A Claude Code skill that transforms a single spoken sentence into a 9:16, 5‑second paper‑collage explainer video with a three‑gate approval flow and optional voiceover.

Stars

165

7-day growth

+68

Forks

14

Open issues

0

License

NOASSERTION

Last updated

2026-07-17

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It enforces a locked editorial visual language (halftone cut‑outs, bold color fields, cream keylines) with automated frame‑by‑frame QA and a repair playbook, reducing manual editing for short‑form metaphorical explainers.

Who it is for

  • Content creators making short social‑media explainers
  • Educators who need quick visual metaphors for lessons
  • Marketers producing branded 9:16 video assets
  • Video editors seeking an automated pipeline for collage animation

Use cases

  • Turning proverbs or quotes into shareable video clips
  • Creating metaphorical B‑roll for presentations or courses
  • Generating consistent visual assets for a brand’s social feed
  • Rapid prototyping of explainer animations with client approval gates

Strengths

  • Three‑gate approval flow prevents wasted generation cost on unapproved ideas
  • Self‑QA checks (contact sheets, first‑frame purity, end‑frame alignment, anti‑fake‑lettering) ensure output reliability
  • Portable design: the pipeline can be swapped to other APIs without changing the prompt templates or QA logic
  • Voiceover fitting with silence trimming and muxing preserves the video stream untouched

Considerations

  • Requires MaxFusion MCP or alternative API keys (Google AI Studio + ElevenLabs) and ffmpeg installed locally
  • Video length is fixed at 5 seconds, limiting narrative depth
  • Dependent on Claude Code as the execution environment; not a standalone application

README quick start

_____ _____ .__ / \ _____ ___ / _ __ || ____ ____ / \ / \ \ \ / /\ \ | / / |/ _ \ /
/ Y / __ _> ) |
_
|
(
//_ \ || |
//
_ >|_/|__| / / / / / /

Collage B-roll Explainers

A Claude Code skill that turns a single spoken sentence into a premium editorial paper-collage explainer video — 9:16, 5 seconds, halftone cut-outs assembling piece by piece on a bold color field, optionally with a fitted voiceover.

You give it a line like "A snowball only needs the first push — the hill does the rest." It proposes a visual metaphor, waits for your approval, generates the finished still, waits again, then animates the whole scene assembling itself from an empty color field — and QAs its own output frame by frame.

Examples

"A snowball only needs the first push — the hill does the rest.""One flame can light the whole room — and lose none of its fire.""Tip the first tile — and the rest of your week runs itself."

Full-quality MP4s (with voiceover) are in examples/.

What the skill enforces

  • Three-gate approval flow — metaphors first, stills second, video last. You approve at each gate; nothing burns generation cost on an unapproved idea.
  • A locked visual language — flat bold paper fields, black-and-white halftone photographic cut-outs, colored cardstock accents, crisp cut edges, cream keylines, paper grain. Color semantics are part of the system (burnt orange = urgency, deep purple = rules, teal = judgment…).
  • Assemble-from-empty motion — the clip opens on a pure empty color field and builds the scene piece by piece with stop-motion timing. First and last frames are prepared locally with ffmpeg and passed as tagged references, so the video lands exactly on the approved still.
  • Self-QA — contact sheets, first-frame purity checks, end-frame comparisons, an anti-fake-lettering rule set, and a repair playbook for the failure modes that actually happen.
  • Voiceover fitting (optional) — pick a voice from your library, generate the line, trim silence, fit it into a 4–5s window, and mux — video stream untouched.

Requirements

  • Claude Code (or any agent

Description

Turn one spoken line into a paper-collage explainer video — Claude Code skill + MaxFusion MCP. English adaptation of gbro-collage-broll by pyang5166.

Related repositories

Similar projects matched by category, topics, and programming language.

MoonshotAI
Featured
MoonshotAI GitHub avatar

Kimi-K3

Kimi K3 is an open-weight, 2.8T-parameter native multimodal agentic model with a 1M-token context window, designed for frontier coding, knowledge work, and reasoning tasks.

AI & Machine LearningAI Agents
3,348
xuchonglang
Featured
xuchonglang GitHub avatar

investing-for-beginners

A structured investing guide for Chinese beginners covering US stocks, options, and cryptocurrency, with focus on foundational concepts and risk awareness.

Blockchain & Web3
2,739
Krishnagangwal
Featured
Krishnagangwal GitHub avatar

CS-Fundamentals

A curated collection of Computer Science fundamentals (PDFs, notes, cheatsheets, interview question banks) for placement preparation, covering seven core subjects plus general resources.

Data & DatabasesDatabases & Storage
2,326