Agent Vision Toolkit Agent Skill

by Anionex• 1.3k•• Scanned•Claim this listing•Request removal
Design & Mediaagentagent skillsclaude codecodexcomputer use

为纯文本模型"看图“设计更好的视觉工具箱和技能，支持多图理解，图片问答，前端UI还原、GUI 自动化等，并可选无缝接入多个主流agent，直接识别粘贴图片｜ A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode

Agent Vision Toolkit is an open-source agent skill by Anionex, written mainly in Python, with 1,254 GitHub stars and the MIT license. Its code was last updated Oct 13, 2026.

aboutSKILL.md / READMEsecurityreviews
–
No reviews yet
Write a review

Sign in with GitHub to rate this listing.

    Agent Vision Toolkit alternatives

    View more →

    Similar agent skills in Design & Media, ranked by GitHub stars. Compare licence, recent activity and scan status before you choose.

    NameStarsLicenceLast updatedScan
    Agent Vision Toolkit (this page)
    Anionex
    		1.3kMITOct 13, 2026Scanned, no flagged issues
    Open Design
    nexu-io
    		105kApache-2.0Nov 1, 2026Scanned, no flagged issues
    Impeccable
    pbakaus
    		99kApache-2.0Nov 1, 2026Scanned, no flagged issues
    Diagram Design
    cathrynlavery
    		64kMITNov 1, 2026Scanned, no flagged issues
    Huashu Design
    alchaincyf
    		28kMITOct 30, 2026Scanned, no flagged issues
    Brag
    latent-spaces
    		20kMITOct 23, 2026Scanned, no flagged issues