video-sketch
Skill46 starsChanged 2 months agoNo licenceView on GitHub
Make an animated explainer film with no footage — a hand-drawn/whimsical, a clean editorial, or a mixed-media paper-collage animation (cut-out pictures from an image model animated with type, tape labels, rubber stamps and torn paper, the "newspaper cutout" motion-design look) written as JavaScript, with an AI voice-over, an original score on sampled instruments and synthesised sound effects, rendered to MP4 and to a self-contained HTML player. It also makes real people talk from their photos -- bobble-heads, puppet cut-outs, a newspaper photo or a painting where only the mouth moves -- each with their own voice. Use when asked for an animation, an animated explainer or promo, a motion-graphics or motion-design video, a "whimsical hand-drawn" video, a collage / mixed-media / cut-out / scrapbook / newspaper-style video, a product or feature explainer, a 30-60 second ad, talking heads or bobble-heads made from photos, or anything that should be illustrated rather than filmed. Also for a square or vertical social promo in 3D motion-design style with real people in it -- a conference speaker announcement, a line-up, an event teaser with a speaker carousel, a ticket and a poster, music only, no narration. Also for a vertical short drama (a micro-drama: characters who speak in their own voices, a hook, a reversal and a twist in about 60 seconds), one film or a set in different looks.
In this repository26 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- hf-cliSkill
- check-scriptSkill
- etsy-keywordsSkill
- film-to-templateSkill
- lead-proposalSkill
- setupSkill
- studio-vmSkill
- topic-researchSkill
- video-captionsSkill
- video-card-designSkill
- video-channel-auditSkill
- video-dubSkill
- video-h3Skill
- video-image-overlaySkill
- video-multicamSkill
- video-multicam-switchSkill
- video-name-labelSkill
- video-projectSkill
- video-resolveSkill
- video-reviewSkill
- video-screen-cutSkill
- video-shortsSkill
- video-showreelSkill
- video-tightenSkill
- video-zoomSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
20 rules. About 0 are common, 2 are distinctive, and 18 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
18
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

