Video2 operations

`shots`

Detect hard cuts (shot boundaries) in video via ffmpeg scene detection and extract midpoint stills per shot. Use when the unit of analysis is a shot — cataloging cuts, QC, or feeding shot-level frames to vision/OCR — not TV program structure or commercial breaks.

View on GitHub Install skill

Overview

Requires ffmpeg and ffprobe on PATH. Scripts are Python 3.11+, run via `uv run` (no separate install step).

Recipes

Copy-paste command sequences agents can run via uv run. Replace <skill_directory> with the absolute path of this skill (the folder that contains SKILL.md) — do not run scripts/… relative to cwd.

Shot catalog (cuts only)

uv run <skill_directory>/scripts/detect.py --input /path/to/clip.mp4

Shot stills for vision analysis

uv run <skill_directory>/scripts/detect.py --input clip.mp4
uv run <skill_directory>/scripts/extract-frames.py --shots-path .mediaskills/generated/clip_shots_*.json

uv run <skill_directory>/scripts/extract-frames.py --input clip.mp4

Threshold tuning

Operations

Each script returns structured JSON — see the script contract.

Op ID	Script	Common flags
`shots.detect`	`detect.py`	--input
`shots.extract_frames`	`extract-frames.py`	--input

Do not use for

Full program structure / act breaks (use `program-master`)
Vision-based scene understanding (use `vision-analysis`)