Captions Overlay

Captions-overlay is a doctrine skill for the HyperFrames captions workflow, meant to load alongside the upstream `/hyperframes` captions reference rather than replace it. Its core idea is a three-way split for every spoken phrase: drop filler like um and uh, ride the verbatim lower-third rail for ordinary content, or promote a rare headline beat to an embed composited behind the subject. The rule that matters most is that captions are an overlay on top of the film, never a reserved bottom band, so you center compositions on the true frame midpoint instead of shifting content up to make room. Reach for it when adding subtitles to talking-head or launch videos, or when laying out a composition that will carry captions. My take: the rail-first, embed-scarce discipline is the useful part, since embedding every word is the mistake it's written to prevent.

skills.sh installs: 61.8K
GitHub stars: 81.8K
last updated: Oct 26, 2026

View on GitHub

Install

$ npx -y skills add heygen-com/hyperframes --skill captions-overlay --agent claude-code

Installs into .claude/skills of the current project.

Files

Captions Overlay Doctrine

Overlay doctrine — supplements the upstream /hyperframes skill's references/captions.md. Applies ON TOP of it; do not expect it folded into the upstream skill.

Two ideas combine here. First, the caption model — every spoken phrase is drop, rail, or embed, and embed is the scarce earned peak, not the default. Second, the overlay law — a caption line is composited ON TOP of the film as an overlay; it is NOT a reserved zone, so you never shift content up or leave a dead band to "make room" for it. The two reinforce each other: because captions ride as an overlay (the verbatim rail in front, the occasional embed behind the subject), the composition keeps its full frame and centers on the true vertical center.