Communitygithub.com

make-video

Generate animated, voiced portrait (1080x1920) YouTube Shorts from a study guide or topic - split a guide into parts, write narration, build kinetic word-synced scenes, voice them with Kokoro TTS and render MP4s. Use when the user asks to make, generate, render or re-render a short, video, part or episode, or to turn a document into a Shorts series.

What is make-video?

make-video is a Claude Code agent skill that generate animated, voiced portrait (1080x1920) YouTube Shorts from a study guide or topic - split a guide into parts, write narration, build kinetic word-synced scenes, voice them with Kokoro TTS and render MP4s. Use when the user asks to make, generate, render or re-render a short, video, part or episode, or to turn a document into a Shorts series.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/rana3128/claude-skills-plugins/tree/HEAD/plugins/video-gen/skills/make-video

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

Make voiced kinetic Shorts

Everything renders with the bundled pipeline in pipeline/ next to this file (the "Base directory for this skill" shown when the skill loads).

0. Setup (once per project)

If the project has no video_gen/ folder with kinetic_build.py, create it:

mkdir -p video_gen && cp <skill dir>/pipeline/* video_gen/
cd video_gen
python3 -m venv .venv && .venv/bin/pip install -r requirements.txt            # drawing (Python 3.11+)
python3.12 -m venv .venv-tts && .venv-tts/bin/pip install -r requirements-tts.txt  # Kokoro voice

ffmpeg must be on PATH. voice.py runs the TTS worker in .venv-tts next to it. Run every command from video_gen/.

1. Read the rules

  • DESIGN.md - the kinetic visual style. Hard rules: boxes stack in one full-width column, never side by side; no accent bars on box edges; big text; each element appears on its spoken word; headings fit one line (about 30 characters); no burned-in subtitles.
  • PARTS.md - the part.md format, narration rules, and how to split a guide. Don't read engine_short.py, templates.py or skin.py unless debugging them.

2. New series: split first, get approval

  1. Analyse the source guide and propose a part list (one concept per part, about 90-125 s each). Stop for user approval. Never cut content to hit a length; add examples and the "why" instead.
  2. Write every <series>/pNN_<slug>/part.md, plus <series>/README.md with the analysis and a parts table.
  3. Add the series folder to SERIES in build_part.py (kicker + footer). Optionally add a logo mark to MARKS in kinetic.py.
  4. Lint narration: .venv/bin/python build_part.py <part dir> --lint and fix every problem. Narration: no recap, no welcome, jump straight to the topic; no symbols or code; spell out acronyms for the voice; beats at most 45 words.

3. Scenes

Each part gets a scenes.py defining SCENES. Two styles (see examples/):

  • Declarative stage blocks (preferred, fast): SCENES = K.part(word, tag, chips, [[blocks...], ...]) using Track, Pipe, Rows, Code, Lanes, Bars, Ring, Fan, Chips, Big, Note. A cue is a word prefix (searched after the block's previous cue), (word, beat) or a beat number. Example: examples/p03_*.
  • Hand-written Scene classes for a metaphor the blocks can't show. Example: examples/p01_*. List cue words in spoken order, or cues come back MISSING.

4. Check, then render

.venv/bin/python kinetic_build.py <part dir> --stills /tmp/pNN.png   # contact sheet + cue report
.venv/bin/python kinetic_build.py <part dir> --out <series>/output   # final <slug>_voiced.mp4
.venv/bin/python cue_scan.py <series>/p*_*                           # text-only sync check

Fix every MISSING cue and overflow before the final render. For a whole series, render the first two parts and get the user's OK on the look, then run the rest 3 at a time in the background (xargs -P 3).

5. Report

A table: MP4 link, topic, length, longest silence (target under 1 s). Mark the parts rendered in the series README. Say plainly what was not checked (frames not viewed, audio not listened to).

Never

  • Put boxes side by side, edge accent bars, small text, or burned-in subtitles.
  • Propose per-video voice calibration; sync is word-timed and generic.
  • Edit engine_short.py directly; build_part.py patches it in memory.

Related Skills