBesty0728
RepositoryUnity-Skills
Skill nameunity-validation
Stars
1.9K
Forks
176
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Besty0728 on GitHub. Read the source before you install it.

Installation

Install the Unity Validation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/validation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Use it in TypingMind

Enable Unity Validation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Unity Validation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Unity Validation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Before calling any skill in this module: if you are about to call a skill with parameters guessed from its name or description, STOP — read this file (or fetch its schema via GET /skills/recommend?includeSchema=true) first. If you already have the parameter definitions from recommend/schema, you may proceed straight to dryRun.

Triggers

  • Checking broken or missing references
  • Validating scene/project integrity
  • Cleaning up before a build
  • 检查断裂或丢失引用、校验场景/项目完整性、构建前清理

Unity Validation Skills

Maintain project health - find problems, clean up, and validate your Unity project.

Operating Mode

  • Approval: 只读分析 skill(validate_scene / validate_find_missing_scripts / validate_find_unused_assets / validate_texture_sizes / validate_project_structure / validate_missing_references / validate_mesh_collider_convex / validate_shader_errors,标 SkillMode.SemiAuto)直接执行;含 Delete 的 skill(validate_cleanup_empty_folders 标 Analyze | Delete、validate_fix_missing_scripts 标 Execute | Delete,默认 SkillMode.FullAuto)需用户 grant。
  • Auto / Bypass: 直接执行。
  • 本模块含 Delete 类高危 skill:validate_cleanup_empty_folders / validate_fix_missing_scripts 一旦 dryRun=false 即真删;它们在 Approval / Auto 下被 IsForbiddenInSemi 自动拦截,仅 Bypass 或 Allowlist 命中可执行。强烈建议先用 dryRun=true 预览。

DO NOT (common hallucinations):

  • Validation skill routes use the validate_* prefix, not validation_*
  • validation_run / validation_check do not exist → use specific skills such as validate_scene, validate_project_structure, validate_missing_references
  • validation_fix does not exist → validation skills report issues; use other modules to fix them
  • validation_clean does not exist → use cleaner module for cleanup operations

Routing:

  • For unused/duplicate asset cleanup → use cleaner module
  • For missing script fix → cleaner_fix_missing_scripts (cleaner module)
  • For compile errors → debug_check_compilation (debug module)

Skills Overview

SkillDescription
validate_sceneComprehensive scene validation
validate_find_missing_scriptsFind objects with missing scripts
validate_fix_missing_scriptsRemove missing script components
validate_cleanup_empty_foldersRemove empty folders
validate_find_unused_assetsFind potentially unused assets
validate_texture_sizesCheck texture sizes
validate_project_structureGet project overview
validate_missing_referencesFind null/missing object references on components
validate_mesh_collider_convexFind non-convex MeshColliders
validate_shader_errorsFind shaders with compilation errors

Six more skills carry SkillCategory.Validation but are implemented and documented in the batch module, so GET /skills/recommend?category=validation returns them alongside the ten above. Their parameters live in ../batch/SKILL.md; each is a preview that you commit with batch_execute(confirmToken), except batch_validate_scene_objects, which is a plain read-only report.

SkillDescription
batch_validate_scene_objectsAnalyze scene objects for missing scripts, missing references, duplicate names, and empty objects
batch_fix_missing_scriptsPreview batch removal of missing scripts
batch_cleanup_temp_objectsPreview deleting temporary helper objects by common temp-name patterns
batch_standardize_namingPreview standardizing names by trimming whitespace and normalizing separators
batch_set_render_layerPreview setting GameObject layers in batch
batch_replace_materialPreview replacing materials in batch

Skills

validate_scene

Comprehensive scene validation.

ParameterTypeRequiredDefaultDescription
checkMissingScriptsboolNotrueCheck for missing scripts
checkMissingPrefabsboolNotrueCheck for missing prefabs
checkDuplicateNamesboolNotrueCheck duplicate names
checkEmptyGameObjectsboolNofalseCheck empty GameObjects (no components)

Returns: {scene, totalIssues, summary: {errors, warnings, info}, issues: [{type, severity, gameObject, path, message, count}]}

validate_find_missing_scripts

Find objects with missing script references.

ParameterTypeRequiredDefaultDescription
searchInPrefabsboolNotrueAlso check prefab assets

Returns: {totalFound, objects: [{source, gameObject, path, missingCount, prefabPath?}]} (prefabPath only present when source="Prefab")

validate_fix_missing_scripts

Remove missing script components.

ParameterTypeRequiredDefaultDescription
dryRunboolNotruePreview only, don't remove

Returns: {success, dryRun, fixedCount, message, objects: [{gameObject, path, missingCount}]}

validate_cleanup_empty_folders

Remove empty folders from project.

ParameterTypeRequiredDefaultDescription
rootPathstringNo"Assets"Starting folder
dryRunboolNotruePreview only, don't delete

Returns: { success, dryRun, emptyFolderCount, folders, message }

validate_find_unused_assets

Find potentially unused assets.

ParameterTypeRequiredDefaultDescription
assetTypestringNo"Material"Filter: Texture/Material/Prefab/etc
limitintNo100Max results

Returns: { success, assetType, potentiallyUnusedCount, assets }

validate_texture_sizes

Check for oversized textures.

ParameterTypeRequiredDefaultDescription
maxRecommendedSizeintNo2048Warn if larger
limitintNo50Max results

Returns: {maxRecommendedSize, largeTextureCount, textures: [{path, name, width, height, maxTextureSize, format, recommendation}]}

validate_project_structure

Get project folder structure overview.

ParameterTypeRequiredDefaultDescription
rootPathstringNo"Assets"Starting folder
maxDepthintNo2Max folder depth

Returns: { success, rootPath, assetCounts, structure }

validate_missing_references

Find null/missing object references on components in the scene.

ParameterTypeRequiredDefaultDescription
limitintNo50Max results

Returns: { success, count, issues: [{ gameObject, path, component, property }] }

validate_mesh_collider_convex

Find non-convex MeshColliders (potential performance issue).

ParameterTypeRequiredDefaultDescription
limitintNo50Max results

Returns: { success, count, nonConvexColliders: [{ gameObject, path, vertexCount }] }

validate_shader_errors

Find shaders with compilation errors.

ParameterTypeRequiredDefaultDescription
limitintNo50Max results

Returns: { success, count, shaders: [{ name, path, errorCount }] }


Common Workflows

Pre-Build Check

python
import unity_skills

# Validate scene
scene_result = unity_skills.call_skill("validate_scene")
if scene_result['totalIssues'] > 0:
    print(f"Warning: {scene_result['totalIssues']} issues found")

# Check texture sizes
texture_result = unity_skills.call_skill("validate_texture_sizes", maxRecommendedSize=2048)
if texture_result['largeTextureCount'] > 0:
    print(f"Warning: {texture_result['largeTextureCount']} oversized textures")

Project Cleanup

python
import unity_skills

# 1. Preview missing scripts fix
preview = unity_skills.call_skill("validate_fix_missing_scripts", dryRun=True)
print(f"Would fix {preview['fixedCount']} objects")

# 2. Actually fix (if preview looks good)
unity_skills.call_skill("validate_fix_missing_scripts", dryRun=False)

# 3. Preview empty folder cleanup
preview = unity_skills.call_skill("validate_cleanup_empty_folders", dryRun=True)
print(f"Would delete {len(preview['folders'])} folders")

# 4. Actually cleanup
unity_skills.call_skill("validate_cleanup_empty_folders", dryRun=False)

# 5. Review unused assets (manual review recommended)
unused = unity_skills.call_skill("validate_find_unused_assets")
for asset in unused['assets']:
    print(f"Potentially unused: {asset}")

Best Practices

  1. Always use dryRun=True first to preview changes
  2. Run validation before major builds
  3. Review unused assets manually before deletion
  4. Keep texture sizes appropriate for target platform
  5. Fix missing scripts before they cause runtime errors
  6. Regular cleanup prevents project bloat

Exact Signatures

Exact names, parameters, defaults, and returns are defined by GET /skills/schema or unity_skills.get_skill_schema(), not by this file.

Frequently asked questions

What does the Unity Validation AI skill do?

Validate project and scene health plus cleanup

Why use Unity Validation on TypingMind?

Because you install it once and use it with any model. Unity Validation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Unity Validation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Besty0728/Unity-Skills/tree/main/SkillsForUnity/unity-skills~/skills/validation. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Unity Validation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Unity Validation?

As many as you like. As long as a model supports skills, you can use Unity Validation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Unity Validation AI skill free?

Yes. It is published on GitHub by Besty0728 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇