domains / families / media / vss-ask-video

vss-ask-video

separate

Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or metadata-answerable questions.

When to use

• The user asks **what happens in the video**, what **objects / people / actions** appear, **colors**, **timing**, **safety**, or other **visual facts** that require watching the clip.
• The user asks for **details** that **cannot be answered** from existing messages, summaries, Elasticsearch/MCP results, or filenames alone—you need **model inference on the video**.
• Follow-up questions about **content details** after a coarse summary or after report generation.

When not to use

• questions answerable from existing messages
• questions answerable from summaries
• questions answerable from Elasticsearch or MCP results
• questions answerable from filenames alone
• questions answerable from prior tool output

Skill page

Source