home/categories/media/bytedance-agentkit-samples-skills-byted-las-vlm-video-skill-md
mediacontent-media

byted-las-vlm-video

Video content understanding operator (las_vlm_video) via Doubao models. Use this skill when user needs to: - Analyze/describe video content with natural language prompts - Ask questions about what happens in a video (objects, actions, scenes) - Summarize video, extract key events, or generate captions Supports public/intranet-accessible video URLs and returns model responses + compression metadata. Requires LAS_API_KEY for authentication.

bytedance
maintainer
bytedance
আপডেট হয়েছে 3/24/2026
স্টার
301
ফর্ক
51
quick start

Installation and usage

Video content understanding operator (las_vlm_video) via Doubao models. Use this skill when user needs to: - Analyze/describe video content with natural language prompts - Ask questions about what happens in a video (objects, actions, scenes) - Summarize video, extract key events, or generate captions Supports public/intranet-accessible video URLs and returns model responses + compression metadata. Requires LAS_API_KEY for authentication.

ইনস্টলেশন
$ install --globalskills.sh
ব্যবহার

ইনস্টল করার পর, টার্মিনালে নিচের কমান্ড চালিয়ে আপনি এই স্কিল ব্যবহার করতে পারবেন:

skills use byted-las-vlm-video