Overview
What It Does
Vision Sft packages a focused media & files workflow for an AI agent. Fine-tune vision-language models (VLMs) with supervised learning on image+text data. Use when adapting a VLM to a visual domain or task, configuring frozen-vision-tower LoRA, or debugging a VLM fine-tune that trains without learning. It is best suited to users who can review the resulting actions and provide only the accounts, files, or command access needed for the task. It is not a substitute for human approval on destructive, financial, security-sensitive, or public-facing actions.
Task ideas
Popular Use Cases
- Create or edit a common file format
- Extract information from uploaded files
- Convert content into a polished deliverable
- Automate repetitive media operations
Installation
Install this Agent Skill
Claude Code
npx skills add https://github.com/wshobson/agents --skill vision-sftCommands derived from the public GitHub SKILL.md record. Checked 2026-09-02. Review the source before running them.
Before you start
Requirements
| Claude Code | Required / review |
| Codex | Required / review |
| Public SKILL.md source | Required / review |
| Review instructions and requested permissions before installation | Required / review |
| Paid service | Check source |
| Supported system | Check source |
Popularity context
Why It’s Popular
Vision Sft is a verified Agent Skill from wshobson with a public SKILL.md, compatible with Claude Code, Codex.
Alternatives
