Animation Montage logo

Animation Montage

Community
kevinpbuckley
animation-montage

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.

Overview

Publisherkevinpbuckley
RepositoryVibeUE
Skill nameanimation-montage
Stars
735
Forks
161
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

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

  • Works with any LLM

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

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

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

1

Install in TypingMind

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

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-montage
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git /tmp/VibeUE
mkdir -p .claude/skills
cp -r /tmp/VibeUE/Content/Skills/animation-montage .claude/skills/animation-montage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

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

The model loads Animation Montage on its own as soon as a request matches it.

Works with any AI model

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

  • Loaded only when it is needed

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

  • Switch models mid-chat

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

Skill instructions

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

🧠 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

⚠️ 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).

python
# List all montages in a path (use "" for no skeleton filter, NOT None)
montages = AnimMontageService.list_montages(search_path, skeleton_filter) -> Array[MontageInfo]

# Get detailed montage info
info = AnimMontageService.get_montage_info(montage_path) -> MontageInfo

# Find montages for a skeleton
montages = AnimMontageService.find_montages_for_skeleton(skeleton_path) -> Array[MontageInfo]

# Find montages using a specific animation
montages = AnimMontageService.find_montages_using_animation(anim_path) -> Array[MontageInfo]

Creation Methods

python
# Create montage from an animation sequence
path = AnimMontageService.create_montage_from_animation(anim_path, dest_path, name) -> str

# Create empty montage for a skeleton
path = AnimMontageService.create_empty_montage(skeleton_path, dest_path, name) -> str

# Duplicate existing montage
path = AnimMontageService.duplicate_montage(source_path, dest_path, new_name) -> str

Section Management (CRITICAL for gameplay!)

python
# List all sections
sections = AnimMontageService.list_sections(montage_path) -> Array[MontageSectionInfo]

# Add new section
AnimMontageService.add_section(montage_path, section_name, start_time) -> bool

# Remove section
AnimMontageService.remove_section(montage_path, section_name) -> bool

# Rename section
AnimMontageService.rename_section(montage_path, old_name, new_name) -> bool

# Move section to new time
AnimMontageService.set_section_start_time(montage_path, section_name, new_time) -> bool

# Get section at time
name = AnimMontageService.get_section_name_at_time(montage_path, time) -> str

Section Linking (Combo/Flow Control)

python
# Link sections: Section1 -> Section2
AnimMontageService.set_next_section(montage_path, from_section, to_section) -> bool

# Set section to loop
AnimMontageService.set_section_loop(montage_path, section_name, loop=True) -> bool

# Clear link (section ends montage)
AnimMontageService.clear_section_link(montage_path, section_name) -> bool

# Get all section links for flow visualization
links = AnimMontageService.get_all_section_links(montage_path) -> Array[SectionLink]

Animation Segments (Multiple Animations in One Montage)

python
# List segments in a slot track
segments = AnimMontageService.list_anim_segments(montage_path, track_index) -> Array[AnimSegmentInfo]

# Add animation at specific time
index = AnimMontageService.add_anim_segment(montage_path, track_index, anim_path, start_time, play_rate) -> int

# Remove segment
AnimMontageService.remove_anim_segment(montage_path, track_index, segment_index) -> bool

# Modify segment timing
AnimMontageService.set_segment_start_time(montage_path, track_index, segment_index, time) -> bool
AnimMontageService.set_segment_play_rate(montage_path, track_index, segment_index, rate) -> bool
AnimMontageService.set_segment_loop_count(montage_path, track_index, segment_index, count) -> bool

Slot Tracks

python
# List slot tracks
tracks = AnimMontageService.list_slot_tracks(montage_path) -> Array[SlotTrackInfo]

# Add new slot track
index = AnimMontageService.add_slot_track(montage_path, slot_name) -> int

# Change slot name
AnimMontageService.set_slot_name(montage_path, track_index, new_slot_name) -> bool

# Remove slot track
AnimMontageService.remove_slot_track(montage_path, track_index) -> bool

Blend Settings

python
# Set blend in (options: Linear, Cubic, HermiteCubic, Sinusoidal, etc.)
AnimMontageService.set_blend_in(montage_path, time, option) -> bool

# Set blend out
AnimMontageService.set_blend_out(montage_path, time, option) -> bool

# Set blend out trigger time (-1 = auto)
AnimMontageService.set_blend_out_trigger_time(montage_path, time) -> bool

# Get all blend settings
settings = AnimMontageService.get_blend_settings(montage_path) -> MontageBlendSettings

Branching Points (Frame-Accurate Gameplay Events)

python
# List all branching points
points = AnimMontageService.list_branching_points(montage_path) -> Array[BranchingPointInfo]

# Add branching point for combo input window
index = AnimMontageService.add_branching_point(montage_path, name, trigger_time) -> int

# Remove branching point
AnimMontageService.remove_branching_point(montage_path, index) -> bool

Root Motion

python
# Enable/disable root motion translation
AnimMontageService.set_enable_root_motion_translation(montage_path, enable) -> bool

# Enable/disable root motion rotation
AnimMontageService.set_enable_root_motion_rotation(montage_path, enable) -> bool

Editor Methods

python
# Open montage in Animation Editor
AnimMontageService.open_montage_editor(montage_path) -> bool

# Refresh editor UI: call this ONCE, AFTER all edits are done (see crash warning below)
AnimMontageService.refresh_montage_editor(montage_path) -> bool

# Jump to section in preview
AnimMontageService.jump_to_section(montage_path, section_name) -> bool

# Play preview
AnimMontageService.play_preview(montage_path, start_section) -> bool

⚠️ CRASH WARNING — never structurally edit a montage while its editor is open. Adding/removing sections, slot tracks, segments, notifies, or branching points reallocates the montage's internal arrays. If the montage editor (Persona) is open, its live preview holds pointers into those arrays and the next tick will dereference freed memory → the editor hard-crashes. Rule: do ALL structural edits FIRST, then refresh_montage_editor() / open_montage_editor() exactly once at the very end. Do NOT call refresh_montage_editor() between edits. (The service now also auto-closes the editor before each structural edit as a safety net, but you should still batch edits and open last so the editor isn't opening and closing repeatedly.)

IMPORTANT: Asset Path Format

All montage_path parameters require the FULL asset path (package_name), NOT the folder path.

python
# CORRECT: Full asset path
montage_path = "/Game/Montages/AM_Attack"

# WRONG: Folder path
montage_path = "/Game/Montages"  # This is a folder, not an asset!

IMPORTANT: Return Struct Field Names (read before printing results)

These methods return UStruct objects. Access fields with the exact snake_case names below — guessing (skeleton_display_name, segment end_time, name, path) raises AttributeError. Each struct field is read-only data already populated; just read it.

MontageInfo (from get_montage_info / list_montages / find_montages_for_skeleton): montage_path, montage_name, skeleton_path, duration, section_count, slot_track_count, notify_count, branching_point_count, blend_in_time, blend_out_time, blend_out_trigger_time, enable_root_motion_translation, enable_root_motion_rotation, slot_names (Array[str]). (No skeleton_display_name — use skeleton_path. No skeleton object — it's a path string.)

MontageSectionInfo (from list_sections): section_name, section_index, start_time, end_time, duration, next_section_name, loops, segment_count.

AnimSegmentInfo (from list_anim_segments / get_anim_segment_info): segment_index, anim_sequence_path, anim_name, start_time, duration, play_rate, anim_start_pos, anim_end_pos, loop_count, loops. (Segments have NO end_time — that field exists only on sections. Compute segment end as start_time + duration. Source-clip range is anim_start_pos → anim_end_pos.)

SlotTrackInfo (from list_slot_tracks): track_index, slot_name, segment_count, total_duration.

SectionLink (from get_all_section_links): from_section, to_section, is_loop.

BranchingPointInfo (from list_branching_points): index, notify_name, trigger_time, section_name.

Tip: when unsure, call discover_python_class('unreal.MontageInfo, unreal.AnimSegmentInfo, unreal.MontageSectionInfo') — the Editor Properties block lists every valid field name. Cheaper than a crash-and-retry loop.

Key Workflows

Create Multi-Animation Montage with Sections

python
import unreal

# 1. Create empty montage
path = unreal.AnimMontageService.create_empty_montage(
    "/Game/Characters/SK_Mannequin",
    "/Game/Montages",
    "AM_ComboAttack"
)

# 2. Add animation segments sequentially (track 0)
unreal.AnimMontageService.add_anim_segment(path, 0, "/Game/Animations/Attack1", 0.0)
unreal.AnimMontageService.add_anim_segment(path, 0, "/Game/Animations/Attack2", 1.0)  
unreal.AnimMontageService.add_anim_segment(path, 0, "/Game/Animations/Attack3", 2.0)

# 3. Add sections at animation boundaries
unreal.AnimMontageService.add_section(path, "Attack1", 0.0)
unreal.AnimMontageService.add_section(path, "Attack2", 1.0)
unreal.AnimMontageService.add_section(path, "Attack3", 2.0)

# 4. Link sections for combo flow
unreal.AnimMontageService.set_next_section(path, "Attack1", "Attack2")
unreal.AnimMontageService.set_next_section(path, "Attack2", "Attack3")
# Attack3 has no next section - ends the montage

# 5. Add branching points for input windows
unreal.AnimMontageService.add_branching_point(path, "Combo1Window", 0.7)
unreal.AnimMontageService.add_branching_point(path, "Combo2Window", 1.7)

# 6. Configure blend settings
unreal.AnimMontageService.set_blend_in(path, 0.15, "Cubic")
unreal.AnimMontageService.set_blend_out(path, 0.2, "Linear")

# 7. Save FIRST, while no editor is open
unreal.EditorAssetLibrary.save_asset(path)

# 8. THEN refresh/open the editor exactly once — never between the edits above
#    (refreshing mid-edit can crash the editor; see CRASH WARNING)
unreal.AnimMontageService.refresh_montage_editor(path)

Create Layered Upper Body Montage

python
import unreal

# 1. Create montage from animation
path = unreal.AnimMontageService.create_montage_from_animation(
    "/Game/Animations/Reload",
    "/Game/Montages",
    "AM_Reload_UpperBody"
)

# 2. Change slot to UpperBody for layered blending
unreal.AnimMontageService.set_slot_name(path, 0, "UpperBody")

# 3. Configure blend
unreal.AnimMontageService.set_blend_in(path, 0.1, "Linear")
unreal.AnimMontageService.set_blend_out(path, 0.15, "Linear")

# 4. Disable root motion for upper body action
unreal.AnimMontageService.set_enable_root_motion_translation(path, False)
unreal.AnimMontageService.set_enable_root_motion_rotation(path, False)

# 5. Save
unreal.EditorAssetLibrary.save_asset(path)

Set Up Looping Idle Section

python
import unreal

montage_path = "/Game/Montages/AM_Combat"

# Add sections
unreal.AnimMontageService.add_section(montage_path, "Idle", 0.0)
unreal.AnimMontageService.add_section(montage_path, "Attack", 2.0)

# Make Idle loop until gameplay interrupts
unreal.AnimMontageService.set_section_loop(montage_path, "Idle", True)

# Attack ends the montage (no next section)
unreal.AnimMontageService.clear_section_link(montage_path, "Attack")

COMMON_MISTAKES

Wrong: Using folder path instead of asset path

python
# WRONG
montages = AnimMontageService.list_sections("/Game/Montages")

# CORRECT
sections = AnimMontageService.list_sections("/Game/Montages/AM_Attack")

Wrong: Refreshing the editor between structural edits (can CRASH the editor)

python
# WRONG - opening/refreshing the editor mid-edit, then editing more, can hard-crash
# the editor (live preview holds dangling pointers into reallocated montage arrays)
AnimMontageService.add_section(path, "Attack", 0.5)
AnimMontageService.refresh_montage_editor(path)   # editor now open
AnimMontageService.add_anim_segment(path, 0, anim, 1.0)  # mutates arrays under live preview -> CRASH risk

# CORRECT - do ALL structural edits first, save, THEN refresh/open exactly once at the end
AnimMontageService.add_section(path, "Attack", 0.5)
AnimMontageService.add_anim_segment(path, 0, anim, 1.0)
unreal.EditorAssetLibrary.save_asset(path)
AnimMontageService.refresh_montage_editor(path)   # single refresh at the very end

Wrong: Adding sections beyond montage duration

python
# WRONG - Section time must be within montage length
# If montage is 3.0s, this fails:
AnimMontageService.add_section(path, "Late", 5.0)  # Beyond duration

# CORRECT - Add segments first to extend duration, then add sections
AnimMontageService.add_anim_segment(path, 0, anim_path, 3.0)  # Extends montage
AnimMontageService.add_section(path, "Late", 3.5)  # Now within range

Wrong: Forgetting to save

python
# WRONG - Changes lost on editor restart
AnimMontageService.add_section(path, "Attack", 0.5)

# CORRECT - Always save after changes
AnimMontageService.add_section(path, "Attack", 0.5)
unreal.EditorAssetLibrary.save_asset(path)

Sample scripts (run via execute_python_code)

  • scripts/create_montage.txt — create a montage from an animation and add named sections.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Animation Montage AI skill do?

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.

Why use Animation Montage on TypingMind?

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

How do I install Animation Montage in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-montage. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Animation Montage?

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

How many AI models can I use with Animation Montage?

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

Is the Animation Montage AI skill free?

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

What are AI skills?

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

How are AI skills different from plugins or MCP servers?

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

View all

Set up your own AI workspace now

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