Guizang's agent skill turns your repo's recent updates into a finished promo video — real components, code-rendered animation, an original code-written soundtrack — no video editor involved.
- agent-skill
- video
- promo
- marketing
video-talkcraft
An agent skill that turns Claude Code into a voiceover-video studio: word-level sync, 108 motion recipes, three-stage acceptance.
video-talkcraft takes a narration script plus a finished voiceover and produces an edited explainer video: it aligns word-level timestamps locally, writes each semantic beat into a SHOTBOOK storyboard, and renders with Remotion — kinetic captions, evidence screenshots, camera moves, and sound design locked to the voice track. It is the voiceover edition of the video-shotcraft series, documented in Chinese, with a live gallery previewing all 108 motion recipes.
What it does
- Word-level subtitle-to-voice alignment computed locally before any rendering
- 108 motion recipe cards, each previewed in a live online gallery
- Seven-layer shot system designed against slide-like output
- Renders real video files via Remotion; three-stage acceptance before delivery
When to use it
For creators who narrate in Chinese and want agent-produced explainer or demo videos with broadcast-style pacing, not slideshow exports.
Getting started
npx skills add Vincentwei1021/video-talkcraft # or clone and symlink: git clone https://github.com/Vincentwei1021/video-talkcraft.git cd video-talkcraft ln -s "$(pwd)" ~/.claude/skills/video-talkcraft
Things to know
PolyForm Noncommercial license — personal and non-commercial use only. Docs are Chinese-first; you provide the finished voiceover, the skill aligns to it rather than generating speech.
Repository
Vincentwei1021/video-talkcraftCharted
Related on the map
geo-sleuth
SkillAn agent skill that geolocates a photo with nothing readable in it — OSM geometry, elevation skylines and satellite tiles turn “where was this taken?” into a measured answer with an error radius.
- agent-skill
- geolocation
- osint
- openstreetmap
Birdview
SkillA skill that makes AI coding agents map the architecture and declare the blast radius before they touch a line of code — rendered as one standalone HTML page.
- skill
- architecture
- code-visualization
- change-scope