Turn a multilingual product launch into a warm editorial film: native language names roll beside a stable product identity, original hand-drawn people and pastel badges. Export landscape, portrait and square MP4s, with reviewed website language evidence, editable source and optional local music or voice clips.
Actual 16-second exports · ten fictional language declarations
index.html + project.jsonlandscape/ + portrait/ + square/: film.mp4, poster, stillsportraits/*.svg + *.png + portrait-pool.jsonfonts/ + assets/ + noticestimeline.json + storyboard.csv + captions.vttsoundtrack.wav + audio-evidence.json (when selected)input-evidence.json + render-evidence.jsonhandoff.md + delivery-manifest.jsonCapabilities: 6–20-second films; native language labels including Arabic, Hindi and CJK; measured font coverage and RAQM shaping; three palettes; eight reusable original portraits; licensed logo and font inputs; 1080, 1440 and 2160 short-edge outputs; exact frame timelines; optional local PCM WAV music and per-language voice clips.
Deliverables: actual H.264/AAC movies, posters, chapter stills, captions, editable project JSON, portrait SVG/PNG pool, website declaration evidence, storyboard CSV, audio/render evidence and SHA-256 handoff manifest. Browser edits download source for a fresh rebuild.
First run: build the included Dockerfile, then run scripts/build-film.py against examples/launch.json with --render. Docker includes Python, Pillow, RAQM and FFmpeg; native Python setup is also documented. Inspect a public HTTPS site or supplied HTML to draft language declarations; review before announcing language support.
Validation: real 16-second / 30-fps movies in all three 1080 formats; actual 1440 and 2160 landscape exports at 12 proof fps; Arabic/Hindi glyph shaping; measured language-window roll-in; full audio/video decode; supplied music/clip/logo flow; edited JSON rebuild; strict input, path, font, pacing and archive checks.
Version 1.0.0: original MIT workflow, hand-drawn fictional people and procedural score, with OFL font notices. Gather is a fictional ten-language concept. Website declarations do not certify complete translations; pronunciation and linguistic quality need a native reader. Optional voices are supplied WAVs, not generated TTS. $4.99 one-time; eligible active Premium membership includes this package.
FROM PACKAGE TO FIRST RESULT
Play the fictional Gather launch in three actual exported formats. Edit the brand, language declarations and palette, then rebuild a reviewed brief into a new delivery.
These steps use a project folder. Open the project in your agent and run terminal commands from its root.
Package folder .agents/skills/language-launch-film
Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.
Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.
Read SKILL.md, review the generator and check its runtime requirements before running:
cd .agents/skills/language-launch-film
docker build -t language-launch-film .
docker run --rm --network none -v "$(pwd):/skill:ro" -v "$(pwd)/output:/output" language-launch-film --input examples/launch.json --output /output/sample-film --renderPlay all three actual MP4s, jump to native language chapters, inspect the original portrait pool and download source. Edit product copy, languages, duration and palette; download edited-launch.json beside the delivery fonts/assets. Review declarations, set reviewed=true and rebuild into a fresh folder. Existing movies remain unchanged until regenerated.
Docker provides Python, Pillow, RAQM and FFmpeg; see SKILL.md for native setup. Arabic/Hindi require RAQM. Bundled CJK fonts cover native language labels; supply a licensed font for CJK brand copy. Original pulse audio is optional; approved local PCM WAV music and voice clips can be mixed. Site inspection reads explicit HTML language declarations, not verified translation completeness. No paid API or TTS call is bundled.
If sample-film already exists, change the output to ./sample-film-2. Existing files are never overwritten.
Use Language Launch Film at .agents/skills/language-launch-film. Read SKILL.md and review scripts/build-film.py. Run examples/launch.json into a new output folder and show me all generated files. Keep fictional sample content clearly labeled.
Tried this workflow? Help others decide with an honest review.
The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.
This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.
The documented 1.0.0 workflow lists: index.html + project.json; landscape/ + portrait/ + square/: film.mp4, poster, stills; portraits/*.svg + *.png + portrait-pool.json; fonts/ + assets/ + notices; timeline.json + storyboard.csv + captions.vtt; soundtrack.wav + audio-evidence.json (when selected); input-evidence.json + render-evidence.json; handoff.md + delivery-manifest.json. Some files or exports are optional; follow the package’s setup and inspect the delivered result.
Docker provides Python, Pillow, RAQM and FFmpeg; see SKILL.md for native setup. Arabic/Hindi require RAQM. Bundled CJK fonts cover native language labels; supply a licensed font for CJK brand copy. Original pulse audio is optional; approved local PCM WAV music and voice clips can be mixed. Site inspection reads explicit HTML language declarations, not verified translation completeness. No paid API or TTS call is bundled.
