Spoken Short-Video Eight-Step Output Model

Problem It Solves

Short-video scripts often lack clear constraints: the opening may miss an information promise, the structure may stack points without stories, or the assistant may add book citations, product hooks, and private-domain conversion without being asked. This skill frames oral video production as step-limited output: it first defines scope, then produces a verbatim script, instead of automatically continuing into extra content.

How It Works

The core approach uses dual entry, optional nine steps, and three modes:
- Entry A: user provides an event, phenomenon, or trending term; the skill performs hotspot matching, then derives conflict.
- Entry B: user already has a viewpoint, judgment, or stance; it moves directly to conflict construction.
- Default core steps: usually complete conflict, opening, and structure only, then ask whether to add evidence, actionable insight, hook, replication point, or review.
It supports script creation from topic to draft, scoring an existing script with optimization notes, and building a content matrix from audience tags as audience × conflict × insight direction. Book citations and conversion hooks have explicit trigger rules: if the user does not request them, the skill does not force theory or preset a product direction.

Boundaries

This is useful when creators want to turn a fuzzy idea into an executable spoken draft, especially when persona, output scope, and conversion goal must be confirmed first. It does not replace topic judgment, account positioning, or product strategy. If a topic lacks natural traffic, the skill may recommend dropping it. For better control, specify scope such as core steps only, add hook, or all nine steps before asking for the final script.