changelog-video

Converts weekly changelog markdown into a branded square video with voiceover, captions, and animated UI mockups.

Updated Sep 6, 2026
One-click install
npx skills add https://github.com/AbuBakar125-co/Resturant_web --skill changelog-video-abubakar125-co
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: changelog-video
Source: https://github.com/AbuBakar125-co/Resturant_web/tree/main/agent/skills/changelog-video
Command: npx skills add https://github.com/AbuBakar125-co/Resturant_web --skill changelog-video-abubakar125-co

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? Turning a weekly product changelog into a polished, on-brand video normally requires manual scripting, voiceover recording, motion design, and caption timing. This Skill automates that entire pipeline, producing a lint-clean, seam-verified HyperFrames video project from a single changelog markdown file. ## Core Features & Use Cases - End-to-end video pipeline: Parses a changelog digest, cuts it to a 45-60 second editorial script, generates Annie voiceover via HeyGen TTS, and aligns word-level timestamps into a caption rail. - Visualization-first scenes: Routes every changelog theme through a visualization registry that mocks the actual UI (editor, inspector, terminal, render panel) instead of bullet-point slides. - Self-contained brand kit: Ships fonts (TT Norms Pro, ABC Solar Display), an animated background pattern, background music, a pronunciation lexicon, and a master HTML scaffold so every video stays on-brand. - Use Case: Given a weekly digest markdown with four themes and thirty items, produce a 1080x1080 square video with spoken narration, timed captions, animated product mockups, and verified quality gates before rendering. ## Quick Start Use the changelog-video skill to turn this weekly changelog markdown into the branded weekly video project.

Frequently Asked Questions about changelog-video

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

FAQPage Schema
How do I turn a changelog into a video automatically?

Provide a changelog markdown with themes and items, and the pipeline parses it, cuts it to a 45-60 second script, generates HeyGen voiceover, aligns captions, and builds a HyperFrames project. Rendering happens only when explicitly requested.

How are captions synchronized with the voiceover?

The HeyGen TTS helper emits word-level timestamps of the spoken text, and the align-captions.mjs script maps them back onto display tokens to produce captions.json. If timestamps are missing, a whisper forced-alignment fallback generates them from the audio.

What video format and length does the changelog video use?

Output is a square 1080x1080 composition targeting 45-60 seconds total: a title under 2 seconds, roughly four theme scenes of 9-12 seconds each, and an outro under 3.5 seconds.

What happens if a technical term is missing from the pronunciation lexicon?

The pipeline stops and asks the user how the term is pronounced, then adds the display-to-spoken mapping to lexicon.json. Guessing pronunciations is explicitly forbidden because the TTS would read terms like JSON or CLI incorrectly.

Why does the changelog video build fail the caption gate?

Builds fail when the caption rail LINES array in the scaffold is left empty or vo-words.json is missing. Populate LINES from captions.json and verify sampled rendered frames show visible caption text before shipping.