Skip to content
SkillModel-led4,251 tokens in use

dbs-script-flow

Checks a short-video transcript for logic gaps, repeated points and lines that are hard to speak, and marks the spots where viewers are likely to swipe away.

11,518 stars on the repository Custom / Unknowndontbesilent2025/dbskill · skills/dbs-script-flow
npx -y skills add dontbesilent2025/dbskill -g --all
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing dbs-script-flow costs

78tokens idle
4,251tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Fair
  • Frontmatter8/15
  • Structure16/25
  • Examples12/15
  • Output0/15
  • Size15/15
  • Resources0/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

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.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers