analyze-videolisted

# Analyze video → reusable prompting template Someone found a video style they love. Your job is to deconstruct it into a reusable prompting template — a formula they can plug any product, person or setting into and get that same style back from `seedance-2.0`. The output is **not** a single prompt. It is a **formula file** saved into `skills/novoads-api/prompting/prompt-library/`, built the way [seedance-2-ugc.md](../prompt-library/seedance-2-ugc.md) is built: layers, variables, option banks, rules, and a worked example, so the agent can generate unlimited prompts in that style. **Nothing in steps 1 to 6 touches the API.** Frame extraction, transcription and analysis are local work on the user's own file: no calls, no credits. Only step 7, the optional test render, spends anything, and it runs through the two gates in [SKILL.md](../../SKILL.md) like every other generation. **The 15-second constraint is the whole design problem.** `seedance-2.0` and `seedance-2.0-mini` take any integer 4 to 15 seconds, and the reference video is usually 30 to 60. Your template has to distil the style into what fits one 15-second clip, and say how to recreate the longer arc across a series of clips. ## Dependencies - **ffmpeg** / **ffprobe** — required for frame and audio extraction (step 1). `brew install ffmpeg` on macOS. - **whisper** — optional, for transcription (step 2). `pip3 install openai-whisper`. If it is unavailable, ask the user to paste the dialogue instead. Neither is