Agent Vision Toolkit

Anionex/agent-vision-toolkit

Equip text-only agents with image questions, OCR, target localization, cropping, SVG tracing, and screenshot comparison tools.

Conteúdo atualizado:

Ver no GitHub
npx skills add Anionex/agent-vision-toolkit --skill vision-skills
1.260Estrelas50ForksÚltimo push do repositório

Sobre este Skill

Equip text-only agents with image questions, OCR, target localization, cropping, SVG tracing, and screenshot comparison tools.

Por que escolhemos

Curated from the upstream task instructions. Use the original repository and its linked runtime files for installation, dependencies, and licensing.

Antes de usar

  • Requires Python 3.11+ and a configured vision API for model-based tools; optional tools need Pillow, NumPy, or a browser as documented.

Agentes compatíveis

Claude CodeCodex CLICursorGitHub CopilotDeepSeek HarnessGemini CLIGrok BuildHermes AgentOpenCodePiKiroRovo DevQoderMistral VibeGoogle Antigravity

Fontes e referências

As fontes originais estão nos links abaixo. As sugestões práticas são recomendações editoriais do SkillHey.