embedded-captions

Add captions to talking-head videos using 36 visual identities.

Updated Aug 23, 2026

Search Tags:#visual identity #subtitles #captions #video processing #talking-head

Ready to run

npx skills add https://github.com/jpratt9/dotfiles --skill embedded-captions-jpratt9

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: embedded-captions
Source: https://github.com/jpratt9/dotfiles/tree/main/.agents/skills/embedded-captions
Command: npx skills add https://github.com/jpratt9/dotfiles --skill embedded-captions-jpratt9

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires hyperframes, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill solves the problem of adding professional captions to talking-head videos, providing a wide range of visual identities to choose from, allowing users to create cinematic, thematic, or verbatim captions that enhance the viewing experience.

Core Features & Use Cases

36 Visual Identities: Offers a vast selection of visual styles, including cinematic, thematic, and verbatim options.
Customization: Allows users to customize captions based on the video content, including tone, shot, and platform.
Efficiency: Automates the process of adding captions, saving time and effort compared to manual methods.

Quick Start

Use the embedded-captions skill to generate captions for a video with the 'anchor' identity: 'add captions to video.mp4 using anchor'.

Frequently Asked Questions about embedded-captions

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I add professional captions to a talking-head video?▼

You can add professional captions to a talking-head video by applying one of 36 visual identities to your single-subject clip. The Skill automates subtitle generation using column-flow or themed constitutions to enhance the viewing experience.

What visual identities are available for video captions?▼

There are 36 visual identities available for video captions, including cinematic, thematic, and verbatim options. These styles allow you to customize subtitle aesthetics based on the video content, tone, shot, and target platform.

Does hyperframes support local processing for adding subtitles?▼

Yes, hyperframes supports local processing for adding subtitles. You need hyperframes installed to run the caption engines, which process single-subject clips locally without requiring external cloud rendering.

Can I use verbatim captions for single-subject video clips?▼

Yes, you can generate verbatim captions for single-subject video clips. The Skill offers verbatim embed options alongside themed constitutions, allowing exact transcription styling tailored for talking-head footage.

What is the difference between column-flow and themed constitutions for video processing?▼

Column-flow and themed constitutions are two caption engines for video processing. Column-flow manages dynamic subtitle layout, while themed constitutions apply specific stylistic rules to generate customized visual identities.

What are the limitations of adding captions to talking-head videos?▼

A key limitation is that adding captions requires a single-subject clip to function correctly. Additionally, you must have the hyperframes dependency installed to run the column-flow and themed constitution engines locally.