Not in the top 1,000 by GitHub stars
kevinpbuckley/VibeUE
Unreal Engine Vibe Coding tool
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
Content/Skills/animation-blueprint/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/animation-editing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/animation-montage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/animsequence/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/asset-management/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/behavior-trees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/blueprint-graphs/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/blueprints/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/bulk-maintenance/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/customizable-object/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/engine-settings/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/enhanced-input/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/enum-struct/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/fab/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/foliage/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/frame-rate/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/gameplay-tags/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/gas/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/landscape/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/landscape-auto-material/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/landscape-materials/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/level-actors/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/map-blockout/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/materials/SKILL.md
Week of Nov 2, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
A local comparison is unavailable. You can inspect the recorded versions on GitHub.
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/metasounds/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/niagara-emitters/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/niagara-systems/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/pcg/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/pie-testing/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/profiling/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/project-settings/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/skeleton/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/sound-cues/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/state-trees/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/terrain-data/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/umg-widgets/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/uv-mapping/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/vibeue/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Network or broad shell
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Content/Skills/viewport/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Not checked yet → After Local scripts
f62f3848c005 → b0c1bfeac7ac
Diff text is unavailable under the recorded licenses. Line counts and the GitHub link remain available.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Not checked yet
First observation → f62f3848c005
No earlier version was observed for comparison.
Heat
7.7- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- animation-blueprint
Content/Skills/animation-blueprint - animation-editing
Content/Skills/animation-editing - animation-montage
Content/Skills/animation-montage - animsequence
Content/Skills/animsequence - asset-management
Content/Skills/asset-management - behavior-trees
Content/Skills/behavior-trees - blueprint-graphs
Content/Skills/blueprint-graphs - blueprints
Content/Skills/blueprints - bulk-maintenance
Content/Skills/bulk-maintenance - customizable-object
Content/Skills/customizable-object - engine-settings
Content/Skills/engine-settings - enhanced-input
Content/Skills/enhanced-input - enum-struct
Content/Skills/enum-struct - fab
Content/Skills/fab - foliage
Content/Skills/foliage - frame-rate
Content/Skills/frame-rate - gameplay-tags
Content/Skills/gameplay-tags - gas
Content/Skills/gas - landscape
Content/Skills/landscape - landscape-auto-material
Content/Skills/landscape-auto-material - landscape-materials
Content/Skills/landscape-materials - level-actors
Content/Skills/level-actors - map-blockout
Content/Skills/map-blockout - materials
Content/Skills/materials - metasounds
Content/Skills/metasounds - niagara-emitters
Content/Skills/niagara-emitters - niagara-systems
Content/Skills/niagara-systems - pcg
Content/Skills/pcg - pie-testing
Content/Skills/pie-testing - profiling
Content/Skills/profiling - project-settings
Content/Skills/project-settings - skeleton
Content/Skills/skeleton - sound-cues
Content/Skills/sound-cues - state-trees
Content/Skills/state-trees - terrain-data
Content/Skills/terrain-data - umg-widgets
Content/Skills/umg-widgets - uv-mapping
Content/Skills/uv-mapping - vibeue
Content/Skills/vibeue - viewport
Content/Skills/viewport
How it works
animation-blueprint
When your agent uses it
Navigate, inspect, and author Animation Blueprints — state machines, states, transitions, and transition rules (AnimGraphService). Use when the user asks to create or edit an Animation Blueprint/AnimBP, add a state machine or states, wire transitions between states, set a state's animation, or inspect AnimGraph structure.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
5,675 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚠<U+FE0F> #1 GOTCHA — Transitions need a RULE or they NEVER fire
- Critical Rules
- Workflows
- Authoring State Machines (build / edit)
- Data Structures
- Driving bones directly — skeletal controls, no state machine
- Common Patterns
- Sample scripts (run via `execute_python_code`)
- Additional gotchas
Files
SKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesSKILL.mdcore21,978 bytesscripts/build_state_machine.txtdoc1,229 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "animation-system"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Animation Blueprint Skill
> **Loading skills:** skills load through the engine's `AgentSkillToolset` (`ListSkills`/`GetSkills`) —
> there is no `vibeue-skills-manager` tool. Run VibeUE services with `execute_python_code`
> (`unreal.AnimGraphService.<method>()`); reach engine toolsets with `call_tool`.
> An AnimBP **is a Blueprint**. The state-machine/AnimGraph authoring here is VibeUE
> `AnimGraphService` (intact). For its **variables and compile**, note VibeUE's `BlueprintService`
> was trimmed: **variable creation and blueprint compile moved to the engine** toolset
> `editor_toolset.toolsets.blueprint.BlueprintTools` (`add_variable`, `compile_blueprint`), called via
> `call_tool`. `BlueprintService` still has `list_variables`, `get_variable_info`,
> `set_variable_default_value`, `variable_exists`, components, and overridable functions. Bool fieldsView the complete source on GitHubanimation-editing
When your agent uses it
Preview, validate, and bake bone-rotation edits on AnimSequences with constraint awareness and retarget safety. Use when the user asks to edit/pose/adjust an animation's bones, raise an arm, create a swing/wave/dance/pose, mirror or copy a pose, set joint limits, or learn bone constraints. Load together with animsequence (keyframes) and skeleton (structure).
What it loads into context
Frontmatter
245 tokensAlways available to the agent
SKILL.md
1,301 tokensWhen the skill is activated
Reference documents
2,780 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚠<U+FE0F> Critical Rules
- Task Index
- Sub-docs
- Verification
Files
SKILL.mdcore5,179 bytesSKILL.mdcore5,179 bytesSKILL.mdcore5,179 bytesSKILL.mdcore5,179 bytesapi-reference.mddoc3,815 bytescommon-mistakes.mddoc3,141 bytesscripts/learn_constraints.txtdoc656 bytesscripts/mirror_pose.txtdoc770 bytesscripts/multi_bone_edit.txtdoc1,121 bytesscripts/preview_validate_bake.txtdoc1,219 bytesscripts/safe_discovery.txtdoc803 bytesworkflows.mddoc3,946 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "animation-system"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Animation Editing Skill
Covers the **profile → preview → validate → bake** workflow for safe bone edits with correct
bone-space handling and constraint validation.
> **Load companion skills:** `animsequence` (basic keyframe creation), `skeleton` (structure,
> retargeting), `animation-blueprint` (state machines / AnimGraph). Skills load via the engine's
> `AgentSkillToolset` (`ListSkills` / `GetSkills`) — there is no `vibeue-skills-manager` tool. Run the
> VibeUE services below with `execute_python_code` (`unreal.<Service>.<method>()`).
> **🛡<U+FE0F> Safe discovery — never `unreal.load_asset()` in loops (memory crash 0xC0000005).**
> Use `SkeletonService.list_skeletons(path)`, `AnimSequenceService.find_animations_for_skeleton(skeleton)`,View the complete source on GitHubanimation-montage
When your agent uses it
Create and manipulate Animation Montages — sections, slots, segments, branching points, notifies, and blend settings (AnimMontageService). Use when the user asks to create a montage (from an animation or empty), add or link montage sections, set up slots/segments, add branching points, or adjust montage blend timing.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
3,762 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Quick Reference - Python API
- IMPORTANT: Asset Path Format
- IMPORTANT: Return Struct Field Names (read before printing results)
- Key Workflows
- COMMON_MISTAKES
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesSKILL.mdcore14,565 bytesscripts/create_montage.txtdoc808 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "animation-system"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Animation Montage Skill
Use `AnimMontageService` for animation montage operations.
## Quick Reference - Python API
### Discovery Methods
> ⚠<U+FE0F> **`list_montages` filters are strings, not `None`** (issue #461) — pass `""` for "no
> filter", never `None` (an FString arg can't be null and raises a TypeError).
> **Playback rate:** there is no `set_playback_rate_scale` method; set the montage's `RateScale`
> directly — `unreal.load_asset(montage_path).set_editor_property("RateScale", 1.5)` then
> `unreal.EditorAssetLibrary.save_asset(montage_path)`.View the complete source on GitHubanimsequence
When your agent uses it
Create and edit AnimSequence keyframes and tracks — add/remove keyframes, set bone tracks, query sequence info, and bake edits (AnimSequenceService). Use when the user asks to create a new animation sequence, add keyframes/tracks, or edit raw animation data. For constraint-aware bone posing, also load animation-editing.
What it loads into context
Frontmatter
272 tokensAlways available to the agent
SKILL.md
3,021 tokensWhen the skill is activated
Reference documents
12,938 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚠<U+FE0F> Critical Rules
- COMMON_MISTAKES
- IMPORTANT: Asset Path Format
- Sub-docs available
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesSKILL.mdcore12,706 bytesapi-reference.mddoc8,879 bytesbone-rotation.mddoc3,729 bytesdata-structures.mddoc6,058 bytesmethod-categories.mddoc2,355 bytespatterns.mddoc11,496 bytesscripts/inspect_sequence.txtdoc829 bytesworkflows.mddoc17,848 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "animation-system"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Animation Sequence & Editing Skill
This skill covers the **inspect → profile → preview → validate → bake** workflow for safe animation bone edits with correct bone-space handling and constraint validation.
> **Loading skills:** skills load via the engine's `AgentSkillToolset` (`ListSkills` / `GetSkills`) —
> there is no `vibeue-skills-manager` tool. Run the VibeUE services below with `execute_python_code`
> (`unreal.AnimSequenceService.<method>()` / `unreal.SkeletonService.<method>()`).
>
> **Related Skills:**
> - **skeleton** - For modifying skeleton bone transforms/hierarchy and retargeting modes
> - **animation-blueprint** - For state machines and AnimGraph navigation
>View the complete source on GitHubasset-management
When your agent uses it
Import files from disk (images, meshes, any format the editor imports), export textures, query the Content Browser selection, and check if an asset is open (AssetDiscoveryService). Search, load, save, move, rename, duplicate, and delete assets are handled by Unreal's native AssetTools toolset or EditorAssetLibrary. Use when the user asks to import an image, mesh or other file from disk, export a texture, query the Content Browser selection, or check whether an asset is open in an editor. Also use for static-mesh LOD reimport, section material mapping, or gray/default surfaces after reimport.
What it loads into context
Frontmatter
169 tokensAlways available to the agent
SKILL.md
6,528 tokensWhen the skill is activated
Reference documents
452 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Data Assets & Data Tables — no dedicated VibeUE service (issues #451, #452)
- Critical Rules
- Workflows
- Sample scripts (run via `execute_python_code`)
- Additional gotchas
Scripts executed separately
scripts/mesh_material_slots.py
Files
SKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesSKILL.mdcore27,607 bytesreferences/mesh-reimport-materials.mddoc2,066 bytesscripts/find_and_save.txtdoc1,172 bytesscripts/mesh_material_slots.pyruns3,469 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "asset-management"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Asset Discovery & Management Skill
For static-mesh LOD reimport, lost textures or gray/default surfaces despite a
correct component material, read [mesh reimport material mappings](references/mesh-reimport-materials.md).
The bundled `scripts/mesh_material_slots.py` exposes explicit section inspection
and remapping through the existing engine Python API; no native service rebuild.
> 🔀 **Engine owns general asset ops now.** In the Unreal 5.8 consolidation, searching, loading,
> saving, moving, renaming, duplicating, and deleting assets moved to Unreal's native **`AssetTools`**
> toolset (reach it via `call_tool`; run `describe_toolset` for its actions) — or you can drive
> `unreal.EditorAssetLibrary` / `unreal.AssetRegistryHelpers` directly from `execute_python_code`.
> The old **`manage_asset` MCP tool is GONE.** VibeUE's `AssetDiscoveryService` was trimmed to onlyView the complete source on GitHubbehavior-trees
When your agent uses it
Create, inspect, and edit Behavior Tree and Blackboard assets — composites, tasks, decorators, services, node properties, blackboard key bindings, key CRUD and metadata, tree round-trips and validation (BehaviorTreeService + BlackboardService). Use when the user asks to build a Behavior Tree, add BT nodes or decorators, bind blackboard keys, author a blackboard, or validate/repair a BT asset.
What it loads into context
Frontmatter
243 tokensAlways available to the agent
SKILL.md
1,972 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The golden workflow
- Node paths — the addressing scheme
- Things that are not obvious and will bite you
- Round-trips, repair, safety
- Blackboards beyond key CRUD
Files
SKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytesSKILL.mdcore7,552 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this
> session, call it with `{action: "load", skill: "ai-and-navigation"}` for UE domain knowledge on
> Behavior Trees — architecture, node semantics, best practices. If no such tool is available, skip
> this line entirely and proceed with this skill alone — do NOT attempt the call.
# Behavior Trees Skill
Two services, reachable from Python (`unreal.BehaviorTreeService.*`, `unreal.BlackboardService.*`)
and as AICallable tools:
```
BlackboardService → UBlackboardData assets: create, key CRUD, metadata, re-parenting
BehaviorTreeService → UBehaviorTree assets: structure, sub-nodes, properties, build, validate
```View the complete source on GitHubblueprint-graphs
When your agent uses it
Add, connect, and configure nodes in Blueprint event graphs and function graphs — function-call/event/branch/timer/custom-event/delegate nodes, Standard Macro nodes (ForEachLoop/ForLoop/WhileLoop/DoOnce/Gate/IsValid/FlipFlop via add_macro_instance_node), macro-graph creation, pin wiring, node layout, arrays, comment boxes, and the batch build_graph API. Use when the user asks to wire up Blueprint logic, add or connect nodes, add a loop/macro node, build an event graph, set up a timer/delay, broadcast a delegate, or lay out an existing graph.
What it loads into context
Frontmatter
235 tokensAlways available to the agent
SKILL.md
11,689 tokensWhen the skill is activated
Reference documents
12,100 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Sample scripts (run via `execute_python_code`)
- Sub-docs Available
- Additional gotchas
Files
SKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesSKILL.mdcore47,800 bytesarray-operations.mddoc4,456 bytesbuild-graph.mddoc21,030 bytesfunction-classes.mddoc1,194 bytesnode-layout.mddoc2,765 bytesnode-reference.mddoc12,500 bytesscripts/build_event_graph.txtdoc1,614 bytesscripts/timer_with_custom_event.txtdoc2,615 bytesworkflows.mddoc6,086 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "blueprint-fundamentals"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Blueprint Graph Editing Skill
> **Also load `blueprints` skill** when creating new blueprints, adding variables/components, or overriding functions.
> This skill covers **node-level graph editing** — adding nodes, wiring pins, setting values, and layout.
## Critical Rules
### ⚠<U+FE0F> Nothing works during Play-In-Editor — and it fails SILENTLY
Every `BlueprintService` method resolves its target through `LoadBlueprint()`, which fails while PIE
is running. You get no error. You get an **empty array**, **`False`**, or an **empty-string node id**
— which reads exactly like "that node type doesn't exist" or "that spawner key is wrong". It is veryView the complete source on GitHubblueprints
When your agent uses it
Create and modify Blueprint assets, variables, functions, components, event dispatchers, and interfaces. Use when the user asks to create a Blueprint/BP, add a variable or component to a Blueprint, make an event dispatcher/delegate, implement a Blueprint interface, or inspect a Blueprint's class/components. For node-level graph wiring, also load blueprint-graphs.
What it loads into context
Frontmatter
193 tokensAlways available to the agent
SKILL.md
7,736 tokensWhen the skill is activated
Reference documents
1,995 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Task Index
- Sub-docs
- Verification
- Additional gotchas
Files
SKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesSKILL.mdcore31,377 bytesintrospection.mddoc4,261 bytesscripts/add_component.txtdoc1,725 bytesscripts/add_interface.txtdoc931 bytesscripts/create_blueprint.txtdoc2,895 bytesscripts/event_dispatcher.txtdoc1,632 bytesworkflows.mddoc4,081 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "blueprint-fundamentals"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Blueprint System Skill
> **For node-level graph editing** (adding nodes, connecting pins, wiring logic, timers, layout), load the `blueprint-graphs` skill.
## Critical Rules
### ⚠<U+FE0F> Components added with `add_component` are NOT on the CDO
`add_component` creates a **SCS node template**, not an instance on the class default object. So the
obvious way to configure it silently does nothing — `get_components_by_class` on the CDO returns an
empty list and the loop body never runs:
View the complete source on GitHubbulk-maintenance
When your agent uses it
Plan, dry-run, apply, verify, roll back, and resume explicit bounded batches for Blueprint interface migration, metadata hygiene, asset naming/organization, and unused-asset cleanup preparation.
What it loads into context
Frontmatter
106 tokensAlways available to the agent
SKILL.md
906 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 1. Blueprint interface migration
- 2. Blueprint metadata hygiene
- 3. Asset naming and organization
- 4. Dead/unused cleanup preparation
- Partial failure and resume
Files
SKILL.mdcore3,914 bytesSKILL.mdcore3,914 bytes
Read SKILL.md
# Safe Bulk Maintenance
Use `unreal.WorkflowService.run_bulk_maintenance(plan_json, apply, batch_size, stop_on_error)` for an
explicit target list. It is dry-run-first, path-scoped, bounded to 100 targets per GC batch, returns
one result per target, rolls back a failed apply operation, and writes a resumable report under
`Saved/VibeUE/Bulk`.
Rules:
1. Discover candidates, but pass the final explicit `targets` array yourself. Never turn a search
result directly into deletion.
2. Call once with `apply=False`, inspect every `would-change`/refusal, then repeat the exact plan with
`apply=True` and the same `resume_id`.
3. Set `path_scope` so a malformed target cannot escape the intended content folder.View the complete source on GitHubcustomizable-object
When your agent uses it
Read, build, wire, parameterize and compile Mutable Customizable Object graphs (UCustomizableObject) — skeletal mesh chains, mesh sections and materials, components, enum/float/color/texture parameters, switches, groups and child objects, compile errors (CustomizableObjectService). Use when the user asks about Mutable, a Customizable Object / CO asset, character customization graphs, or modular characters built with Mutable.
What it loads into context
Frontmatter
194 tokensAlways available to the agent
SKILL.md
2,363 tokensWhen the skill is activated
Reference documents
1,344 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The golden workflow — a compilable object
- Reading an existing object
- Things that are not obvious and will bite you
- Groups and child objects
- Compile
- Deeper reference
Files
SKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesSKILL.mdcore9,526 bytesnode-reference.mddoc5,152 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this
> session, call it with `{action: "search", query: "mutable customizable object"}` for UE domain
> knowledge on Mutable. If no such tool is available, skip this line entirely and proceed with this
> skill alone — do NOT attempt the call.
# Mutable Customizable Objects Skill
One service, reachable from Python (`unreal.CustomizableObjectService.*`) and as AICallable tools.
It edits the Customizable Object's **editor graph** (the node graph you see in the CO editor) and
compiles it. Discover exact signatures with
`discover_python_class('unreal.CustomizableObjectService')`.
- **Is Mutable on?** `is_mutable_available()`. In UE 5.8 it normally is (the default-enabled
MutableAssetUserData plugin loads it). If it returns False, every method explains that theView the complete source on GitHubengine-settings
When your agent uses it
Configure Unreal Engine core settings — rendering, physics, audio, garbage collection, console variables (cvars), and scalability levels (EngineSettingsService). Use when the user asks to change engine/rendering settings, set a console variable (r.*, etc.), adjust scalability/quality levels, or read engine config categories.
What it loads into context
Frontmatter
105 tokensAlways available to the agent
SKILL.md
1,290 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Browsing registered settings
- Workflows
- Data Structures
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore5,418 bytesSKILL.mdcore5,418 bytesSKILL.mdcore5,418 bytesSKILL.mdcore5,418 bytesSKILL.mdcore5,418 bytesSKILL.mdcore5,418 bytesSKILL.mdcore5,418 bytesscripts/set_cvars.txtdoc778 bytes
Read SKILL.md
# Engine Settings Skill
> 🔀 **Registered settings moved to the engine.** Category-based registered-setting access
> (`list_categories` / `list_settings` / `get_setting` / `set_setting`) is now Unreal 5.8's native
> **`ConfigSettingsToolset`** — reach it with `call_tool` (run `describe_toolset` on
> `ConfigSettingsToolset` for its actions/params). VibeUE's `EngineSettingsService` was trimmed to
> the delta the engine doesn't cover: **console variables (cvars), scalability levels, raw engine
> INI read/write, and config save**. Use those from `execute_python_code` as shown below.
## Critical Rules
### ⚠<U+FE0F> CVars (VibeUE) vs Registered Settings (engine toolset)
- **CVars** (console variables) → `unreal.EngineSettingsService.get_console_variable` /View the complete source on GitHubenhanced-input
When your agent uses it
Create and configure Enhanced Input — Input Actions, Mapping Contexts, key mappings, triggers, and modifiers (InputService). Use when the user asks to set up player input, create an Input Action (IA_) or Input Mapping Context (IMC_), bind keys to actions, or configure input triggers/modifiers.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
2,457 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Workflows
- Sample scripts (run via `execute_python_code`)
- PIE input injection (issue #550)
Files
SKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesSKILL.mdcore9,835 bytesscripts/setup_input.txtdoc749 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "enhanced-input"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Enhanced Input Skill
## Critical Rules
### 🚨 Real Python method names — do NOT search for the docstring's "action" names
The `InputService` class docstring lists MCP-style action ids (`action_create`,
`mapping_list_contexts`, `action_configure`, ...). Those are **not** the Python method
names — `discover_python_class(method_filter=...)` matches nothing for them. The complete
real API is below; you rarely need a discovery call at all:
| Area | Methods |View the complete source on GitHubenum-struct
When your agent uses it
Create, modify, and introspect UserDefinedEnums and UserDefinedStructs (EnumStructService). Use when the user asks to create a Blueprint enum or struct, add enum values or struct members, or inspect an enum/struct's fields. Useful for defining a DataTable row struct.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
2,324 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Workflows
- Available Property Types
- Troubleshooting
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesSKILL.mdcore9,397 bytesscripts/create_enum_struct.txtdoc808 bytes
Read SKILL.md
# Enum and Struct Skill
## Critical Rules
### Read-Only Native Types
Native C++ enums and structs are **read-only**. Only UserDefinedEnums and UserDefinedStructs can be modified:
```python
import unreal
# Search for user-defined enums only (editable)
enums = unreal.EnumStructService.search_enums("Weapon", True) # bUserDefinedOnly=True
View the complete source on GitHubfab
When your agent uses it
Search Fab's public free catalog (including Quixel Megascans) and directly import eligible assets without adding them to the account library, or discover/import the signed-in Epic account's owned Fab library. Use for free Fab/Quixel searches, owned-library questions, compatibility checks, and Fab imports. No purchasing or entitlement claiming.
What it loads into context
Frontmatter
150 tokensAlways available to the agent
SKILL.md
1,129 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Public free flow (Quixel/Megascans and other sellers)
- Owned-library flow
- Rules
Files
SKILL.mdcore5,073 bytesSKILL.mdcore5,073 bytes
Read SKILL.md
# Fab asset import
`FabService` supports two deliberately separate paths:
- **Public free catalog:** search exact zero-price listings and directly import eligible glTF/GLB
downloads. This does not sign in, purchase, claim an entitlement, or add the listing to My Library.
- **Owned library:** use the editor/launcher Epic session to list and import assets already owned by the
account, including migrated Unreal Marketplace items.
## Public free flow (Quixel/Megascans and other sellers)
1. Call `search_free_catalog(query="", seller_filter="Quixel Megascans", format_filter="gltf")`.
Results are compact and include `id`, `title`, `seller`, `price`, formats, thumbnail, and an opaque
`next_cursor`. Results require an exact-zero **Personal** tier; UEFN-reference-only offers areView the complete source on GitHubfoliage
When your agent uses it
Create foliage types and place/scatter foliage instances on landscapes and meshes (FoliageService). Use when the user asks to add trees/grass/bushes/rocks as foliage, create a foliage type from a mesh, scatter or paint foliage instances, or query/remove foliage on a surface.
What it loads into context
Frontmatter
164 tokensAlways available to the agent
SKILL.md
3,370 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Return Types - EXACT Properties
- Workflows
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesSKILL.mdcore12,690 bytesscripts/scatter_foliage.txtdoc884 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "landscape-and-foliage"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Foliage & Vegetation Skill
## Critical Rules
### Mesh Path Required
All placement methods require a valid `UStaticMesh` or `UFoliageType` asset path. Use `discover_python_class('unreal.FoliageService')` to see available methods.
### Surface Trace
All scatter/add methods trace downward to find the ground surface. If no surface is hit (e.g., position is outside the landscape bounds), that instance is rejected. Check `instances_rejected` in the result.
View the complete source on GitHubframe-rate
When your agent uses it
Diagnose and remove FPS caps so the editor and game run uncapped (or at a target FPS). Use when the user says the editor/game is "locked", "capped", or "stuck" at a frame rate (commonly 60 FPS), asks to "unlock"/"uncap"/"raise" FPS, or wants to set a max FPS. Covers t.MaxFPS, VSync, fixed/smoothed frame rate, and background CPU throttling (EngineSettingsService).
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
1,321 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚠<U+FE0F> Diagnose first — don't guess
- Workflow — read the current state
- Workflow — uncap FPS
- Verify
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore4,869 bytesSKILL.mdcore4,869 bytesSKILL.mdcore4,869 bytesSKILL.mdcore4,869 bytesscripts/uncap_fps.txtdoc1,275 bytes
Read SKILL.md
# Frame Rate / FPS Caps Skill
A "locked at 60 FPS" editor or game is almost never caused by a single setting — there
are **five independent caps** and any one of them holds the frame rate down. Check and
clear them all, in this order, before declaring it fixed.
## ⚠<U+FE0F> Diagnose first — don't guess
`t.MaxFPS = 0` already means *uncapped*, so if the editor is still stuck at 60 the cap is
coming from somewhere else (usually VSync to a 60 Hz monitor, or the smoothed frame-rate
range). Read every source below before changing anything.
> 🩺 **"Capped" vs "slow" are different problems.** If the frame rate is *low* rather than *pinned*
> at a round number, it's not a cap — it's a workload. Run `unreal.PerformanceService.frame_timing()`View the complete source on GitHubgameplay-tags
When your agent uses it
Create, list, remove, and rename Gameplay Tags with runtime registration (GameplayTagService). Use when the user asks to add or register gameplay tags, list/query existing tags, or rename/remove tags (e.g. Ability.Attack.Melee, State.Stunned).
What it loads into context
Frontmatter
131 tokensAlways available to the agent
SKILL.md
2,298 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Workflows
- API Reference
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesSKILL.mdcore9,284 bytesscripts/add_tags.txtdoc821 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "gameplay-tags"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Gameplay Tags Skill
Manage Unreal Engine Gameplay Tags. Core CRUD (add / remove / rename / list) is now owned by
Unreal 5.8's native **`GameplayTagsToolset`** (call it via `call_tool`). VibeUE keeps only the
delta the engine toolset does NOT provide — runtime hierarchy queries, bulk registration, and
tag-value lookup: `unreal.GameplayTagService.has_tag` / `get_tag_info` / `get_children` /
`add_tags` / `request_tag` / `request_tag_container`.
Tags are written to INI config **and** registered at runtime — they appear immediately in the editor tag picker without restart.
## Critical Rules
View the complete source on GitHubgas
When your agent uses it
Author and PIE-verify Gameplay Ability System content — abilities, attribute sets, gameplay effects, gameplay events, costs/cooldowns, cues — by composing Epic's GASToolsets/GameplayTagsToolset with Blueprint/Object tools and Python. Use when the user asks to add abilities, attributes, damage/buff effects, cooldowns, gameplay cues, or to inspect a live ASC.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
1,796 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Ownership matrix — who does what
- Python exposure facts (live-verified, UE 5.8)
- PIE verification recipe (one round-trip per step)
- C++ authoring gotchas (for the coding-agent handoff)
- Verification rules
Files
SKILL.mdcore7,362 bytesSKILL.mdcore7,362 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "gameplay-ability-system"}` for UE domain knowledge (ASC setup, attribute/effect/ability APIs, networking) — treat it as the rubric for any review / "best practices" question. If no such tool is available, skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Gameplay Ability System Skill
**Compose, do not duplicate.** Everything GAS needs already exists across Epic's engine toolsets,
the generic Blueprint/Object tools, and Python. VibeUE adds no GAS wrapper service; this skill is
the routing map plus the live-verified gotchas.
## Ownership matrix — who does what
| Operation | Owner |
|---|---|
| Inspect a live ASC (PIE): attributes, active tags, active effects, granted abilities | Epic **`GASToolsets.AbilitySystemInspectorToolset`** → `GetAttributeValues` / `GetActiveTags` / `GetActiveEffects` / `GetGrantedAbilities`. Input is `{"actor": {"refPath": "<actor path>"}}` — works on PIE actors, no selection needed |
| Discover attribute set classes / attributes | Epic **`GASToolsets.AttributeSetToolset`** → `FindAttributeSetClasses` / `ListAttributes` |View the complete source on GitHublandscape
When your agent uses it
Create and edit landscape terrain — heightmaps, sculpting, paint layers, terrain analysis, mesh projection, and procedural features like mountains/valleys/craters (LandscapeService). Use when the user asks to create a landscape, sculpt/raise/lower terrain, import or export a heightmap, paint terrain layers, or add procedural terrain features. For terrain materials load landscape-materials; for real-world heightmaps load terrain-data.
What it loads into context
Frontmatter
260 tokensAlways available to the agent
SKILL.md
7,926 tokensWhen the skill is activated
Reference documents
11,116 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Sub-docs available
- Critical Rules
- Related Skills
- Sample scripts (run via `execute_python_code`)
- Additional gotchas
Files
SKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesSKILL.mdcore33,116 bytesintelligent-sculpting.mddoc8,490 bytesreturn-types.mddoc4,652 bytesscripts/sculpt_terrain.txtdoc810 bytesworkflows-creation.mddoc10,419 bytesworkflows-editing.mddoc18,900 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "landscape-and-foliage"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Landscape Terrain Skill
## Sub-docs available
This skill is split into the lean index (you are reading it) plus sibling sub-docs. Skills
load via the engine's `AgentSkillToolset` (`ListSkills` / `GetSkills`) — request
`landscape/<section>` through `GetSkills`, or read the sibling `*.md` file (it sits next to
this `SKILL.md` on disk) directly:
| Sub-doc | When to load |
|---------|--------------|
| `return-types.md` | Exact property names of `LandscapeCreateResult`, `LandscapeInfo_Custom`, `LandscapeLayerInfo_Custom`, `LandscapeSplinePointInfo`, `LandscapeSplineSegmentInfo`, `LandscapeSplineMeshEntryInfo`, plus the `create_landscape` signature. |View the complete source on GitHublandscape-auto-material
When your agent uses it
Create production-quality landscape materials with the master-material + material-function + material-instance paradigm, RVT, and auto-layering. Use when the user asks for an auto/procedural landscape material, slope/altitude/distance-based layer blending, Runtime Virtual Textures, biome configuration via instances, or layer material functions. For basic layer-blend materials load landscape-materials.
What it loads into context
Frontmatter
289 tokensAlways available to the agent
SKILL.md
2,231 tokensWhen the skill is activated
Reference documents
7,167 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill
- Architecture Overview
- Critical Rules
- Sub-docs available
- Common Mistakes
- Related Skills
Files
SKILL.mdcore9,954 bytesSKILL.mdcore9,954 bytesSKILL.mdcore9,954 bytesSKILL.mdcore9,954 bytesSKILL.mdcore9,954 bytesSKILL.mdcore9,954 bytesarchitecture-details.mddoc3,920 bytesbiomes-and-templates.mddoc4,545 bytesmaterial-functions.mddoc2,053 bytesparameter-reference.mddoc4,473 bytesreference-example.mddoc2,140 bytesrvt-setup.mddoc2,289 bytesworkflows.mddoc8,897 bytes
Read SKILL.md
# Landscape Auto-Material System Skill
## When to Use This Skill
Use this skill when you need **production-quality** landscape materials with:
- A master material → material instance workflow (artists change parameters, not graphs)
- Automatic layer blending by slope, altitude, or distance
- Material functions for reusable logic (layer sampling, color correction, etc.)
- Runtime Virtual Textures for scalable landscape rendering
- Biome configuration through material instances (swap textures/thresholds, same master)
For **simple prototyping** with 2-5 painted layers, load the **landscape-materials** skill instead (the engine's AgentSkillToolset `GetSkills` exposes it).
## Architecture OverviewView the complete source on GitHublandscape-materials
When your agent uses it
Create landscape materials with layer blending, texture setup, and layer info objects (LandscapeMaterialService). Use when the user asks to build a landscape/terrain material, set up paint layers (grass/rock/dirt), create layer info objects, add a grass output, or assign a material to a landscape. For production master-material+RVT systems, load landscape-auto-material.
What it loads into context
Frontmatter
203 tokensAlways available to the agent
SKILL.md
1,517 tokensWhen the skill is activated
Reference documents
3,404 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use This Skill vs. landscape-auto-material
- Critical Rules
- Task Index
- Sub-docs
- Verification
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore6,624 bytesSKILL.mdcore6,624 bytesSKILL.mdcore6,624 bytessatellite.mddoc3,114 bytesscripts/create_landscape_material.txtdoc929 bytesworkflows.mddoc11,256 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "materials-and-shaders"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Landscape Material System Skill
## When to Use This Skill vs. landscape-auto-material
- **This skill** (`landscape-materials`): Simple materials with 2-5 layers using `LandscapeLayerBlend`. Good for prototyping.
- **`landscape-auto-material`**: Production materials using material functions, RVT, and material instances. Good for shipping quality. Use when you need the Real_Landscape paradigm with auto-layering, altitude/slope blending via material functions, and biome configuration through material instances.
If you need material functions, Runtime Virtual Textures, or the master-material + instance pattern, load the **landscape-auto-material** skill (the engine's AgentSkillToolset `GetSkills` exposes it).
## Critical Rules
### 🚨 Inspect Before Modifying Existing Landscape MaterialsView the complete source on GitHublevel-actors
When your agent uses it
List, find, place, move, rotate, and modify actors in the current level (ActorService + editor subsystems). Use when the user asks to find/list actors in the level, move or rotate an actor, set an actor's properties/folder/transform, or spawn/delete level actors.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
6,402 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Workflows
- Re-run a placed actor's construction script
- Sample scripts (run via `execute_python_code`)
- Additional gotchas
Files
SKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesSKILL.mdcore25,733 bytesscripts/manipulate_actors.txtdoc1,181 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "actors-and-components"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Level Actors Skill
> 🔀 **Engine owns the basics now.** In the Unreal 5.8 consolidation, listing / finding / spawning /
> moving / transforming / selecting actors moved to Unreal's native toolsets — `ActorTools`,
> `SceneTools`, and `EditorAppToolset` (selection, camera, PIE, screenshots), reachable via
> `call_tool`. Equivalently you can drive `unreal.EditorActorSubsystem` /
> `unreal.LevelEditorSubsystem` directly from `execute_python_code` (shown throughout below).
> **VibeUE's `ActorService` was trimmed to only the delta the engine doesn't provide:** transform
> lock (`set_actor_lock_location`), absolute-transform flags, preserve-scale-ratio, viewport camera
> framing (`get_actor_view_camera` / `calculate_actor_view` / `set_viewport_camera`), and full
> property dumps (`get_all_properties`). `ActorService.add_actor` / `set_property` / `get_property`
> no longer exist — use the engine toolsets or `EditorActorSubsystem` for spawning and property edits.View the complete source on GitHubmap-blockout
When your agent uses it
Procedurally design an AAA-style open-world FPS map blockout (roads, POIs, fields, forests/treelines, railway/bridges) from a landscape, validate it through gated checks, and materialize it into engine geometry. Use when the user asks to block out or lay out an open-world/FPS map, place roads/POIs/forests/railways procedurally, or turn a blockout plan into splines, paint layers, foliage, and actors.
What it loads into context
Frontmatter
304 tokensAlways available to the agent
SKILL.md
1,918 tokensWhen the skill is activated
Reference documents
14,437 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Sub-docs available
- Critical Rules
- Two-Phase Workflow
- Status
- Related Skills
Files
SKILL.mdcore7,562 bytesSKILL.mdcore7,562 bytesSKILL.mdcore7,562 bytesSKILL.mdcore7,562 bytesSKILL.mdcore7,562 bytesSKILL.mdcore7,562 bytesSKILL.mdcore7,562 bytesconfig-reference.mddoc3,993 bytesmaterialization.mddoc6,839 bytesreturn-types.mddoc5,698 bytesstage-rules.mddoc10,982 bytesworkflows.mddoc7,773 bytes../../../docs/design/map-designer-spec.mddoc20,127 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "levels-and-world-partition"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Procedural FPS Map Blockout Skill
Take a VibeUE-generated landscape (heightmap + paint layers) and turn it into a
fully validated, AAA-style open-world FPS map blockout — roads, POIs, fields,
forests/treelines, railway, bridges — then materialize the plan as real engine
geometry. Quality benchmark is **Arma / Squad**.
The design pipeline is **gated**: every stage runs ordered pass/fail checks
against the authoritative spec at [docs/design/map-designer-spec.md](../../../docs/design/map-designer-spec.md).
You may not advance until all checks PASS. On failure, fix the offending element
and re-run the stage.
View the complete source on GitHubmaterials
When your agent uses it
Create and edit materials and material instances — graph nodes, parameters, functions, custom HLSL, and instance overrides (MaterialService + MaterialNodeService). Use when the user asks to create or edit a material/material instance, wire material nodes, add material parameters, set blend/shading modes, or recreate a material graph. For landscape materials load landscape-materials. Also use for generated organic PBR detail, texture seams, projection coordinates, and surface-normal diagnosis.
What it loads into context
Frontmatter
157 tokensAlways available to the agent
SKILL.md
5,412 tokensWhen the skill is activated
Reference documents
3,728 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Task Index
- Sub-docs
- Verification
- Related skills
- Additional gotchas
Files
SKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesSKILL.mdcore23,204 bytesreference.mddoc4,232 bytesreferences/generated-organic-surfaces.mddoc2,580 bytesscripts/create_instance.txtdoc2,019 bytesscripts/create_material.txtdoc2,652 bytesscripts/export_graph.txtdoc976 bytesscripts/material_graph_batch.txtdoc2,536 bytesworkflows.mddoc8,821 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "materials-and-shaders"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Material System Skill
For generated textures on large organic surfaces, seams after triplanar projection,
or overly strong tissue relief, read [generated organic surfaces](references/generated-organic-surfaces.md).
For gray/default surfaces after mesh reimport, use the asset-management skill's
LOD-section mapping helper before changing the shader or buying new textures.
## Critical Rules
### Material information over MCP: use `GetMaterialInfoResult`
Call `VibeUE.MaterialService.GetMaterialInfoResult` with only `materialPath`.View the complete source on GitHubmetasounds
When your agent uses it
Create and modify MetaSound Source assets — add/connect nodes, wire pins, set input defaults, and play procedurally (MetaSoundService). Use when the user asks to create a MetaSound, build or edit a MetaSound graph, add operator/input/output nodes, or generate procedural audio.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
5,498 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Key Concepts
- Workflow
- Method Reference
- Common DataTypes
- Complete Example — 880 Hz Sine Tone
- Complete Example — One-Shot SoundWave (Gunshot)
- Return Type Attribute Reference
- Known Node Pins
- Connecting to a Stereo (or Quad) output
- Notes
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesSKILL.mdcore20,341 bytesscripts/create_metasound.txtdoc776 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "audio-and-metasounds"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# MetaSound Service Skill
Use this skill to create and edit MetaSound Source assets via Python.
```python
import unreal
ms = unreal.MetaSoundService()
```
## Key Concepts
- **MetaSound Source** — a procedural audio asset (`UMetaSoundSource`) defined by a node graph. It replaces SoundCue for runtime-parameterisable sounds.View the complete source on GitHubniagara-emitters
When your agent uses it
Niagara emitter color/curve authoring (tint, hue-shift, ColorFromCurve keys), rapid-iteration parameter tuning, and Custom-HLSL scratch-pad authoring (NiagaraEmitterService + NiagaraScratchPadService). Module/renderer CRUD is owned by the engine NiagaraToolsets. Use when the user asks to recolor or hue-shift particles, edit color curves, tune emitter params, or build a scratch-pad/Custom HLSL module. For system-level lifecycle, load niagara-systems.
What it loads into context
Frontmatter
339 tokensAlways available to the agent
SKILL.md
2,096 tokensWhen the skill is activated
Reference documents
6,439 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Niagara Emitters Skill
- ⚠<U+FE0F> CRITICAL: Script Stages
- Task Index
- Sub-docs
- Verification
Files
SKILL.mdcore8,220 bytesSKILL.mdcore8,220 bytesSKILL.mdcore8,220 bytescolor.mddoc9,308 bytesreference.mddoc3,937 bytesscratch-pad.mddoc11,107 bytesscripts/build_emitter.txtdoc1,933 bytesscripts/recolor_emitter.txtdoc1,081 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "niagara-vfx"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
## Niagara Emitters Skill
> **Architecture (read first):** VibeUE extends Unreal's native MCP endpoint. Emitter **module and
> renderer CRUD** (add/remove/enable/reorder modules, add/remove renderers, set module/renderer
> inputs, search module scripts) are owned by the **engine** `NiagaraToolsets.*` toolsets, called
> through `call_tool`. VibeUE's `NiagaraEmitterService` was trimmed to the **color/curve authoring**
> the engine doesn't provide, plus a rapid-iteration-parameter reader.
**VibeUE `NiagaraEmitterService` (this skill) keeps ONLY color/curve authoring + a param reader:**
- `set_color_tint` — add/set a ScaleColor tint (handles ColorFromCurve automatically)
- `get_color_curve_keys` / `set_color_curve_keys` — read/replace ColorFromCurve keyframes
- `shift_color_hue` — hue-rotate a ColorFromCurve while preserving detail (best for recolors)View the complete source on GitHubniagara-systems
When your agent uses it
Rapid-iteration parameter tuning, diagnostics, and Custom-HLSL scratch-pad authoring for Niagara systems (VibeUE NiagaraService + NiagaraScratchPadService). System/emitter/parameter CRUD is owned by the engine NiagaraToolsets. Use when the user asks to tune emitter rapid-iteration params, compare/diagnose systems, or build scratch-pad/Custom HLSL modules. For emitter color/module work, load niagara-emitters.
What it loads into context
Frontmatter
207 tokensAlways available to the agent
SKILL.md
2,818 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Niagara Systems Skill
- Loading skills
- ⚠<U+FE0F> System / emitter / parameter CRUD → engine NiagaraToolsets
- ⚠<U+FE0F> Parameter Discovery Order (rapid-iteration tuning)
- Quick Reference (VibeUE NiagaraService — kept methods)
- ⚠<U+FE0F> User Parameter Types (engine `NiagaraToolsets` — reference)
- Related
- Additional gotchas
Files
SKILL.mdcore11,278 bytesSKILL.mdcore11,278 bytesSKILL.mdcore11,278 bytesSKILL.mdcore11,278 bytesscripts/create_system.txtdoc1,878 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "niagara-vfx"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
## Niagara Systems Skill
> **Architecture (read first):** VibeUE extends Unreal's native MCP endpoint. System / emitter /
> parameter **create / add / copy / remove / list / compile** are owned by the **engine** toolset
> `NiagaraToolsets.NiagaraToolset_System` (plus `…_Assets`, `…_Component`, `…_Blueprint`, `…_Info`),
> called through `call_tool`. VibeUE's `NiagaraService` was trimmed to the rapid-iteration-parameter
> tuning + diagnostics that the engine toolset does not cover, and `NiagaraScratchPadService`
> (Custom-HLSL graph authoring) which is unique to VibeUE.
**VibeUE `NiagaraService` (this skill) keeps ONLY:**
- Rapid-iteration parameter read/write — `list_rapid_iteration_params`, `set_rapid_iteration_param`, `set_rapid_iteration_param_by_stage`
- Diagnostics — `compare_systems`, `get_emitter_lifecycle`, `debug_activation`View the complete source on GitHubpcg
When your agent uses it
Create, inspect, and edit PCG Graph assets — add nodes, configure settings, connect pins, and wire procedural generation graphs (native PCG Python API). Use when the user asks to build a PCG graph, add PCG nodes (Surface Sampler, Static Mesh Spawner, filters), wire PCG pins, place a PCGVolume and generate, or set up procedural scattering.
What it loads into context
Frontmatter
276 tokensAlways available to the agent
SKILL.md
1,744 tokensWhen the skill is activated
Reference documents
3,643 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚠<U+FE0F> Read this before writing any code
- ⚠<U+FE0F> Prerequisites
- Creating a PCG Graph Asset
- Loading an Existing PCG Graph
- Adding Nodes
- Identifying Nodes
- Discovering Available Node Types
- Task Index
- Sub-docs
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesSKILL.mdcore6,910 bytesreference.mddoc4,566 bytesscripts/build_pcg_graph.txtdoc1,220 bytesworkflows.mddoc10,228 bytes
Read SKILL.md
# PCG Skill
PCG (Procedural Content Generation) in UE 5.7 is production-ready and fully scriptable via
the `PCGPythonInterop` plugin. No VibeUE service wrapper is needed — the Python API is complete.
## ⚠<U+FE0F> Read this before writing any code
These are the mistakes that cause infinite retry loops. Check each one before executing:
**Do not call `discover_python_class` or `discover_python_function` on any PCG class — this skill contains everything you need. Calling discover bloats context and causes content filter failures.**
1. **Volume Sampler input pin is `"Volume"`, not `"In"`** — `add_edge(input_node, 'In', sampler_node, 'Volume')`. Using `'In'` silently no-ops and produces 0 points.
2. **`voxel_size` is a `Vector`, not a float** — `set_editor_property('voxel_size', unreal.Vector(200, 200, 200))`. Passing a float raises a TypeError.View the complete source on GitHubpie-testing
When your agent uses it
Start, stop, and query Play-In-Editor (PIE) sessions for runtime testing of Blueprints, gameplay logic, widgets, AI, and any in-game behavior. Use when the user asks you to "play", "test", "run", "PIE", "start/stop the game", or otherwise needs a live game world to validate changes.
What it loads into context
Frontmatter
201 tokensAlways available to the agent
SKILL.md
7,344 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- PIE control — engine `EditorAppToolset`
- Standard Test Loop
- Net mode from Python — `EngineSettingsService`
- Validating widgets in PIE — `WidgetService`
- Spawning test actors in PIE — `PIEActorService`
- Calling functions with real RPC routing — `PIEActorService.call_function`
- Driving gameplay input in PIE — `InputService` (issue #550)
- Seeing the game — `capture_image` (issues #544/#546)
- Full-rate unfocused verification — `PerformanceService` (issue #549)
- Gotchas
- When to use PIE
- When NOT to use PIE
- Additional gotchas
Files
SKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesSKILL.mdcore30,329 bytesscripts/pie_test_loop.txtdoc951 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "automation-and-testing"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Play-In-Editor (PIE) Testing Skill
PIE is the only way to validate runtime behavior — Blueprint logic, AI ticking, animation, input, widget interaction, gameplay events. Without starting PIE, your "fix" is unverified.
## PIE control — engine `EditorAppToolset`
Generic PIE start/stop/status is owned by Unreal 5.8's native **`EditorToolset.EditorAppToolset`**,
invoked through `call_tool` (run `describe_toolset` on it for exact action names/params):
| Action | Description |
|--------|-------------|
| `StartPIE` | Start PIE if not already running. Succeeds (no-op) if already running. |View the complete source on GitHubprofiling
When your agent uses it
Diagnose frame-rate bottlenecks (CPU vs GPU bound FIRST), control Unreal Insights traces, sample live frame times, and annotate performance captures. Use when FPS is low/bad, the game is slow, or you need to find what is limiting the frame rate.
What it loads into context
Frontmatter
195 tokensAlways available to the agent
SKILL.md
4,519 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- 🚦 STEP 0 — Is it CPU-bound or GPU-bound? (DO THIS FIRST, ALWAYS)
- ⏱<U+FE0F> Frame-time budgets — what a target FPS actually costs
- 🛠<U+FE0F> CVars tune the renderer — they do NOT fix the game thread
- ⚠<U+FE0F> Gotchas — read before writing any code
- Trace Control
- Annotations — Mark Regions and Bookmarks
- Reading a capture back — `analyse()`
- Standalone capture — representative readings
- Recommended flow
- Channel Reference
- Opening Traces in Unreal Insights
Files
SKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytesSKILL.mdcore18,071 bytes
Read SKILL.md
# Profiling Skill
Unreal 5.8's native toolsets have **no** performance or tracing tools, so this is VibeUE's net-new
capability: `unreal.PerformanceService` answers "are we CPU- or GPU-bound?" and drives Unreal
Insights captures from Python with no C++ required. Run everything here through `execute_python_code`.
The whole API is small — read the live signatures once with
`discover_python_class(class_name="unreal.PerformanceService")`:
| Method | Purpose |
|--------|---------|
| `frame_timing(target_fps=60.0)` | Game/Render/GPU/RHI thread ms + a CPU-vs-GPU `bound` verdict + a `hint`, plus a per-thread `budget` breakdown gated against `target_fps` (`budget.meets_target` PASS/FAIL). **Run FIRST.** |
| `force_hitch(thread="game", ms=250.0, frames=1)` | Validation helper — deliberately stall a KNOWN thread (`"game"`/`"render"`/`"both"`/`"gpu"`) to confirm the verdict fires. CPU paths are self-measuring: validate from the SAME response (`observed_peak_*_ms`, `verdict_matched_expect`) — do NOT follow up with `frame_timing`. Only the async `gpu` path is read back on a following frame. Clamped (≤5000 ms, ~10 s total) for safety. |
| `report(title=..., source="both", file="")` | Write a self-contained, shareable HTML report (live verdict + budget + analyse stats + a data-driven "fix in this order" list) to `Saved/VibeUE/Performance/report_<timestamp>.html`. |View the complete source on GitHubproject-settings
When your agent uses it
Configure Unreal Engine project settings and editor preferences — UI appearance, toolbar icons, scale, colors, and any UDeveloperSettings subclass (ProjectSettingsService). Use when the user asks to change a project setting or editor preference, configure a UDeveloperSettings category, or read/write project config values.
What it loads into context
Frontmatter
93 tokensAlways available to the agent
SKILL.md
2,863 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Workflows
- Data Structures
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesSKILL.mdcore12,288 bytesscripts/configure_setting.txtdoc946 bytes
Read SKILL.md
# Project Settings Skill
> 🔀 **Registered settings moved to the engine.** Category-based registered-setting access
> (`list_categories` / `list_settings` / `get_setting` / `set_setting` /
> `set_category_settings_from_json`) is now Unreal 5.8's native **`ConfigSettingsToolset`** — reach
> it with `call_tool` (run `describe_toolset` on `ConfigSettingsToolset` for its actions/params).
> VibeUE's `ProjectSettingsService` was trimmed to the delta the engine doesn't cover:
> **`discover_settings_classes` + direct INI read/write (`get_ini_value` / `set_ini_value` /
> `*_ini_array` / `list_ini_sections` / `list_ini_keys`) + config save**, plus
> **`set_settings_property` / `get_settings_property`** for one property of a settings class by
> name. Use those from `execute_python_code` as shown below.
## Critical Rules
View the complete source on GitHubskeleton
When your agent uses it
Edit skeleton bone transforms/hierarchy, retargeting modes, curve metadata, blend profiles, bone constraints, and learn constraints from animations (VibeUE SkeletonService). Socket CRUD, bone enumeration, physics-asset, and material/LOD inspection are owned by the engine SkeletalMeshTools. Use when the user asks to add/transform bones, set retargeting, manage blend profiles or curves, or set bone constraints. For animation bone edits, also load animation-editing.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
4,554 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Sockets, bone enumeration, inspection → engine SkeletalMeshTools
- Critical Rules
- Workflows
- Data Structures
- Common Mistakes
- Related
Files
SKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesSKILL.mdcore17,660 bytesscripts/add_socket.txtdoc1,393 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "animation-system"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Skeleton & Skeletal Mesh Skill
> **Architecture (read first):** VibeUE extends Unreal's native MCP endpoint. **Socket CRUD, bone
> enumeration, physics-asset assignment, and material/LOD/morph inspection** are owned by the **engine**
> toolset `editor_toolset.toolsets.skeletal_mesh.SkeletalMeshTools` (called via `call_tool`). VibeUE's
> `SkeletonService` was trimmed to what the engine doesn't cover: **bone transform/hierarchy editing,
> retargeting config, curve metadata, blend profiles, bone constraints, and learn-from-animations**.
>
> **Loading skills:** skills load through the engine's `AgentSkillToolset` (`ListSkills`/`GetSkills`) —
> there is no `vibeue-skills-manager` tool. Run VibeUE services with `execute_python_code`
> (`unreal.SkeletonService.<method>()`); reach engine tools with `call_tool` (discover with
> `list_toolsets` / `describe_toolset`).View the complete source on GitHubsound-cues
When your agent uses it
Create and modify SoundCue assets — add/connect nodes (mixer, random, delay, attenuation, modulator, etc.) and set audio properties (SoundCueService). Use when the user asks to create a Sound Cue, build a SoundCue node graph, or wire audio playback logic.
What it loads into context
Frontmatter
239 tokensAlways available to the agent
SKILL.md
3,110 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Service Access
- Audio Flow Direction
- Critical Rules
- Workflows
- API Reference
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesSKILL.mdcore11,179 bytesscripts/create_sound_cue.txtdoc682 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "audio-and-metasounds"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
> **Wrong skill for MetaSound assets?** If the user asked about `MetaSound`, `MS_` assets, or `UMetaSoundSource`, load the `metasounds` skill instead (via `GetSkills` / AgentSkillToolset).
> SoundCue and MetaSound are completely separate systems — do not use `SoundCueService` for MetaSound tasks.
# Sound Cue Editor Skill
## Service Access
```python
import unreal
svc = unreal.SoundCueService()
```
View the complete source on GitHubstate-trees
When your agent uses it
Create, inspect, and edit StateTree assets — states, tasks, transitions, conditions, considerations, and property bindings for AI behavior and game logic (StateTreeService). Use when the user asks to build a StateTree, add states/tasks/transitions, bind task properties, set up Utility AI considerations, or wire StateTree delegate transitions.
What it loads into context
Frontmatter
220 tokensAlways available to the agent
SKILL.md
6,180 tokensWhen the skill is activated
Reference documents
14,665 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- ⚠<U+FE0F> StateTree Blueprint Tasks Require the Blueprints Skill
- ⚠<U+FE0F> STT Graph Editing Rules
- Key Concepts
- State Paths
- ⚠<U+FE0F> Common Mistakes
- Workflow
- Sub-docs available
- COMMON_MISTAKES
- Sample scripts (run via `execute_python_code`)
- Additional gotchas
Files
SKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesSKILL.mdcore25,900 bytesapi-bindings.mddoc22,574 bytesapi-reference.mddoc9,923 bytesblueprint-tasks.mddoc6,562 byteschangelog.mddoc17,537 bytesevent-payloads.mddoc4,176 bytesscripts/build_state_tree.txtdoc1,614 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "ai-and-navigation"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# StateTree Skill
StateTree is Unreal Engine's hierarchical state machine system for AI behavior and game logic.
This skill covers creating and editing StateTree assets via `unreal.StateTreeService`.
## ⚠<U+FE0F> StateTree Blueprint Tasks Require the Blueprints Skill
**StateTree Tasks prefixed `STT_` (e.g. `STT_Rotate`, `STT_Move`) are Blueprint assets.**
They are edited with `BlueprintService`, not `StateTreeService`.
**Always load the `blueprints` skill** when the user asks to:
- Add or edit variables on an STT taskView the complete source on GitHubterrain-data
When your agent uses it
Generate heightmaps, map reference images, and water feature splines (rivers, lakes, oceans) from real-world geographic data (terrain_data tool). Use when the user asks to build terrain from a real location/coordinates, download a real-world heightmap, or add rivers/lakes/oceans from map data. Downloads Mapbox tiles server-side and produces UE5-compatible heightmaps + landscape splines.
What it loads into context
Frontmatter
243 tokensAlways available to the agent
SKILL.md
4,253 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Test Prompts
- Step-by-Step Example (Mount Fuji)
- Parameters Reference
- UE5 Landscape Import Settings
- Terrain Character Guide
- Water Features Reference
- Troubleshooting
Files
SKILL.mdcore15,213 bytesSKILL.mdcore15,213 bytesSKILL.mdcore15,213 bytesSKILL.mdcore15,213 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "landscape-and-foliage"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# Real-World Terrain Skill
Generates heightmaps and water feature splines from real geographic coordinates via the `terrain_data`
MCP tool. The tool downloads Mapbox tiles server-side and writes UE5-compatible heightmaps + landscape
splines into the project's `Saved/Terrain/` folder — no API key or chat configuration is required.
## Workflow
### Heightmap (always run first)
1. `preview_elevation` — fetch elevation stats + suggested settings. Returns `suggestedZScale`, `suggestedXYScales` (resolution → XY scale), height range.
2. `generate_heightmap` — generate the 16-bit PNG using suggested settingsView the complete source on GitHubumg-widgets
When your agent uses it
Create and modify UMG Widget Blueprints (UI) — build the widget hierarchy, set properties, style fonts/brushes, author widget animations, bind events, capture previews, run PIE checks, and wire MVVM ViewModels. Use when the user asks to create a UI/HUD/menu, add or arrange widgets (Button, TextBlock, Image, panels), style or animate a widget, or set up data bindings in a Widget Blueprint (WBP).
What it loads into context
Frontmatter
208 tokensAlways available to the agent
SKILL.md
4,182 tokensWhen the skill is activated
Reference documents
6,180 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Critical Rules
- Task Index
- Sub-docs
- Verification (do this before claiming success)
- Additional gotchas
Files
SKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesSKILL.mdcore16,494 bytesmvvm.mddoc4,237 bytesreference.mddoc10,747 bytesscripts/apply_brush.txtdoc1,501 bytesscripts/apply_font.txtdoc1,302 bytesscripts/build_menu.txtdoc1,336 bytesscripts/capture_preview.txtdoc892 bytesscripts/create_animation.txtdoc1,241 bytesscripts/create_widget.txtdoc1,107 bytesscripts/edit_slots.txtdoc1,428 bytesscripts/inspect_hierarchy.txtdoc964 bytesscripts/mvvm_hud.txtdoc2,059 bytesscripts/pie_inspect.txtdoc1,430 bytesworkflows.mddoc9,143 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "umg-and-slate"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# UMG Widget Blueprints Skill
This skill covers authoring **Widget Blueprints (WBP)** with `WidgetService`. Read the Critical Rules
below first — they prevent the most common failures. Then pick a task from the Task Index and load the
matching workflow doc and/or run the matching sample script.
> Load the **`blueprints`** skill when you also need to add Blueprint variables, functions, or
> components, and **`blueprint-graphs`** when wiring event-graph nodes for bound events.
## Critical Rules
### 🚨 Creating Widget Blueprints — only one pattern worksView the complete source on GitHubuv-mapping
When your agent uses it
Inspect, generate, transform, and visualize UV channels on StaticMesh assets (UVMappingService). Use when the user asks to check/add/remove UV channels, auto-unwrap UVs, transform (tile/offset/rotate) UVs, check UV health/islands, or export a UV layout image.
What it loads into context
Frontmatter
186 tokensAlways available to the agent
SKILL.md
5,004 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When NOT to Use This Service
- Critical Rules
- Per-Region UV Edits (Artist-Grade)
- Common Mistakes to Avoid
- Return Types — Exact Properties
- Workflows
- Property Formats
- Verification After Edits
- Sample scripts (run via `execute_python_code`)
Files
SKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesSKILL.mdcore19,255 bytesscripts/inspect_uvs.txtdoc653 bytes
Read SKILL.md
> 🧠 **Brains complement:** IF an `unreal-engine-skills-manager` tool (external MCP) exists in this session, call it with `{action: "load", skill: "meshes-static-and-skeletal"}` for UE domain knowledge on this topic — correct APIs, architecture, best practices — and treat it as the rubric for any review / "best practices" question. If no such tool is available (e.g. running under Claude Code or Codex without that MCP), skip this line entirely and proceed with this skill alone — do NOT attempt the call.
# UV Mapping Skill
For seams on imported organic assets, first distinguish UV boundaries from split
corner normals, image-border wrapping and invalid material-section indices. See
the materials skill's `references/generated-organic-surfaces.md` and the
asset-management skill's `references/mesh-reimport-materials.md`. Do not unwrap
an approved mesh merely because its shading has a sharp band.
`UVMappingService` provides automation-grade UV channel manipulation for StaticMesh assets in UE 5.7+. The service is built around mesh-description editing and post-build commits — every mutation marks the package dirty and rebuilds render data, but **does not save**. Follow with `unreal.EditorAssetLibrary.save_asset(mesh_path)` once you finish a batch.
## When NOT to Use This Service
View the complete source on GitHubvibeue
When your agent uses it
Unreal Engine 5 development using the VibeUE Python API. Use when working in Unreal Engine — blueprints, state trees, materials, actors, landscapes, animation, niagara, widgets, sound, foliage, gameplay tags, enhanced input, skeletons, PCG (procedural content generation), and more. VibeUE is an extension of Unreal's native MCP endpoint.
What it loads into context
Frontmatter
84 tokensAlways available to the agent
SKILL.md
6,526 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Wait for VibeUE readiness after launch
- Health heartbeat — dead or wedged editor detection
- Persisted Python results -- a timed-out call is not a failed call
- Discover and load skills
- How work gets done — `execute_python_code` is the workhorse
- Never leave a map loaded - it crashes the editor on the next level change
- Tools — what each is for
- Engine toolsets replace the old VibeUE tools
- Gate and audit helpers in `vibeue`
- Additional gotchas
Files
SKILL.mdcore26,452 bytesSKILL.mdcore26,452 bytesSKILL.mdcore26,452 bytesSKILL.mdcore26,452 bytesSKILL.mdcore26,452 bytesSKILL.mdcore26,452 bytesSKILL.mdcore26,452 bytes
Read SKILL.md
VibeUE is an **extension on Unreal Engine's native MCP endpoint** (`http://localhost:8000/mcp`).
There is no separate VibeUE server, no API key, and no in-editor chat — VibeUE simply registers
extra Python services (`unreal.<Service>`) and skill packs on top of the engine's own toolsets.
## Wait for VibeUE readiness after launch
`BuildAndLaunchGame.ps1` / `.sh` print `Editor-PID=<pid>` — treat that as the process identity. Check
once, then watch the filesystem for `<ProjectDir>/Saved/VibeUE/Signals/editor-<pid>-true.json` before
using MCP. Wait at most 180 seconds, do not poll MCP while waiting, and fail if that Editor process
exits or the timeout expires. Ignore signal files for other or dead PIDs. The signal only means
`RegisterToolsets()` reached its end; Python, World, and level readiness remain separate checks.
The file is JSON, written atomically, so it is complete the moment it appears:
View the complete source on GitHubviewport
When your agent uses it
Control the Unreal Editor level viewport — camera type/position, view mode, FOV, exposure, layout, and rendering settings (ViewportService). Use when the user asks to move the editor camera, change the view mode (Lit/Unlit/Wireframe), set FOV/exposure, switch viewport layout, or frame the level for a screenshot.
What it loads into context
Frontmatter
162 tokensAlways available to the agent
SKILL.md
5,284 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Methods
- Critical Rules
- Workflows
- Sample scripts (run via `execute_python_code`)
- Additional gotchas
Files
SKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesSKILL.mdcore20,744 bytesscripts/set_camera.txtdoc907 bytes
Read SKILL.md
# Viewport Control Skill
## Methods
| Method | Description |
|--------|-------------|
| `get_viewport_info()` | Get full viewport state (type, camera, FOV, exposure, layout) |
| `set_viewport_type(type)` | Switch perspective/orthographic views |
| `get_viewport_type()` | Get current view type as string |
| `set_view_mode(mode)` | Switch rendering mode (lit, wireframe, unlit, etc.) |
| `get_view_mode()` | Get current rendering mode |
| `set_fov(degrees)` | Set field of view (5-170, default 90) |
| `get_fov()` | Get current FOV |
| `set_near_clip_plane(distance)` | Set near clipping plane (-1 = engine default) |View the complete source on GitHubSkills included
- animation-blueprint
- animation-editing
- animation-montage
- animsequence
- asset-management
- behavior-trees
- blueprint-graphs
- blueprints
- bulk-maintenance
- customizable-object
- engine-settings
- enhanced-input
- enum-struct
- fab
- foliage
- frame-rate
- gameplay-tags
- gas
- landscape
- landscape-auto-material
- landscape-materials
- level-actors
- map-blockout
- materials
- metasounds
- niagara-emitters
- niagara-systems
- pcg
- pie-testing
- profiling
- project-settings
- skeleton
- sound-cues
- state-trees
- terrain-data
- umg-widgets
- uv-mapping
- vibeue
- viewport
Repository facts
- License
- MIT
- Created
- Sep 12, 2025
- Last pushed
- Nov 5, 2026
- Forks
- 178
- Open issues
- 2
- Project activity
- Active
Rank over the last 12 weeks
Now #987 · best #760 · down 214 in 30 days
- #859 on Oct 19
- #872 on Oct 20
- #883 on Oct 21
- #857 on Oct 22
- #869 on Oct 23
- #987 since Oct 25
67 earlier periods
- #761 on Aug 2
- #763 on Aug 7
- #777 on Aug 9
- #811 from Aug 10 to Aug 11
- #809 on Aug 12
- #811 on Aug 13
- #796 on Aug 14
- #768 on Aug 15
- #791 on Aug 16
- #799 on Aug 17
- #819 on Aug 18
- #813 on Aug 19
- #805 on Aug 20
- #807 on Aug 21
- #760 on Aug 22
- #809 on Aug 23
- #828 on Aug 24
- #833 on Aug 25
- #820 on Aug 26
- #824 on Aug 27
- #858 on Aug 28
- #779 on Aug 29
- #786 on Aug 30
- #829 on Aug 31
- #850 on Sep 1
- #825 on Sep 2
- #835 on Sep 3
- #805 on Sep 4
- #785 on Sep 5
- #815 on Sep 6
- #834 on Sep 7
- #859 on Sep 8
- #836 on Sep 9
- #831 on Sep 10
- #802 on Sep 12
- #828 on Sep 14
- #819 on Sep 15
- #830 on Sep 16
- #829 on Sep 17
- #818 on Sep 18
- #795 on Sep 19
- #811 on Sep 20
- #823 on Sep 21
- #852 on Sep 22
- #836 on Sep 23
- #800 on Sep 24
- #773 on Sep 25
- #781 on Sep 26
- #811 on Sep 27
- #836 on Sep 28
- #865 on Sep 29
- #843 on Sep 30
- #789 on Oct 1
- #816 on Oct 4
- #829 on Oct 5
- #826 on Oct 6
- #850 on Oct 7
- #892 on Oct 8
- #855 on Oct 9
- #835 on Oct 10
- #834 on Oct 11
- #854 on Oct 12
- #859 from Oct 13 to Oct 14
- #844 on Oct 15
- #854 on Oct 16
- #828 on Oct 17
- #814 on Oct 18
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 7, 2026
Risk level changed on Nov 7, 2026
New signal: Dangerous shell operation
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 511 notes
Content/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedContent/Skills/animation-blueprint/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 1 dangerous shell commandin 1 file: vibeue/SKILL.md:198
- 3 network referencesin 2 files: pie-testing/SKILL.md:128 vibeue/SKILL.md:6
- No hidden or obfuscated text
- No instruction overrides
- 1 executable scriptin 1 file: asset-management/scripts/mesh_material_slots.py:1
- 2 references to secretsin 2 files: uv-mapping/SKILL.md:351 vibeue/SKILL.md:278
- No requests to vote in Hot
Show all 7 signals by file
Content/Skills/asset-management/scripts/mesh_material_slots.py
- Executable scriptline 1
Executable file
Content/Skills/pie-testing/SKILL.md
Content/Skills/uv-mapping/SKILL.md
- Access to secretsline 351
[Credential-related source omitted]
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Signal confidence: 7 facts
- Executable script in prose of a file that runsasset-management/scripts/mesh_material_slots.py:1Low confidence
- Network access in prose of the SKILL.mdpie-testing/SKILL.md:128Low confidence
- Network access in prose of the SKILL.mdpie-testing/SKILL.md:129Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueuv-mapping/SKILL.md:351Low confidence
- Network access in prose of the SKILL.mdvibeue/SKILL.md:6Low confidence
- Dangerous shell operation in code of the SKILL.mdvibeue/SKILL.md:198High confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuevibeue/SKILL.md:278Low confidence
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md Content/Skills/animation-blueprint/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md Content/Skills/animation-blueprint/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md Content/Skills/animation-blueprint/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md Content/Skills/animation-blueprint/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md Content/Skills/animation-blueprint/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md Content/Skills/animation-blueprint/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.