deepseek-vision-skill — tool profile and history

Current measurement

Momentum uses available readings from the last 7 days: measured with at least two comparable readings, estimated otherwise.

Reading history

Classifications

Domains

• Agents, skills and MCP

Type

Other

Use cases

• Coding assistants

Neighbouring tools

These entries declare the same topics. No similarity is inferred: only the shared topics are stated.

• UI-TARS-desktopThe Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent InfShared topics : multimodal, vision
• PixelRAGThe end of web parsing. The beginning of scalable pixel-native search. link: https://pixelShared topics : multimodal, vision
• modlensThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coShared topics : multimodal, vision
• agent-vision-toolkit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 toShared topics : multimodal, vision
• claude-code-vision-skill为 Claude Code 赋能多模态视觉能力，适配 纯文本 LLM 底座，用于截图 / UI / 图表分析；搭配 browser-harness 可做前端布局自动化检查。Shared topics : multimodal, vision
• achatbotAn open source chat bot architecture for voice/vision (and multimodal) assistants, local(Shared topics : multimodal, vision