👁️
AI EngineeringTypeScript

Vision Toolkit

by Anionex

Vision Toolkit is an AI Engineering skill for Claude Code, published by Anionex in dsh-vision-toolkit.

805 stars35 forkson Anionex/dsh-vision-toolkitAdded 2026/08/22+6% in starsRepository updated 2026/08/21
agent-skillsagent-vision-toolkitcomputer-visiondeepseekdeepseek-harnessdshdsh-plugingui-automationocrpluginpythonscreenshot-testingtext-only-llmtypescriptui-restorationvision-language-modelvision-tools
Install in seconds
Install Vision Toolkit
Copy Vision Toolkit into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Anionex/dsh-vision-toolkit/tree/main/assets/skill ~/.claude/skills/skill

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Anionex/dsh-vision-toolkit.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
assets/skill/SKILL.md in Anionex/dsh-vision-toolkit
Installs to
~/.claude/skills/skill
Collection
The only skill cataloged from this repository
Category
AI Engineering2451 skills

What Vision Toolkit does

Vision Toolkit gives text-only agents tools to inspect images, locate objects, run OCR, compare screenshots, and extract regions. Use it when a task depends on visual evidence instead of text alone.

Vision Toolkit is cataloged under AI Engineering on DirSkills. Vision Toolkit comes from a repository tagged agent-skills, agent-vision-toolkit, computer-vision, deepseek and deepseek-harness.

Documentation

README

vision-skills

Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.

The visual execution schemas are mounted only for the current Agent after this Skill is loaded. A normal skill call activates them for the next model step. If this content arrived through a direct /vision-skills invocation and the visual tools are still absent, call vision_toolkit_activate once. Do not call that bootstrap when the visual tools are already present.

Pick the tool by the question you are answering:

This is the opening of the README. Read the full README on GitHub.

Commands Vision Toolkit provides

Slash commands named in this skill’s SKILL.md, listed in the order they first appear.

  • /vision-skills

Frequently asked about Vision Toolkit

  • How does Vision Toolkit compare to other AI Engineering skills?

    Vision Toolkit ranks #1587 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Vision Toolkit against them. Open each page to compare what they document and how they install.