short-drama-breakdown studies reference series or your own finished cuts. A script measures episode length, shot length and dialogue density from the videos, and the agent reads sampled frames and subtitles to describe the opening beat, how information is delivered, the end-of-episode hook and how one episode leads into the next.
It lays your plan or your own cut next to the benchmark in a gap table, hands the gaps to the skill that owns each fix, and can reverse-engineer a video into a verbatim script and, if asked, setup documents, storyboard and prompts. Reverse-engineered material stays in the benchmark folder unless the work is yours or licensed. The skill’s text is in Chinese.
What You Get
- A registry file per reference series with its source and permitted use
- Measured statistics: episode length, shot length, dialogue density, opening and ending timing
- A written reading of each reference covering opening, information delivery, hooks and cross-episode links
- A same-ruler gap table between the benchmark and your own plan or cut
- Optionally a reconstructed script and setup, storyboard and prompt documents from a video you own
Common Use Cases
- Study what top series do in their first three seconds before writing your own opening
- Measure your finished cut against a benchmark and send each gap to the right stage skill
- Reverse a video you own into a script to remake or continue it
What Makes It Unique
It keeps measurement, interpretation and unknowns apart in every note, and it keeps study material fenced off: real titles, character names and lines from a study reference may not enter your own project documents. Reconstructed documents leave the benchmark folder only when the work is registered as owned or licensed with the basis written down. It never sets pacing numbers for you; the creator confirms them.
Under The Hood
The agent runs a bundled Python script on the local machine with ffmpeg and ffprobe to measure videos, cut contact sheets of representative frames, attach subtitle transcripts and optionally cut shot slices, writing the results under the project’s input folder. It reads the videos and subtitles you provide and writes Markdown and JSON files in the project. The instructions ask whether footage may go to an external model service and keep records of that choice. It does not fetch web pages or call web services by itself.