CA

catvton-train-reconstruction

Specialized pipeline for training and reviewing CatVTON models with support for local dataset annotations and mask generation.

Install

mkdir -p .claude/skills/catvton-train-reconstruction && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/14776" && unzip -o skill.zip -d .claude/skills/catvton-train-reconstruction && rm skill.zip

Installs to .claude/skills/catvton-train-reconstruction

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Use when implementing, reviewing, or extending CatVTON-style training in this repository. Focus on DressCode-based training, agnostic mask generation from local dataset annotations, and attention checkpoint export compatible with CatVTON inference layouts.
256 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Intermediate

Key capabilities

  • Generate agnostic masks for training
  • Validate training pair datasets
  • Export attention checkpoints
  • Review CatVTON model implementation
  • Manage CatVTON-style training in this repository
  • Validate dataset logic against DressCode files

How it works

This skill manages CatVTON-style training within a specific repository, focusing on generating agnostic masks and ensuring checkpoint compatibility.

Inputs & outputs

You give it
local DressCode dataset annotations
You get back
CatVTON-compatible attention checkpoints

When to use catvton-train-reconstruction

  • Generate agnostic masks for training
  • Validate training pair datasets
  • Export attention checkpoints
  • Review CatVTON model implementation

About this skill

CatVTON Train Reconstruction

Use this skill for work inside CatVTON_practice.

What this repo is for

This project is a practice implementation of CatVTON-style training centered on the local DressCode dataset under data/DressCode.

The important local constraint is that DressCode here does not already contain agnostic_masks, so training must either generate them on the fly or cache them before use.

Workflow

  1. Read references/repo-notes.md.
  2. Keep the implementation scoped to this repo before reaching back into the original CatVTON repo.
  3. Preserve CatVTON-compatible checkpoint layout:
    • <output>/<dataset_tag>/attention
  4. Prefer self-attention-only training unless the user explicitly asks for a different fine-tuning target.
  5. When changing dataset logic, validate against the actual files under data/DressCode.

Validation rules

  • Confirm train_pairs.txt and test pair files still parse.
  • Confirm masks are generated or loaded consistently.
  • Confirm the saved checkpoint contains attention weights that can be reloaded later.

References

  • references/repo-notes.md

When not to use it

  • When the task is outside the CatVTON_practice repository
  • When the dataset is not local DressCode
  • When not focused on CatVTON-style training

Limitations

  • Training is centered on the local DressCode dataset under data/DressCode
  • Implementation is scoped to this repo before reaching back into the original CatVTON repo
  • Training must either generate agnostic_masks on the fly or cache them before use

How it compares

This skill provides a structured workflow for CatVTON training with specific dataset and checkpoint constraints, unlike a generic training setup.

Compared to similar skills

catvton-train-reconstruction side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
catvton-train-reconstruction (this skill)0No flagsIntermediate
robotics-code-generator148moNo flagsAdvanced
modal57moReviewIntermediate
hugging-face-cli36moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

robotics-code-generator

HumaizaNaz

Generates clean, runnable ROS 2, Gazebo, Isaac Sim, and VLA code for humanoid robotics

1490

modal

davila7

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch processing jobs, scheduling compute-intensive tasks, or serving APIs that require GPU acceleration or dynamic scaling.

587

hugging-face-cli

patchy631

Execute Hugging Face Hub operations using the `hf` CLI. Use when the user needs to download models/datasets/spaces, upload files to Hub repositories, create repos, manage local cache, or run compute jobs on HF infrastructure. Covers authentication, file transfers, repository creation, cache operations, and cloud compute.

350

computer-use-agents

davila7

Build AI agents that interact with computers like humans do - viewing screens, moving cursors, clicking buttons, and typing text. Covers Anthropic's Computer Use, OpenAI's Operator/CUA, and open-source alternatives. Critical focus on sandboxing, security, and handling the unique challenges of vision-based control. Use when: computer use, desktop automation agent, screen control AI, vision-based agent, GUI automation.

1040

machine-learning-ops-ml-pipeline

sickn33

Design and implement a complete ML pipeline for: $ARGUMENTS

436

ray-train

davila7

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.

336

Search skills

Search the agent skills registry