huggingface-vision-trainer

huggingface-vision-trainer is a skill for Claude Code from huggingface/skills. It costs 194 tokens per session (7,600 once invoked), scanned A, original, Apache-2.0.

Instructions for training and fine-tuning computer-vision models, which help software detect, classify or segment objects in images. Training can run on Hugging Face Jobs cloud GPUs, and results are saved to the Hugging Face Hub.

In plain words
What is it for?
Use it to train object detectors, image classifiers, or image-segmentation models on custom datasets, including models based on D-FINE, RT-DETR, DETR, YOLOS, timm, SAM and SAM2.
Why use it?
It provides a defined process for preparing supported datasets and running vision training without setting up a local graphics processor.

Skill for Claude Code ✓ vendor

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool; positional $N argument.

Part of the huggingface-skills plugin — 26 skills, 1 MCP server shipped together

Good fit Use it to train object detectors, image classifiers, or image-segmentation models on custom datasets, including models based on D-FINE, RT-DETR, DETR, YOLOS, timm, SAM and SAM2.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/huggingface/skills/huggingface-vision-trainer
About the project

Hugging Face Skills is a collection of packaged instructions, scripts, and resources that teach AI agents how to perform tasks in the Hugging Face ecosystem, such as managing models and datasets, training models, and running evaluations. It is for coding agents that need to use Hugging Face Hub and machine-learning workflows. The catalogue entries are the project's own skills and integrations for agent clients.

huggingface/skills · 11,024 stars · on GitHub · huggingface.co

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add huggingface/skills --skill huggingface-vision-trainer
Clone the repo
git clone --depth 1 https://github.com/huggingface/skills

Made for: Claude Code.

Or install huggingface-skills, the plugin that ships this one along with the rest of its 26 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for huggingface-vision-trainer

README.md
[![agentmods](https://agentmods.dev/badge/skills/huggingface/skills/huggingface-vision-trainer/github.svg)](https://agentmods.dev/skills/huggingface/skills/huggingface-vision-trainer)
Your own site
<a href="https://agentmods.dev/skills/huggingface/skills/huggingface-vision-trainer"><img src="https://agentmods.dev/badge/skills/huggingface/skills/huggingface-vision-trainer/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for huggingface-vision-trainer

Your own site · 80×15
<a href="https://agentmods.dev/skills/huggingface/skills/huggingface-vision-trainer"><img src="https://agentmods.dev/badge/skills/huggingface/skills/huggingface-vision-trainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 194 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,600 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 23 Mar 2026
  • Snyk warn 23 Mar 2026
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00194 $0.07600
Opus 5 $0.00097 $0.03800
Sonnet 5 $0.00039 $0.01520
Haiku 4.5 $0.00019 $0.00760

Measured 9d ago against content hash c7aba4de75fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

huggingface-vision-trainer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/dataset_inspector.py, scripts/estimate_cost.py, scripts/image_classification_training.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

3 near-identical copies found in the catalogue:

skills/huggingface-vision-trainer/SKILL.md · 594 lines

How it starts

The opening of the file, as written. The whole thing — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Vision Model Training on Hugging Face Jobs

Train object detection, image classification, and SAM/SAM2 segmentation models on managed cloud GPUs. No local GPU setup required—results are automatically saved to the Hugging Face Hub.

When to Use This Skill

Use this skill when users want to:

  • Fine-tune object detection models (D-FINE, RT-DETR v2, DETR, YOLOS) on cloud GPUs or local
  • Fine-tune image classification models (timm: MobileNetV3, MobileViT, ResNet, ViT/DINOv3, or any Transformers classifier) on cloud GPUs or local
  • Fine-tune SAM or SAM2 models for segmentation / image matting using bbox or point prompts
  • Train bounding-box detectors on custom datasets
  • Train image classifiers on custom datasets
  • Train segmentation models on custom mask datasets with prompts
  • Run vision training jobs on Hugging Face Jobs infrastructure
  • Ensure trained vision models are permanently saved to the Hub
  • hugging-face-jobs — General HF Jobs infrastructure: token authentication, hardware flavors, timeout management, cost estimation, secrets, environment variables, scheduled jobs, and result persistence. Refer to the Jobs skill for any non-training-specific Jobs questions (e.g., "how do secrets work?", "what hardware is available?", "how do I pass tokens?").
  • hugging-face-model-trainer — TRL-based language model training (SFT, DPO, GRPO). Use that skill for text/language model fine-tuning.

Local Script Execution

Helper scripts use PEP 723 inline dependencies. Run them with uv run:

uv run scripts/dataset_inspector.py --dataset username/dataset-name --split train
uv run scripts/estimate_cost.py --help

Prerequisites Checklist

Before starting any training job, verify:

Account & Authentication

  • Hugging Face Account with Pro, Team, or Enterprise plan (Jobs require paid plan)
  • Authenticated login: Check with hf_whoami() (tool) or hf auth whoami (terminal)
  • Token has write permissions
  • MUST pass token in job secrets — see directive #3 below for syntax (MCP tool vs Python API)

Read the full file on GitHub · 594 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 9d ago First seen · 594 lines · 194 tokens per session scan A c7aba4de75fa

Subscribe to this mod's changes

huggingface-vision-trainer is a skill published in the GitHub repository huggingface/skills (11,024 stars, last pushed 5d ago), licensed Apache-2.0. It adds 194 tokens to every session and 7,600 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

agent-platform-rag-engine-management

Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…

google/skills · 85 tokens

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and generates guidance to design and deploy a governed, secure agentic-analytics solution for data that's distributed across Google Cloud, other cloud providers, or on-premises. Data that's outside Google Cloud (such as data from Databricks, Snowflake, Salesforce, SAP, or Oracle systems) is…

google/skills · 138 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens