FreePublished on GitHub

deep-motion-editing

Guides DeepMotionEditing BVH animation, skeleton-aware motion retargeting, motion style transfer, and Blender visualization workflows for research use.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill

Works withBlender

See how to install

Files included (34)

SKILL.md3.3 KB
references/architecture-overview.md1.1 KB
references/repo-provenance.md1.8 KB
references/repo-routing-metadata.json357 B
references/troubleshooting.md2.2 KB
scripts/check_environment.py1.3 KB
sub-skills/animation-data/references/api-reference.md8.3 KB
sub-skills/animation-data/references/data-formats.md8.1 KB
sub-skills/animation-data/references/troubleshooting.md8.0 KB
sub-skills/animation-data/scripts/inspect_bvh.py15.9 KB
sub-skills/animation-data/scripts/validate_openpose_json.py7.5 KB
sub-skills/animation-data/SKILL.md7.2 KB
sub-skills/blender-visualization/references/conversion-and-skinning.md1.2 KB
sub-skills/blender-visualization/references/loading-and-rendering.md1.4 KB
sub-skills/blender-visualization/references/troubleshooting.md1.7 KB
sub-skills/blender-visualization/scripts/build_blender_command.py4.3 KB
sub-skills/blender-visualization/scripts/fbx_to_bvh.py2.1 KB
sub-skills/blender-visualization/SKILL.md2.3 KB
sub-skills/motion-retargeting/references/api-reference.md7.2 KB
sub-skills/motion-retargeting/references/data-preparation.md4.8 KB
sub-skills/motion-retargeting/references/troubleshooting.md6.4 KB
sub-skills/motion-retargeting/references/workflows.md5.4 KB
sub-skills/motion-retargeting/scripts/run_retargeting.py10.2 KB
sub-skills/motion-retargeting/scripts/run_training.py6.3 KB
sub-skills/motion-retargeting/scripts/validate_retargeting_data.py8.0 KB
sub-skills/motion-retargeting/SKILL.md5.6 KB
sub-skills/motion-style-transfer/references/configuration.md5.3 KB
sub-skills/motion-style-transfer/references/data-formats.md6.1 KB
sub-skills/motion-style-transfer/references/troubleshooting.md6.6 KB
sub-skills/motion-style-transfer/references/workflows.md9.3 KB
sub-skills/motion-style-transfer/scripts/prepare_style_dataset.py6.8 KB
sub-skills/motion-style-transfer/scripts/run_style_transfer.py7.9 KB
sub-skills/motion-style-transfer/scripts/run_training.py9.0 KB
sub-skills/motion-style-transfer/SKILL.md6.9 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Deep Motion Editing

Use this repo skill when a task names Deep Motion Editing, BVH motion editing, skeleton-aware retargeting, unpaired motion style transfer, OpenPose motion style, Mixamo BVHs, or Blender rendering/skinning. It is a script-oriented research checkout, not a conventional installable Python package. Read references/repo-provenance.md before assuming the skill matches a new checkout.

Start safely

This source snapshot has no setup.py, pyproject.toml, requirements file, or console entry point; do not invent pip install deep-motion-editing. For the selected Python workflows, install only the route dependencies in a disposable environment, for example:

python -m pip install "numpy<2" scipy pyyaml tqdm torch
# Add these only for training/logging/probe work:
python -m pip install tensorboardX tensorboard matplotlib scikit-learn

Use Python 3.7+ as documented by the project. CUDA is recommended for model inference/training; CPU is useful for format checks but is only a partial neural substitute. Use Blender 2.80-era or a tested newer Blender for bpy workflows; ordinary Python cannot import bpy. Keep datasets, checkpoints, OpenPose outputs, FBX assets, and generated results outside the skill tree. Do not download or overwrite them implicitly. Run the read-only environment probe scripts/check_environment.py before a new task. Read references/troubleshooting.md for legacy imports, paths, optional dependencies, and backend failures.

Route to the focused workflow

User intent	Read next
BVH parsing/writing, topology, JSON validation, kinematics, cleanup	`sub-skills/animation-data/SKILL.md`
Mixamo/custom data, intra/cross retargeting, evaluation, training	`sub-skills/motion-retargeting/SKILL.md`
3D/2D style transfer, normalization, Xia/BFA preparation, training	`sub-skills/motion-style-transfer/SKILL.md`
Blender BVH load/render, FBX skinning or conversion	`sub-skills/blender-visualization/SKILL.md`

The central cross-workflow contract is: validate BVH hierarchy and frame data first, preserve source inputs, write new outputs, then validate the result before neural comparison or rendering. Sibling routes link to each other when a task crosses that boundary.

Verification boundary

A parser/help check does not reproduce a paper result. Meaningful neural runs need the correct pretrained checkpoints, normalization files, dataset layout, model configuration, and a suitable backend. Blender routes additionally need a Blender executable and compatible FBX assets. This generated skill was built from a 2021 source snapshot and intentionally omits large binaries and external data; those limitations are recorded in the references and external verification artifacts, not hidden.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

More skills from this repository

3d-resnets-pytorch

Free

Routes 3D ResNets PyTorch video action-recognition workflows across training, inference, and data preparation.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

3ddfa

Free

Guide 3DDFA Python inference, geometry rendering, training/evaluation, and optional C++ ONNX workflows for 3D dense face alignment.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

3ddfa-v2

Free

Routes 3DDFA_V2 face-alignment setup, still-image demos, video tracking, and ONNX benchmarking workflows.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

ab3dmot

Free

Operate AB3DMOT 3D multi-object tracking workflows for KITTI and nuScenes data, tracking, evaluation, and visualization.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

accelerate

Free

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model inference/offload, checkpointing, tracking, and troubleshooting.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

acme

Free

Route Acme reinforcement-learning framework tasks across core loops, replay/data, JAX agents, and TensorFlow/Sonnet agents.

The English summary is being prepared. Showing the original description.

VectorSpaceLab/AREX-Skill339Updated Sep 3, 2026

See all skills by VectorSpaceLab

Report a problem with this skill

Install

Install with a command

npx skills add https://github.com/VectorSpaceLab/AREX-Skill --skill deep-motion-editing

Paste it into your terminal and run it (requires Node.js). You can choose which agents to install it for, such as Claude Code or Codex.

Ask your agent

Please install the following Agent Skill.
https://github.com/VectorSpaceLab/AREX-Skill/tree/main/skills/repositories/repo-skills/deep-motion-editing

First review SKILL.md and the bundled files and confirm there is nothing suspicious (such as sending data externally or reading credentials). Then place it in ~/.claude/skills/deep-motion-editing/ for Claude Code, or ~/.agents/skills/deep-motion-editing/ for Codex.

Send this text to Claude Code or Codex as is. It checks the contents before installing.

View source on GitHub

Repository: VectorSpaceLab/AREX-Skill
Stars: 339
Forks: 26
Category: Research & Learning
License: Apache-2.0
Original language: English
Last updated: Sep 3, 2026

A skill is a set of instructions and scripts for an agent. cccskills does not guarantee that skills are safe. Review the contents before you install.