agent-vision-toolkit

Provides visual capabilities such as image understanding, question answering, frontend UI reconstruction, and GUI automation for pure text models.

Agent SkillDevOpen source

View source →

Type: Agent Skill
Open source: Yes
GitHub Stars: ★ 1.0k
Source: skill-github
Repository: github.com/Anionex/agent-vision-toolkit

Overview

agent-vision-toolkit is a visual toolkit and skill set designed specifically for pure text models, supporting multi-image understanding, image question answering, frontend UI reconstruction, and GUI automation. It seamlessly integrates with multiple mainstream agents (such as Codex, Claude Code, Pi, etc.) to directly recognize pasted images. This toolkit enables text models to handle visual tasks, enhancing their performance in multimodal scenarios. Ideal for developers and teams looking to augment the visual capabilities of text models.

Capabilities

▪Multi-image understanding
▪Image question answering
▪Frontend UI reconstruction
▪GUI automation
▪Seamless integration with mainstream agents
▪Direct recognition of pasted images

Use cases

Enhancing text models' image understanding capabilitiesBuilding image-based question answering systemsAutomating frontend UI testingImproving GUI automation efficiency

Setup

Requires: API KeyNode 环境

Please refer to the installation instructions in the project README.

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to install agent-vision-toolkit?

Please refer to the installation instructions in the project README.

Which mainstream agents are supported?

Supports Codex, Claude Code, Pi, and others.

Is it open source?

Yes, under the MIT license.

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

sast-skills

Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.

Agent Skill

audit-skills

Lightweight code audit plugin focused on security boundary checks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP