Image to Three.js Model
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
Navigate, inspect, and author Animation Blueprints — state machines, states, transitions, and transition rules (AnimGraphService).
$ npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kevinpbuckley/VibeUE animation-blueprint --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Content/Skills/animation-blueprint .claude/skills/animation-blueprint && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "animation-blueprint" agent skill from https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprint into .claude/skills/animation-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "animation-blueprint", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprintType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kevinpbuckley/VibeUE animation-blueprint --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git skills-src && mkdir -p .agents/skills && cp -r skills-src/Content/Skills/animation-blueprint .agents/skills/animation-blueprint && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "animation-blueprint" agent skill from https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprint into .agents/skills/animation-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "animation-blueprint", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kevinpbuckley/VibeUE animation-blueprint --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/Content/Skills/animation-blueprint .cursor/skills/animation-blueprint && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "animation-blueprint" agent skill from https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprint into .cursor/skills/animation-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "animation-blueprint", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kevinpbuckley/VibeUE.git --path Content/Skills/animation-blueprint--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kevinpbuckley/VibeUE animation-blueprint --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/Content/Skills/animation-blueprint .gemini/skills/animation-blueprint && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "animation-blueprint" agent skill from https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprint into .gemini/skills/animation-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "animation-blueprint", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kevinpbuckley/VibeUE animation-blueprintInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git skills-src && mkdir -p .github/skills && cp -r skills-src/Content/Skills/animation-blueprint .github/skills/animation-blueprint && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "animation-blueprint" agent skill from https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprint into .github/skills/animation-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "animation-blueprint", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kevinpbuckley/VibeUE animation-blueprint --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kevinpbuckley/VibeUE.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/Content/Skills/animation-blueprint .opencode/skills/animation-blueprint && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "animation-blueprint" agent skill from https://github.com/kevinpbuckley/VibeUE/tree/master/Content/Skills/animation-blueprint into .opencode/skills/animation-blueprint/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "animation-blueprint", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
animation-blueprintNavigate, inspect, and author Animation Blueprints — state machines, states, transitions, and transition rules (AnimGraphService).
Animation Blueprint is an agent skill from kevinpbuckley/VibeUE. 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.
Its SKILL.md is about 5.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts.
It sits in Game Development. It works with Python. The repository describes itself as: Unreal Engine Vibe Coding tool. The licence is MIT.
Read from SKILL.md and the folder at commit dc051be. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/, which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Animation Blueprint loads about 5.4k tokens when it runs. Until then it costs about 86 tokens; SKILL.md has 1,182 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from kevinpbuckley/VibeUE at commit dc051be, republished under its MIT licence (© kevinpbuckley). 1,182 words, ~5,441 tokens.
.claude/skills/animation-blueprint/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.🧠 Brains complement: IF an
unreal-engine-skills-managertool (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.
Loading skills: skills load through the engine's
AgentSkillToolset(ListSkills/GetSkills) — there is novibeue-skills-managertool. Run VibeUE services withexecute_python_code(unreal.AnimGraphService.<method>()); reach engine toolsets withcall_tool.
An AnimBP is a Blueprint. The state-machine/AnimGraph authoring here is VibeUE
AnimGraphService(intact). For its variables and compile, note VibeUE'sBlueprintServicewas trimmed: variable creation and blueprint compile moved to the engine toolseteditor_toolset.toolsets.blueprint.BlueprintTools(add_variable,compile_blueprint), called viacall_tool.BlueprintServicestill haslist_variables,get_variable_info,set_variable_default_value,variable_exists, components, and overridable functions. Bool fields on info structs drop the C++bprefix in Python — useis_pure,is_output,already_overridden(NOTb_is_pure); calldiscover_python_classto confirm field names rather than guessing.
add_transition() only draws the arrow between two states. The transition's rule graph
starts empty, which evaluates to false, so the transition is inert — the state
machine will never move. You MUST set a rule on every transition:
import unreal
abp = "/Game/ABP_Character"
BT = "editor_toolset.toolsets.blueprint.BlueprintTools"
# 1) Add the bool/float variable the rule reads, then COMPILE so it resolves.
# Variable creation + compile are ENGINE BlueprintTools (call_tool), not VibeUE:
call_tool(BT, "add_variable", {"blueprint": {"refPath": abp}, "variable_name": "bIsDead", "variable_type": "bool"})
call_tool(BT, "compile_blueprint", {"blueprint": {"refPath": abp}})
# (Run describe_toolset(BT) for exact arg names.)
# 2) Draw the transition (VibeUE AnimGraphService)
unreal.AnimGraphService.add_transition(abp, "Locomotion", "Idle", "Dead", 0.2)
# 3) Give it a rule — THIS is what makes it fire
unreal.AnimGraphService.set_transition_rule_from_bool(abp, "Locomotion", "Idle", "Dead", "bIsDead")Rule options:
set_transition_rule_from_bool(abp, machine, src, dst, bool_var, invert=False)set_transition_rule_comparison(abp, machine, src, dst, float_var, op, value) — op ∈ greater/less/greater_equal/less_equal/equal/not_equalset_transition_rule_automatic(abp, machine, src, dst, trigger_time=-1.0) — fires when the source state's animation is (almost) finished; perfect for one-shots (attack→idle)clear_transition_rule(...) — non-destructively reset a ruleAfter authoring, always run validate_state_machine() (see below) and compile.
Use AnimGraphService to navigate directly to states and graphs:
import unreal
# Open an AnimBP's main AnimGraph
unreal.AnimGraphService.open_anim_graph("/Game/ABP_Character", "AnimGraph")
# Open a specific state inside a state machine
unreal.AnimGraphService.open_anim_state("/Game/ABP_Character", "Locomotion", "IdleLoop")
# Open a transition rule
unreal.AnimGraphService.open_transition("/Game/ABP_Character", "Locomotion", "Idle", "Walk")State machine names come from the node title, not the graph name. Use list_state_machines() to get the correct names:
machines = unreal.AnimGraphService.list_state_machines("/Game/ABP_Character")
for m in machines:
print(f"Machine: {m.machine_name}") # Use THIS name for open_anim_stateAll name lookups are case-insensitive, but prefer using exact names from introspection:
# Both work:
unreal.AnimGraphService.open_anim_state(path, "State Controller", "In Air Loop")
unreal.AnimGraphService.open_anim_state(path, "state controller", "in air loop")CRITICAL: AnimBlueprints require a skeleton reference. Always find the skeleton first.
import unreal
# Step 1: Find skeleton from reference blueprint
ref_bp_path = "/Game/Blueprints/SandboxCharacter_CMC_ABP"
if unreal.EditorAssetLibrary.does_asset_exist(ref_bp_path):
ref_bp = unreal.load_asset(ref_bp_path)
skeleton = ref_bp.get_editor_property('target_skeleton')
skeleton_path = skeleton.get_path_name()
print(f"Using skeleton: {skeleton_path}")
else:
# Or load directly if you know the path
skeleton_path = "/Game/Characters/UEFN_Mannequin/Meshes/SK_UEFN_Mannequin"
skeleton = unreal.load_asset(skeleton_path)
# Step 2: Delete existing if needed
asset_path = "/Game/Tests/ABP_TestCharacter"
if unreal.EditorAssetLibrary.does_asset_exist(asset_path):
unreal.EditorAssetLibrary.delete_asset(asset_path)
# Step 3: Create AnimBlueprint with skeleton
asset_tools = unreal.AssetToolsHelpers.get_asset_tools()
blueprint_factory = unreal.AnimBlueprintFactory()
blueprint_factory.set_editor_property("target_skeleton", skeleton)
blueprint_factory.set_editor_property("parent_class", unreal.AnimInstance)
animation_blueprint = asset_tools.create_asset(
"ABP_TestCharacter",
"/Game/Tests",
unreal.AnimBlueprint,
blueprint_factory
)
# Step 4: Save
if animation_blueprint:
unreal.EditorAssetLibrary.save_asset(asset_path, only_if_is_dirty=False)
print(f"Created: {asset_path}")Opening in Editor:
# Use open_editor_for_assets (plural) with list
editor_subsystem = unreal.get_editor_subsystem(unreal.AssetEditorSubsystem)
opened = editor_subsystem.open_editor_for_assets([animation_blueprint])⚠️ DO NOT use AssetEditorSubsystem.open_editor_for_asset() (singular) - it will cause AttributeError.
import unreal
abp_path = "/Game/Blueprints/SandboxCharacter_CMC_ABP"
# Get overview
parent = unreal.AnimGraphService.get_parent_class(abp_path)
skeleton = unreal.AnimGraphService.get_skeleton(abp_path)
print(f"Parent: {parent}, Skeleton: {skeleton}")
# List all graphs
graphs = unreal.AnimGraphService.list_graphs(abp_path)
for g in graphs:
print(f"Graph: {g.graph_name} ({g.graph_type}), Nodes: {g.node_count}")import unreal
abp_path = "/Game/ABP_Character"
# Find all state machines
machines = unreal.AnimGraphService.list_state_machines(abp_path)
for machine in machines:
print(f"\nState Machine: {machine.machine_name} ({machine.state_count} states)")
# List states in this machine
states = unreal.AnimGraphService.list_states_in_machine(abp_path, machine.machine_name)
for state in states:
end_marker = " [END]" if state.is_end_state else ""
print(f" - {state.state_name} ({state.state_type}){end_marker}")import unreal
abp_path = "/Game/Blueprints/SandboxCharacter_CMC_ABP"
# Open the AnimBP and navigate to a specific state
unreal.AnimGraphService.open_anim_state(
abp_path,
"State Controller", # State machine name
"In Air Loop" # State name
)import unreal
abp_path = "/Game/ABP_Character"
machine_name = "Locomotion"
# Get all transitions in a state machine
transitions = unreal.AnimGraphService.get_state_transitions(abp_path, machine_name)
for t in transitions:
auto = " [AUTO]" if t.is_automatic else ""
print(f"{t.source_state} -> {t.dest_state} (blend: {t.blend_duration}s){auto}")
# Get transitions for a specific state
idle_transitions = unreal.AnimGraphService.get_state_transitions(abp_path, machine_name, "Idle")build_state_machineBuild (or extend) a whole machine from one JSON spec in a single atomic, idempotent call. Re-running it never duplicates existing states/transitions. It sets animations, rules, the entry state, then compiles — and returns a JSON report.
import unreal, json
abp = "/Game/ABP_Character"
BT = "editor_toolset.toolsets.blueprint.BlueprintTools"
# Add the variables the rules read FIRST, then compile so the rules can resolve them.
# Variable creation + compile are ENGINE BlueprintTools (call_tool), not VibeUE:
call_tool(BT, "add_variable", {"blueprint": {"refPath": abp}, "variable_name": "Speed", "variable_type": "float"})
call_tool(BT, "add_variable", {"blueprint": {"refPath": abp}, "variable_name": "bAttack", "variable_type": "bool"})
call_tool(BT, "compile_blueprint", {"blueprint": {"refPath": abp}})
spec = {
"states": [
{"name": "Idle", "animation": "/Game/Anims/Idle", "loop": True, "pos": [0, 0]},
{"name": "Walk", "animation": "/Game/Anims/Walk", "loop": True, "pos": [350, 0]},
{"name": "Attack", "animation": "/Game/Anims/Attack", "loop": False, "pos": [350, 250]},
],
"transitions": [
{"from": "Idle", "to": "Walk", "rule": {"type": "comparison", "variable": "Speed", "op": "greater", "value": 10}, "blend": 0.15},
{"from": "Walk", "to": "Idle", "rule": {"type": "comparison", "variable": "Speed", "op": "less_equal", "value": 10}},
{"from": "Idle", "to": "Attack", "rule": {"type": "bool", "variable": "bAttack"}},
{"from": "Attack", "to": "Idle", "rule": {"type": "automatic"}}, # when the attack anim ends
],
"entry": "Idle",
}
report = json.loads(unreal.AnimGraphService.build_state_machine(abp, "Locomotion", json.dumps(spec)))
print(report) # {"success":true,"states_created":3,"transitions_created":4,"errors":[]}rule.type ∈ bool (variable, optional invert), comparison (variable,op,value),
automatic (optional trigger_time), always (always-true), or omit rule to leave it inert.
import unreal
abp = "/Game/ABP_Character"
# State machine + states
unreal.AnimGraphService.add_state_machine(abp, "Locomotion", 0, 0)
unreal.AnimGraphService.add_state(abp, "Locomotion", "Idle", 0, 0)
unreal.AnimGraphService.add_state(abp, "Locomotion", "Walk", 350, 0)
# One call: create+assign the sequence player inside the state AND wire it to Output Pose
unreal.AnimGraphService.set_state_animation(abp, "Locomotion", "Idle", "/Game/Anims/Idle", True)
unreal.AnimGraphService.set_state_animation(abp, "Locomotion", "Walk", "/Game/Anims/Walk", True)
# Default/entry state
unreal.AnimGraphService.set_entry_state(abp, "Locomotion", "Idle")
# Transitions + rules (rules are mandatory — see top gotcha)
unreal.AnimGraphService.add_transition(abp, "Locomotion", "Idle", "Walk", 0.15)
unreal.AnimGraphService.set_transition_rule_comparison(abp, "Locomotion", "Idle", "Walk", "Speed", "greater", 10.0)
unreal.AnimGraphService.set_transition_priority(abp, "Locomotion", "Idle", "Walk", 1)
# Compile via engine BlueprintTools:
call_tool("editor_toolset.toolsets.blueprint.BlueprintTools", "compile_blueprint", {"blueprint": {"refPath": abp}})validate_state_machineresult = unreal.AnimGraphService.validate_state_machine(abp, "Locomotion")
print(f"valid={result.is_valid} states={result.state_count} transitions={result.transition_count}")
for e in result.errors: print("ERROR:", e) # inert transitions, no entry state
for w in result.warnings: print("WARN :", w) # unreachable states, states with no animationTreat any errors as a build failure. The most common error is an inert transition
(a transition with no rule) — fix it with one of the set_transition_rule_* calls.
import unreal
abp_path = "/Game/ABP_Character"
sequences = unreal.AnimGraphService.get_used_anim_sequences(abp_path)
for seq in sequences:
print(f"{seq.sequence_name}")
print(f" Path: {seq.sequence_path}")
print(f" Used in: {seq.used_in_graph}")import unreal
abp_path = "/Game/ABP_Character"
# If you have a node GUID from get_nodes_in_graph
node_id = "ABC123-DEF456-..."
unreal.AnimGraphService.focus_node(abp_path, node_id)Python Naming Convention: C++ types like
FAnimStateMachineInfoare exposed asAnimStateMachineInfoin Python (noFprefix).
| Property | Type | Description |
|---|---|---|
machine_name | string | Display name of the state machine |
node_id | string | Node GUID |
state_count | int | Number of states |
parent_graph_name | string | Graph containing this machine |
| Property | Type | Description |
|---|---|---|
state_name | string | Display name of the state |
node_id | string | Node GUID |
state_type | string | "State", "Conduit", "Entry" |
is_end_state | bool | True if no outgoing transitions |
pos_x | float | X position in graph |
pos_y | float | Y position in graph |
| Property | Type | Description |
|---|---|---|
transition_name | string | Display name |
node_id | string | Node GUID |
source_state | string | Source state name |
dest_state | string | Destination state name |
priority | int | Priority (lower = higher) |
blend_duration | float | Crossfade time in seconds |
is_automatic | bool | Auto-transition based on sequence |
rule_type | string | None (inert), Bool, Comparison, Automatic, Custom |
rule_variable | string | Bound variable name (for Bool/Comparison rules) |
rule_summary | string | Human-readable rule, e.g. Speed > 150, bIsDead == true |
has_rule | bool | False = inert (never fires). True = transition can fire |
Returned by validate_state_machine().
| Property | Type | Description |
|---|---|---|
is_valid | bool | True when there are no blocking errors |
state_count | int | Number of states |
transition_count | int | Number of transitions |
errors | [string] | Blocking problems (inert transitions, no entry state) |
warnings | [string] | Non-blocking issues (unreachable states, states with no animation) |
Not every AnimBP is a state machine. A spinning rotor, a windmill sail, a turret yaw, a rudder that follows a variable — all are a pose piped through Modify Bone nodes, which is a different graph shape and has its own traps.
The chain is always: a pose source → Local To Component → one Modify Bone per bone →
Component To Local → Output. Skeletal controls only operate in component space, and
connect_anim_nodes does not insert the space conversions for you.
import unreal
AG, BS = unreal.AnimGraphService, unreal.BlueprintService
PATH, G = "/Game/ABP_Windmill", "AnimGraph"
REF = "SPAWN AnimGraphNode_LocalRefPose|Local Space Ref Pose" # no sequence needed
L2C = "SPAWN AnimGraphNode_LocalToComponentSpace|Local To Component"
C2L = "SPAWN AnimGraphNode_ComponentToLocalSpace|Component To Local"
ref = BS.create_node_by_key(PATH, G, REF, -900, -80)
l2c = BS.create_node_by_key(PATH, G, L2C, -640, -80)
AG.connect_anim_nodes(PATH, G, ref, "Pose", l2c, "LocalPose")
mb = AG.add_modify_bone_node(PATH, G, "sails", -340, -80)
AG.connect_anim_nodes(PATH, G, l2c, "ComponentPose", mb, "ComponentPose")
getter = BS.create_node_by_key(PATH, G, "SPAWN K2Node_VariableGet|Get SailRotation", -400, 200)
BS.connect_nodes(PATH, G, getter, "SailRotation", mb, "Rotation")
c2l = BS.create_node_by_key(PATH, G, C2L, 0, -80)
AG.connect_anim_nodes(PATH, G, mb, "Pose", c2l, "ComponentPose")
AG.connect_to_output_pose(PATH, G, c2l, "Pose")Pin names to remember: LocalPose in / ComponentPose out on Local To Component; ComponentPose
in / Pose out on Modify Bone and Component To Local.
connect_anim_nodes
(and connect_to_output_pose) to an already-wired single-link input now breaks the existing link
and wires the new source in its place — no need to disconnect_anim_node(node, "Pose") first — and
returns False (logging a Warning with the schema's reason) when the schema refuses. Previously it
stacked an illegal second link that compiled the AnimBP to BS_ERROR with an empty error list.add_modify_bone_node creates the node with rotation_mode, translation_mode and scale_mode all
set to Ignore. You can connect the Rotation pin, compile clean, and see absolutely nothing move —
there is no warning. Set the mode on the node's inner node struct after creating it:
for i in range(0, 12):
o = unreal.find_object(None, f"{PATH}.{name}:{G}.AnimGraphNode_ModifyBone_{i}")
if not o:
continue
n = o.get_editor_property("node")
n.set_editor_property("rotation_mode", unreal.BoneModificationMode.BMM_ADDITIVE)
n.set_editor_property("rotation_space", unreal.BoneControlSpace.BCS_COMPONENT_SPACE)
n.set_editor_property("translation_mode", unreal.BoneModificationMode.BMM_IGNORE)
n.set_editor_property("scale_mode", unreal.BoneModificationMode.BMM_IGNORE)
o.set_editor_property("node", n) # write the struct back, or the change is lostBMM_ADDITIVE and BMM_REPLACE behave identically when the bone is at identity in the ref pose.
create_node_by_key needs the spawner key, which embeds the node's display name, and the two
kinds of variable are spelled differently:
| Variable lives on | Display name | Spawner key |
|---|---|---|
The AnimBP itself (add_member_variable) | Get SailRotation | SPAWN K2Node_VariableGet|Get SailRotation |
A C++ UAnimInstance subclass | Get Sail Rotation (spaced) | SPAWN K2Node_VariableGet|Get Sail Rotation |
Never hard-code either — discover_nodes(PATH, "SailRotation", "", 20) and match on display_name,
which works for both.
Put the accumulator in the AnimBP's EventGraph on Event Blueprint Update Animation (its
DeltaTimeX pin), write a float, and convert it to the Rotator the Modify Bone reads:
DeltaTimeX ─┐
├─ float * float ─ float * float ─┐ (RPM → deg/sec is × 6)
SpinRPM ────┘ 6.0 ─────────┤
├─ float + float ─→ SET SailAngle
SailAngle (get) ──────────────────────────────┘
SailAngle (get) ─→ MakeRotator(Roll=) ─→ SET SailRotationFloat maths nodes are FUNC KismetMathLibrary::Multiply_DoubleDouble and ::Add_DoubleDouble
(display names float * float / float + float) — Blueprint "float" is a double in UE5.
MakeRotator is FUNC KismetMathLibrary::MakeRotator with pins Roll, Pitch, Yaw.
Verify it is actually running rather than trusting the compile: in PIE read the variable off the live
instance, twice, in separate execute_python_code calls (see the pie-testing skill — Python
blocks the game thread, so a sampling loop inside one call returns the same value every time).
comp = actor.get_components_by_class(unreal.SkeletalMeshComponent)[0]
ai = comp.get_anim_instance()
print(ai.get_editor_property("SailAngle"), comp.get_socket_rotation("sails").roll)import unreal
if unreal.AnimGraphService.is_anim_blueprint("/Game/SomeAsset"):
# It's an AnimBP, safe to use AnimGraphService
machines = unreal.AnimGraphService.list_state_machines("/Game/SomeAsset")import unreal
abp_path = "/Game/ABP_Character"
machines = unreal.AnimGraphService.list_state_machines(abp_path)
for machine in machines:
states = unreal.AnimGraphService.list_states_in_machine(abp_path, machine.machine_name)
for state in states:
print(f"{machine.machine_name}/{state.state_name}")execute_python_code)scripts/build_state_machine.txt — add a state machine with two states, set state animations, add a transition, compile.connect_anim_nodes replaces an existing pose link on the target input rather than erroring; it returns False if the schema refuses the connection, so check the return instead of hunting for a BS_ERROR with an empty error list.© kevinpbuckley, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 1 other file (scripts) in Content/Skills/animation-blueprint of kevinpbuckley/VibeUE.
Open the folder on GitHubat commit dc051be
Animation Blueprint next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Animation Blueprint this skillkevinpbuckley/VibeUE | 730 | — | ~5.4k | Automated safety check: Pass | MIT | |
| Image to Three.js Modelimg2threejs/img2threejs | 18k | 1 repos | ~8.2k | Automated safety check: Pass | Apache-2.0 | |
| 2D Map and Scene Generator0x0funky/agent-sprite-forge | 4.4k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Bambu Studio AIheyixuan2/bambu-studio-ai | 223 | — | ~4.3k | Automated safety check: Pass | MIT | |
| Spine AnimationGenielabsOpenSource/spine-animation-ai | 521 | — | ~17k | Automated safety check: Pass | CC-BY-NC-4.0 | |
| Unreal BridgeTornLux/UnrealBridge | 306 | — | ~8.4k | Automated safety check: Notes | MIT |
img2threejs/img2threejs
Rebuilds the object in a reference image as a procedural, animation-ready Three.js model written entirely in code, using staged sculpting with quality checks.
0x0funky/agent-sprite-forge
Plans and builds 2D game maps and scenes, from tilemaps and parallax backgrounds to HD-2D plates, with collision checks, a playable HTML preview and Tiled, Godot or LDtk export.
heyixuan2/bambu-studio-ai
End-to-end 3D printing for Bambu Lab printers. An agent skill from heyixuan2/bambu-studio-ai.
GenielabsOpenSource/spine-animation-ai
Create Spine 2D skeletal animations from pre-existing character assets (separated body-part PNGs, atlas spritesheet, or a full character image).
TornLux/UnrealBridge
Execute Python scripts inside a running Unreal Engine 5.3+ editor via TCP bridge.
0x0funky/agent-sprite-forge
Produces game-ready 2D characters, creatures, props, icons and effects as master stills, sheets or clips, and exports frames for common game engines.
kevinpbuckley/VibeUE
Previews, validates and bakes bone-rotation edits on Unreal Engine AnimSequences, enforcing a coordinate space and a constraint-checked preview-validate-bake loop.
kevinpbuckley/VibeUE
Creates and edits Unreal Engine Animation Montages through AnimMontageService: sections, slots, segments, branching points, notifies and blend settings.
kevinpbuckley/VibeUE
Creates and edits AnimSequence keyframes and bone tracks in Unreal Engine through AnimSequenceService, following an inspect, preview, validate and bake workflow with correct bone-space handling.
kevinpbuckley/VibeUE
Imports files into Unreal Engine, exports textures, reads the Content Browser selection and checks open assets via VibeUE, plus mesh reimport material fixes.
kevinpbuckley/VibeUE
Changes Unreal Engine console variables, scalability levels and raw INI values through VibeUE's Python API, now that registered settings moved to the engine's own toolset.
kevinpbuckley/VibeUE
Creates and wires Unreal Engine Enhanced Input assets through VibeUE's InputService: Input Actions, Mapping Contexts, key bindings, triggers and modifiers.
Works with
Categories
Navigate, inspect, and author Animation Blueprints — state machines, states, transitions, and transition rules (AnimGraphService). Animation Blueprint is an agent skill from kevinpbuckley/VibeUE. Navigate, inspect, and author Animation Blueprints — state machines, states, transitions, and transition rules (AnimGraphService).
Animation Blueprint fits situations like: the user asks to create; edit an Animation Blueprint/AnimBP; add a state machine; wire transitions between states.
Run `npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a claude-code`. Or copy the skill folder (Content/Skills/animation-blueprint in kevinpbuckley/VibeUE) into .claude/skills/animation-blueprint in your project. Claude Code loads it when a task matches its description.
Run `npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a codex`. Or copy the skill folder (Content/Skills/animation-blueprint in kevinpbuckley/VibeUE) into .agents/skills/animation-blueprint in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kevinpbuckley/VibeUE --skill animation-blueprint -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/animation-blueprint, .gemini/skills/animation-blueprint, .github/skills/animation-blueprint and .opencode/skills/animation-blueprint in your project.
SKILL.md names no scripts, command-line tools or credentials: Animation Blueprint is instructions for the agent only. Our summary lists: Python 3.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Animation Blueprint is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 5.4k tokens (SKILL.md is roughly 22k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Animation Blueprint: Image to Three.js Model (img2threejs/img2threejs, 18k stars), 2D Map and Scene Generator (0x0funky/agent-sprite-forge, 4.4k stars), Bambu Studio AI (heyixuan2/bambu-studio-ai, 223 stars) and Spine Animation (GenielabsOpenSource/spine-animation-ai, 521 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
kevinpbuckley (a GitHub user) maintains it in kevinpbuckley/VibeUE, which has 730 GitHub stars. The repository holds 39 skills in this directory. The repository was last updated on October 7, 2026.
Source: kevinpbuckley/VibeUE on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.