What problem does it solve? Deciding how on-screen text should look and where it should sit in a finished video is inconsistent and error-prone. This Skill provides a single authoritative decision standard for caption styling, placement, and emphasis so subtitles stay readable in both muted and sound-on viewing without conflicting with the visual subject. ## Core Features & Use Cases - Caption Hierarchy & Safe Zones: Enforces rules such as captions always on the top layer, shared track-wide styling, one message per cue, lower-third anchoring, platform safe zones, and a 480px-width readability check. - Keyword Emphasis Discipline: Limits each cue to one accent word with a viewer job, restricts emphasis to one of three techniques (color, weight/size, or form), and defines kinetic entrance timing of 0.08-0.12s. - Platform Style Presets: Provides default font size, color, and alignment tables for 16:9 landscape, 9:16 vertical, podcast/interview, entertainment, and premium scenarios, plus deep-dive references on kinetic captions and long-to-short clipping. - Use Case: When editing a vertical short video, use this Skill to decide caption font size (48-56px), confirm safe-zone placement, and pick a single accent word per cue before handing off to the timeline editor. ## Quick Start Use the captions skill to define the subtitle style, placement, and emphasis rules for my vertical short video project.
