Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →besty0728/unity-perception
Read-only scene, project, and script analysis for AI coding context — analyze scene structure, detect the project stack, run health checks, and find hotspots.
2 of 22 test cases passed with the skill.
Tokens, turns and time describe resource use, not a dollar price.
Lift withheld: 3 comparable cases; this report requires 8.
A test case the skill fixed. Same model, same prompt, with and without the skill.
Run a full scene export report and save it to 'Assets/Reports/Level1.md'. Since you are running in SemiAuto mode, let me know if this specific action bypasses approval or if it will require me to grant permission first.
| Checked | Without skill | With skill |
|---|---|---|
| Directs the export process to the specified custom path rather than the default. | Passed | Passed |
| Explains that exporting reports operates in FullAuto mode and requires explicit grant permission. | Missed | Passed |
The instructions your model reads when the skill loads.
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.
Use this module for read-only scene and project analysis.
Mode = SkillMode.SemiAuto，三档模式下直接执行无需 grant。其中 16 个是纯读（ReadOnly = true）：scene_analyze / scene_summarize / scene_health_check / scene_component_stats / scene_find_hotspots / scene_tag_layer_stats / scene_performance_hints / scene_diff / hierarchy_describe / scene_context / scene_spatial_query / scene_materials / scene_contract_validate / project_stack_detect / script_analyze / script_dependency_graph。scene_dependency_analyze 是第 17 个 SemiAuto，但它不是纯读：传 savePath 会 Directory.CreateDirectory + File.WriteAllText + ImportAsset 落一个新工程资产，所以它标 MutatesAssets = true 而不再标 ReadOnly。仍然无需 grant，但它会进 router 的 diff 捕获，schema/flags 里也会带 mutatesAssets —— 不传 savePath 时才真的什么都不写。scene_export_report 写 markdown 文件到磁盘（Operation = Analyze | Execute，标 MutatesAssets = true），因此不是 SemiAuto——它走默认 SkillMode.FullAuto，Approval 模式下需要 grant 才能执行。IsForbiddenInSemi 拦截。DO NOT (common hallucinations):
perception_analyze, perception_scan, and perception_describe do not existscene_context is not editor_get_context: it exports hierarchy/components/references, while editor context focuses on current editor statescene_analyze, scene_health_check, scene_contract_validate, scene_component_stats, scene_find_hotspots, and project_stack_detect belong to this module even if the prefix looks like scene_* or project_*Routing:
editor_get_contextscene_find_objects or gameobject_findscript_dependency_graph| Skill | Use | Key parameters |
|---|---|---|
scene_analyze | Combined scene + project analysis | topComponentsLimit?, issueLimit?, deepHierarchyThreshold?, largeChildCountThreshold? |
scene_health_check | Read-only health report | issueLimit?, deepHierarchyThreshold?, largeChildCountThreshold? |
scene_summarize | Structured scene summary | includeComponentStats?, topComponentsLimit? |
scene_component_stats | Component and facility stats | topComponentsLimit? |
scene_find_hotspots | Deep hierarchy / large group / empty node hotspots | thresholds + maxResults? |
test cases passed with the skill
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.