New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Layered-Collage Documentary Shorts

by hassancs91 in hassancs91/claude-faceless-shorts-creator

Builds a vertical collage-style documentary short from script to render: scene dissection into image layers, layer production, TSX assembly on a collage kit, frame checks and voice.

MITAuto-check passedMedia & Creative

Install Layered-Collage Documentary Shorts

skills CLI
$ npx skills add hassancs91/claude-faceless-shorts-creator --skill make-vox -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install hassancs91/claude-faceless-shorts-creator make-vox --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/hassancs91/claude-faceless-shorts-creator.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/make-vox .claude/skills/make-vox && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
make-vox
GitHub stars
271
Token cost
~1.5k tokens
SKILL.md length
620 words
Files
1
Skills in repo
5
Repo updated
First seen
Licence
MIT

At a glance

Builds a vertical collage-style documentary short from script to render: scene dissection into image layers, layer production, TSX assembly on a collage kit, frame checks and voice.

  • Works in 6 steps: script + scene dissection → layer production (cheapest source that… → TSX assembly (the choreography) → …
  • Producing a documentary or explainer short in a paper-collage style
  • SKILL.md covers Artifact contract, Format, Stage 1 — script + scene… and Stage 2 — layer production…, plus 5 more sections
  • Calls python, node and npm

What it does

This skill covers the Vox-style paper-collage look end to end for a vertical short of 35 to 45 seconds at 1080 by 1920. Every scene is dissected into separate image layers such as paper board, die-cut subjects, maps, archival prints, label chips and arrows, and the TSX side choreographs them with many simple staggered moves plus a virtual camera instead of complex per-image animation. Stage one is a script.md beat sheet listing each scene's camera move, its layers with sources and timing, and its annotations. A scene should have two to six layers, and facts are verified before scripting.

Layer production picks the cheapest source that works: AI images through tools/gen_image.py with die-cuts from tools/cutout.py (rembg preferred over the white-key fallback), HTML captured to transparent PNG with Playwright for charts and text blocks, and SVG written directly in TSX for arrows and routes. Map and archival prompts ask for no text, since AI text comes out garbled and label chips annotate instead. Assembly uses the CollageBoard camera and parallax kit in remotion/src/lib/collage.tsx, followed by frame QA, render, and voice plus sound effects through shared tooling. Plain TSX animation and video-model clips are handled by the neighboring make-short and make-ai-short skills.

When your agent uses it

  • Producing a documentary or explainer short in a paper-collage style
  • Making a map-travel or archival-history sequence
  • Continuing an existing vox-N series in the same repository

Example prompts

  • “Make a Vox-style collage short about the history of the shipping container.”
  • “Write the script.md beat sheet for a map-travel short on the Silk Road, with layers for each scene.”
  • “Continue the vox series with a new episode on how espresso machines work.”

Requirements

  • Python with pillow and rembg
  • Playwright with Chromium
  • The Remotion project with its collage kit

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. script + scene dissection
  2. layer production (cheapest source that works, reuse first)
  3. TSX assembly (the choreography)
  4. QA (do not skip; it caught real bugs on vox-1)
  5. voice
  6. SFX/music (suggest-sfx machinery)

What it can do on your machine

Read from SKILL.md and the folder at commit 773054b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • python
    • node
    • npm
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npm and pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Layered-Collage Documentary Shorts loads about 1.5k tokens when it runs. Until then it costs about 179 tokens; SKILL.md has 620 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~179
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from hassancs91/claude-faceless-shorts-creator at commit 773054b, republished under its MIT licence (© hassancs91). 620 words, ~1,510 tokens.

Download SKILL.mdSave it as .claude/skills/make-vox/SKILL.md (or your agent's skills folder).
name
make-vox
description
Build a Vox-style LAYERED-COLLAGE vertical short end-to-end — script + scene dissection into image layers, layer production (AI images via gen_image.py + cutout.py, HTML→PNG, SVG-in-TSX), choreographed TSX assembly on the collage kit (CollageBoard camera, parallax, cutouts, chips, routes), frame QA, render, then voice/SFX via the shared machinery. Use when the user wants a "vox style", documentary, or explainer-collage short, a map-travel or archival-history sequence, or to continue the vox-N series — the paper-collage look, not plain TSX animation (that is make-short) and not video-model pixels (that is make-ai-short). Defers raw TSX crash rules to vidtsx-2d-generator and SFX taste to suggest-sfx.

make-vox — layered-collage documentary shorts, end to end

Every scene is DISSECTED into separate image layers (paper board, die-cut subjects, maps, archival prints, label chips, arrows) and the TSX side choreographs the layers so they assemble on screen. Polish = many simple staggered layer moves + a virtual camera — never complex per-image animation. The visual language + architecture live in vox-shorts/DESIGN.md (read it first); this skill is the build pipeline. Proven on vox-1 (coffee).

Run everything from the repo root. Layer production needs extra Python deps (the only tools in this repo that do): pip install pillow rembg (die-cuts) and pip install playwright && playwright install chromium (HTML→PNG captures).

Artifact contract

vox-shorts/vox-N-<topic>/
  script.md        — beat sheet: per scene → on-screen layers + camera + (VO)
  scenes.json      — optional machine contract once voice lands (like beats.json)
  voice/ · sfx-plan.json · output/        (same machinery as the short-N flow) [voice/output gitignored]
remotion/src/shots/vox-N/VoxN<Name>.tsx   — THE composition
media/projects/vox-N-<topic>/layers/      — every generated layer + gen_image sidecars (committed)

Kit: remotion/src/lib/collage.tsx — CollageBoard (camera keyframes + parallax context), Cutout, ArchivalPhoto, PaperBG, LabelChip, SerifStatement, SketchArrow, Grain, VOX palette. Grow the kit generically; project-specific hacks stay in the shot.

Format

1080×1920 @30, 35–45s. The hook grammar of make-short applies: composed frame 0, loop-friendly tail, no CTA outros.

Stage 1 — script + scene dissection

Write script.md: scenes with, for EACH scene — the camera move (anchor x/y/zoom), the layer list (what image, which source, entrance + timing), annotations (chips/routes/statements). Facts verified before scripting. A scene is 2–6 layers; if you can't name the layers, the scene isn't designed yet.

Stage 2 — layer production (cheapest source that works, reuse first)

  • Photographic subjects / textures / maps / archival prints → python tools/gen_image.py, then python tools/cutout.py for die-cuts (rembg auto; white-key is the no-deps fallback and FAILS on contact shadows — don't fight it, install rembg).
    • Maps/archival: prompt "NO text, no labels" — AI text is gibberish; chips annotate instead.
    • Cutout subjects: "isolated on plain white background" still helps rembg edge quality.
  • Charts / UI / documents / styled text blocks → HTML file + Playwright screenshot (python tools/capture_web.py, omitBackground for alpha).
  • Arrows, routes, shapes → SVG directly in TSX (SketchArrow etc.) — never rasterize.
  • Layers land in media/projects/vox-N-<topic>/layers/; anything reusable by 2+ videos graduates to media/library/.
Show full SKILL.md (319 more words)Show less

Stage 3 — TSX assembly (the choreography)

  • ONE CollageBoard cam={CAM} at the root; scenes are <Sequence layout="none">s INSIDE it so the camera travels ACROSS scene boundaries. Cam keys are GLOBAL frames; entrance ats are LOCAL to their Sequence (the classic local-frame bug — check every cue).
  • Persistent scenery (a map under two scenes) gets its own long Sequence; annotations get a shorter one wrapped in a fade-out so they leave before the next scene composes over them.
  • Geometry pattern: place big layers via constants (MAP = {cx,cy,w}) and derive annotation positions as fractions of the layer (mapPt(0.24, 0.52)), so re-generating art only means re-eyeballing two fractions.
  • Depth taste: background board −0.06, scenery 0–0.05, foreground props 0.08–0.15. Every layer keeps its idle drift (default) — nothing fully freezes.
  • Contrast rule (locked): SerifStatement over any busy layer (map/photo) MUST use backing; light-accent chips (VOX.yellow) need dark kickerColor. Headlines are FONT_EDITORIAL (Source Serif 4 @700) — don't swap fonts per video.
  • Hard rules (frame-based only, monotonic interpolate, Easing.bezier, <Img> never <img>) → vidtsx-2d-generator.

Stage 4 — QA (do not skip; it caught real bugs on vox-1)

cd remotion && npm run gen
node scripts/frames.mjs VoxNName <f0,entrance-cues,camera-arrivals,transitions,last> --scale=0.5

READ every PNG: every entrance landed · camera framing at each arrival (nothing critical cropped) · text contrast over its actual background · cutout edges clean (re-cutout, don't mask in TSX) · scene handoffs (fading annotations gone before the next scene needs the space). Then node scripts/render-all.mjs VoxNName --scale=1 and spot-check frames FROM THE MP4.

Stage 5 — voice

python tools/gen_voice.py --beats … --emit-ts exactly as make-short Stage 4 (word-exact captions if the format wants captions; documentary style often runs caption-free).

Stage 6 — SFX/music (suggest-sfx machinery)

Collage taste: paper slides on entrances, soft thuds on place landings, whooshes on camera moves, route-draw scribbles — sparse and editorial, decorative cues optional: true. The user's ear is the audit gate.

Done =

script.md scenes each name their layers · all layers generated + sidecars in media/projects · composition QA'd at cues and from the final mp4 · contrast rule honored · voice + SFX when requested · kit additions generic.

© hassancs91, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/make-vox of hassancs91/claude-faceless-shorts-creator.

Open the folder on GitHubat commit 773054b

Compare with similar skills

Layered-Collage Documentary Shorts next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Layered-Collage Documentary Shorts compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Layered-Collage Documentary Shorts this skillhassancs91/claude-faceless-shorts-creator271—~1.5kAutomated safety check: PassMIT
Remotionzhuzhaoyun/Molio433—~4kAutomated safety check: PassCustom licence
Claude Typervibe-motion/skills1.3k—~979Automated safety check: PassNone
Remotion Video Enhanceranbeime/skill7.7k—~1.9kAutomated safety check: NotesNone
Concept To VideoMathews-Tom/armory328—~4.9kAutomated safety check: PassMIT
Video ScriptbozhouDev/video-skills-toolkit150—~1.8kAutomated safety check: PassMIT

Similar skills

  • Remotion

    zhuzhaoyun/Molio

    Molio's builtin skill for MAKING a video from any source — wiki notes, articles, scripts, product info, or a brief — and rendering it to MP4.

    433 GitHub stars~4k tokensUpdated today
    Media & CreativeAuto-check passed

  • Claude Typer

    vibe-motion/skills

    Render a Claude-style prompt typing animation video by calling Remotion CLI against the remote site https://www.laosunwendao.com.

    1.3k GitHub stars~979 tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

  • Remotion Video Enhancer

    anbeime/skill

    Adds Remotion-style video transitions and Framer Motion page animations to PPT-based videos and HTML slide viewers, planning the animation sequence first.

    7.7k GitHub stars~1.9k tokensUpdated yesterday
    Media & CreativeAuto-check: notes

  • Concept To Video

    Mathews-Tom/armory

    Turn concepts into animated explainer videos using Manim (Python) with MP4/GIF output, audio overlay, multi-scene composition.

    328 GitHub stars~4.9k tokensUpdated 3 days ago
    Media & CreativeAuto-check passed

  • Video Script

    bozhouDev/video-skills-toolkit

    使用已经锁定的完整口播音频与带时间码字幕，把确认后的逐字稿转成管线无关的视频导演方案和 Beat Graph。适用于“根据最终配音做分镜”“按字幕设计整片画面”“规划 B-roll/证据/素材”“做 HyperFrames 或 Remotion…

    150 GitHub stars~1.8k tokensUpdated 2 mo ago
    Media & CreativeAuto-check passed

  • Render Myth Vs Fact

    gooseworks-ai/goose-skills

    Assemble a myth-vs-fact kinetic-typography explainer video ad (≈29.5s, 9:16) from N myth/fact pairs + hook / turn / punch copy + palette + a brand end-card PNG + a VO track — a hook, 3 red-strike…

    1.2k GitHub stars~2.2k tokensUpdated today
    Media & CreativeAuto-check passed

More from hassancs91/claude-faceless-shorts-creator

  • VidTSX 2D Video Generator

    hassancs91/claude-faceless-shorts-creator

    Generates 2D Remotion-based TSX video files for VidTSX from a shot or scene description, with style presets and rules that keep renders from crashing.

    271 GitHub stars~2.8k tokensUpdated 1 mo ago
    Auto-check passed

  • AI Video Short Maker

    hassancs91/claude-faceless-shorts-creator

    Produces a vertical generative-video short end to end: a locked recurring character animated by a fal video model, ElevenLabs voice, Remotion captions and a clean loop.

    271 GitHub stars~1.6k tokensUpdated 1 mo ago
    Auto-check: notes

  • TSX Vertical Shorts Builder

    hassancs91/claude-faceless-shorts-creator

    Builds a roughly 40-second vertical short end to end from a topic, scripting beats, rendering TSX compositions and layering voice and captions.

    271 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: notes

  • Sound Effects Planner for Shorts

    hassancs91/claude-faceless-shorts-creator

    Proposes beat-synced sound effects for a rendered short from a reusable library, then mixes an audition preview under the voice once you approve the plan.

    271 GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check: notes

Works with

Categories

Questions about Layered-Collage Documentary Shorts

What does Layered-Collage Documentary Shorts do?

Builds a vertical collage-style documentary short from script to render: scene dissection into image layers, layer production, TSX assembly on a collage kit, frame checks and voice. This skill covers the Vox-style paper-collage look end to end for a vertical short of 35 to 45 seconds at 1080 by 1920. Every scene is dissected into separate image layers such as paper board, die-cut subjects, maps, archival prints, label chips and arrows, and the TSX side choreographs them with many simple staggered moves plus a virtual camera instead of complex per-image animation.

When should I use Layered-Collage Documentary Shorts?

Layered-Collage Documentary Shorts fits situations like: producing a documentary or explainer short in a paper-collage style; making a map-travel or archival-history sequence; continuing an existing vox-N series in the same repository.

How do I install Layered-Collage Documentary Shorts in Claude Code?

Run `npx skills add hassancs91/claude-faceless-shorts-creator --skill make-vox -a claude-code`. Or copy the skill folder (.claude/skills/make-vox in hassancs91/claude-faceless-shorts-creator) into .claude/skills/make-vox in your project. Claude Code loads it when a task matches its description.

How do I install Layered-Collage Documentary Shorts in Codex?

Run `npx skills add hassancs91/claude-faceless-shorts-creator --skill make-vox -a codex`. Or copy the skill folder (.claude/skills/make-vox in hassancs91/claude-faceless-shorts-creator) into .agents/skills/make-vox in your project. Codex loads it when a task matches its description.

Can I use Layered-Collage Documentary Shorts in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add hassancs91/claude-faceless-shorts-creator --skill make-vox -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/make-vox, .gemini/skills/make-vox, .github/skills/make-vox and .opencode/skills/make-vox in your project.

What does Layered-Collage Documentary Shorts need to run?

Going by SKILL.md and its folder, Layered-Collage Documentary Shorts needs the command-line tools its instructions call (python, node, npm and pip). Our summary lists: Python with pillow and rembg; Playwright with Chromium; The Remotion project with its collage kit.

Does Layered-Collage Documentary Shorts access the network?

SKILL.md contains no URLs. Its commands use npm and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Layered-Collage Documentary Shorts safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Layered-Collage Documentary Shorts use?

Layered-Collage Documentary Shorts is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Layered-Collage Documentary Shorts use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Layered-Collage Documentary Shorts?

Skills that share tags, products or a category with Layered-Collage Documentary Shorts: Remotion (zhuzhaoyun/Molio, 433 stars), Claude Typer (vibe-motion/skills, 1.3k stars), Remotion Video Enhancer (anbeime/skill, 7.7k stars) and Concept To Video (Mathews-Tom/armory, 328 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Layered-Collage Documentary Shorts?

hassancs91 (a GitHub user) maintains it in hassancs91/claude-faceless-shorts-creator, which has 271 GitHub stars. The repository holds 5 skills in this directory. The repository was last updated on August 18, 2026.

Source: hassancs91/claude-faceless-shorts-creator on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.