dbs-script-flow reads a short-video transcript section by section and looks at three things: whether each section connects to the next, whether any section repeats what was already said, and whether each sentence can be spoken in one breath. Every problem is quoted from the script, given a high, medium or small risk level and paired with a fix you can read aloud.
If you ask it to edit, it marks changes on top of your original text with strikethrough and a new-text marker, keeps a change table and ends with one sentence on which edits matter most. It leaves your arguments, cases and data alone.
What You Get
- A section table showing topic, function and status of every part of the script
- A problem list ranked high, medium and small, each with the quoted original and a speakable fix
- A verdict on logic links, information density and spoken fluency
- Optional mark-up editing that keeps your text visible, with a change table and a priority sentence
Common Use Cases
- Checking a talking-head script before recording to find where attention may fall
- Cutting repeated explanations from a draft that circles one point
- Splitting long sentences and adding glue lines so a script reads naturally aloud
What Makes It Unique
It works on the micro level between neighbouring sections, where other review skills judge the whole piece. It never overwrites your text: edits are layered as strikethrough, new-text and restored-text markers so earlier rounds stay visible. It asks about the shooting style before cutting lines that may depend on a whiteboard or gestures, and says so when a script is already smooth.
Under The Hood
The skill is a single instruction file with no scripts and no references. It reads the transcript you paste or point to and writes a markdown report in the chat. It does not browse, call services or save files; opening or saving review files is left to your environment. The editing mode reuses the same transcript and returns marked-up text in the reply.