video-structure-design

Installation
SKILL.md

Video Structure Design

Bottom-Layer Reasoning

Apply the think-one-step-further mechanism as a lightweight check:

  • Confirm this skill is solving the user's real intent, not only the surface request.
  • Make the output immediately usable and name any unavoidable next action.
  • Extract the reusable structure and, when aligned, propagate it to adjacent prompts, skills, checklists, or workflows.
  • Add one guardrail for the most likely next failure while preserving this skill's primary workflow.

Purpose

Use this skill before writing scripts, storyboards, or AI-video prompts. It decides the video's macro skeleton: what the first second promises, how attention is renewed, where information turns, how the climax lands, and why the viewer stays until the end.

This skill is not the same as screenwriting. Screenwriting handles character, conflict, scene, and dialogue. Video structure handles duration, retention, segment order, information release, beat density, rhythm curve, ending button, loopability, and platform/use-case fit.

Use temporal hinge words when a video needs a natural emotional or behavioral progression. Structure can be driven by "刚刚发生的余温 -> 此刻的行动 -> 即将到来的压力/反转", so the viewer feels time moving instead of watching disconnected cool shots.

Installs
1
GitHub Stars
9
First Seen
Oct 5, 2026