MMSkills: Towards Multimodal Skills for General Visual Agents
概览
Towards Multimodal Skills for General Visual Agents News | Paper | Website | Skill Library | Demos | Overview | Installation | Quick Start | Citation If you find this project helpful, please give us a star ⭐ for the latest updates. - 🏆 MMSkills ranked . - 🤗 The MMSkills dataset is now available on Hugging Face Datasets. - 🌐 The project website is live with demo comparisons and a searchable MMSkills Library indexing across Ubuntu, macOS, VAB-Minecraft, and Mario. - 🚀 The public release includes a compact multimodal desktop-skill subset, OSWorld-ready runtime adapters, task mappings, and model-agnostic skill modes. - 🔌 We are exploring integrations with OpenClaw, Codex, and Claude Code. Stay tuned. Four OSWorld demos compare the same task under no skills, text-only skill guidance, and multimodal MMSkills. To keep GUI text readable in the GitHub README, each case uses three separate 1080p MP4 players instead of a compressed side-by-side composite.
README
以下为原文 README 节选，完整内容请查看原文。
Towards Multimodal Skills for General Visual Agents
News | Paper | Website | Skill Library | Demos | Overview | Installation | Quick Start | Citation
If you find this project helpful, please give us a star ⭐ for the latest updates.
📣 Latest News
- 🏆 [May 2026] MMSkills ranked #1 on Hugging Face Daily Papers.
- 🤗 [May 2026] The MMSkills dataset is now available on Hugging Face Datasets.
- 🌐 [May 2026] The project website is live with demo comparisons and a searchable MMSkills Library indexing 515 skills across Ubuntu, macOS, VAB-Minecraft, and Mario.
- 🚀 [May 2026] The public release includes a compact multimodal desktop-skill subset, OSWorld-ready runtime adapters, task mappings, and model-agnostic skill modes.
- 🔌 [May 2026] We are exploring integrations with OpenClaw, Codex, and Claude Code. Stay tuned.
🎬 Demos
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add walterhu1015/mmskills