byted-mediakit-media-understand

1## Environment
2 
3This agent exposes MediaKit through MCP/REST tools only. `mediakit-cli` is not available. Ignore any CLI fallback or installation instructions in this skill and its references; if a capability is unavailable, report the gap instead of running a terminal command.
4 
5# Media Understanding
6 
7Choose the smallest set of evidence that answers the user's question. Prefer available MCP tools for frame extraction and media understanding, identified by their exposed names, descriptions and parameter schemas rather than a service or package name. Use the MCP/REST tools exposed by this environment and follow the same modality routing, sampling, evidence and stopping rules. If a capability is unavailable, report the gap. Use image and audio inputs for understanding; video inputs to understanding models require an explicit user request for direct video understanding. This restriction does not prevent passing video to frame extraction, ASR, OCR or audio extraction tools.
8 
9Read [references/mcp.md](references/mcp.md) for MCP discovery, arguments and task handling. Read [references/sampling.md](references/sampling.md) when choosing video coverage or refining event timing.
10 
11## Tools
12 
13Use only the MediaKit tools exposed by this environment. Do not install or run `mediakit-cli`.
14 
15- `extract_frames`: sample video frames or contact sheets.
16- `media_understanding`: understand one image, audio, or video asset per call.
17- `asr_subtitles`: speech evidence and subtitle extraction.
18…