Cinematic Caption — effect skill for captions & subtitles

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Designed editorial captions for HyperFrames: scored hero words, subject-aware depth, glass type — not a subtitle strip.

What it does

Turns a transcript (SRT/VTT or word-level JSON) into designed caption moments inside an existing HyperFrames composition: it scores hero words by meaning and proof value, builds ordered mixed-case stacks, anchors type around the speaker and only layers words behind a person when a real matte exists. It writes cinematic-caption-plan.json first, then a namespaced overlay track or caption sub-composition on one seek-safe timeline, and verifies with hyperframes check, cue snapshots and a chronological contact sheet before render. Instructions only (no scripts); it leans on the HyperFrames skills and CLI for transcription, linting and preview. Young repo: three commits over two days in August 2026.

Use when

Not for

Install

Used for

More captions & subtitles skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.