Motion Video in Remotion
ooiyeefei/ccc
Builds marketing and explainer videos in Remotion from rendered scenes, with one real product capture as proof, and cuts them for each platform's formats.
Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos.
Install Model Showdown
$ npx skills add charlie947/motion-graphics-skills --skill model-showdown -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install charlie947/motion-graphics-skills model-showdown --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/model-showdown .claude/skills/model-showdown && rm -rf skills-srcUse ~/.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/
Install the "model-showdown" agent skill from https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdown into .claude/skills/model-showdown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-showdown", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdownType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add charlie947/motion-graphics-skills --skill model-showdown -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install charlie947/motion-graphics-skills model-showdown --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/model-showdown .agents/skills/model-showdown && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "model-showdown" agent skill from https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdown into .agents/skills/model-showdown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-showdown", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add charlie947/motion-graphics-skills --skill model-showdown -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install charlie947/motion-graphics-skills model-showdown --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/model-showdown .cursor/skills/model-showdown && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "model-showdown" agent skill from https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdown into .cursor/skills/model-showdown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-showdown", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/charlie947/motion-graphics-skills.git --path skills/model-showdown--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add charlie947/motion-graphics-skills --skill model-showdown -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install charlie947/motion-graphics-skills model-showdown --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/model-showdown .gemini/skills/model-showdown && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "model-showdown" agent skill from https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdown into .gemini/skills/model-showdown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-showdown", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install charlie947/motion-graphics-skills model-showdownInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add charlie947/motion-graphics-skills --skill model-showdown -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/model-showdown .github/skills/model-showdown && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "model-showdown" agent skill from https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdown into .github/skills/model-showdown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-showdown", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add charlie947/motion-graphics-skills --skill model-showdown -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install charlie947/motion-graphics-skills model-showdown --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/model-showdown .opencode/skills/model-showdown && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "model-showdown" agent skill from https://github.com/charlie947/motion-graphics-skills/tree/main/skills/model-showdown into .opencode/skills/model-showdown/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-showdown", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
model-showdown- GitHub stars
- 180
- Token cost
- ~1.1k tokens
- SKILL.md length
- 430 words
- Files
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos.
- Works in 4 steps: Ask for four things, then wait → The fair-test rules → Stack them → …
- Someone says compare three models
- SKILL.md covers Step 1: Ask for four things,…, Step 2: The fair-test rules, Step 3: Stack them and What I learned the hard way, plus 1 more section
- Calls ffmpeg
What it does
Model Showdown is an agent skill from charlie947/motion-graphics-skills. Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos. Makes a 16:9 side-by-side for a newsletter and a 1080 x 1920 stacked reel for Instagram and TikTok. Use when someone says "compare three models", "same prompt three AIs", "model showdown", "which AI is the best motion designer", "side by side comparison video" or wants a fair head-to-head of AI outputs.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Media & Creative, covering Newsletters, Logo and visual identity and Motion graphics. It works with Instagram and TikTok. The repository describes itself as: 13 Claude Code skills for launch-grade motion graphics. Every frame is code. No After Effects, no video generator. The licence is MIT.
When your agent uses it
- Someone says compare three models
- Same prompt three AIs
- Which AI is the best motion designer
- Side by side comparison video
Example prompts
- “compare three models”
- “same prompt three AIs”
- “model showdown”
- “/model-showdown”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit dfc4284. 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:
ffmpeg
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
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
Model Showdown loads about 1.1k tokens when it runs. Until then it costs about 122 tokens; SKILL.md has 430 words of instructions outside code blocks.
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 charlie947/motion-graphics-skills at commit dfc4284, republished under its MIT licence (© charlie947). 430 words, ~1,071 tokens.
Download SKILL.mdSave it as
.claude/skills/model-showdown/SKILL.md (or your agent's skills folder).- name
- model-showdown
- description
- Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos. Makes a 16:9 side-by-side for a newsletter and a 1080 x 1920 stacked reel for Instagram and TikTok. Use when someone says "compare three models", "same prompt three AIs", "model showdown", "which AI is the best motion designer", "side by side comparison video" or wants a fair head-to-head of AI outputs.
Model showdown, three AIs on one brief
A fair test people can see for themselves. One brief, three models, first try each, one renderer.
Before you start: read brand.md and MOTION.md if they exist. If not, run brand-intake first, or ask for hex codes, a font and a logo file. Never call a result on-brand without them. The brand applies to the headline and labels, never to the models' outputs.
Step 1: Ask for four things, then wait
- The brief, word for word. Every model gets the exact same text.
- The three models, named exactly as their makers write them, and how the user reaches each one (their own accounts only).
- The logo files for each model, attached. Never redrawn from memory.
- The headline, two short lines. Example: "Same prompt." / "Three AI models."
Step 2: The fair-test rules
- First try only. No re-rolls, no fixes, no "one more go" for the one you hoped would win.
- The models write HTML, you render it. Add this to the brief so no model gets a better export:
Deliver ONE self-contained index.html, [WIDTH] x [HEIGHT] px. Output the complete HTML only. A shared renderer will execute window.seek(t) and export each model's output at the same settings.
Implementation: deterministic window.seek(seconds), wrap modulo [SECONDS], every visual state derived from time. Automatic playback when not in ?render mode. Under ?render freeze until seek. Set window.__ready=true after initialisation. No external requests. Do not add controls, debug text, the model name or screenshots.- Same renderer, same settings for all three: same size, 30fps, same length, same encoder.
- A failure stays in. If a model returns broken HTML or nothing, its panel says so. Never swap in a later try.
Show full SKILL.md (215 more words)Show less
Step 3: Stack them
Newsletter (16:9): three panels side by side, each with its model name above it on a plain strip.
Reel (1080 x 1920): three 1080 x 360 panels stacked at y 540, 900 and 1260, over a dark background. Build a transparent 1080 x 1920 overlay.png in HTML holding the headline and the three labels, then:
ffmpeg -y -i a.mp4 -i b.mp4 -i c.mp4 -loop 1 -i overlay.png -f lavfi -i anullsrc=r=48000:cl=stereo -filter_complex "color=c=0x0B0B0F:s=1080x1920:r=30:d=12[bg];[0:v]fps=30,scale=1080:360:force_original_aspect_ratio=increase,crop=1080:360,setsar=1[a];[1:v]fps=30,scale=1080:360:force_original_aspect_ratio=increase,crop=1080:360,setsar=1[b];[2:v]fps=30,scale=1080:360:force_original_aspect_ratio=increase,crop=1080:360,setsar=1[c];[bg][a]overlay=0:540[t1];[t1][b]overlay=0:900[t2];[t2][c]overlay=0:1260[t3];[t3][3:v]overlay=0:0,scale=out_color_matrix=bt709:out_range=tv,format=yuv420p[out]" -map "[out]" -map 4:a -t 12 -c:v libx264 -crf 18 -pix_fmt yuv420p -color_range tv -colorspace bt709 -color_primaries bt709 -color_trc bt709 -c:a aac -b:a 128k -movflags +faststart showdown-reel.mp4Change d=12 and -t 12 to your length. The crop keeps the centre, so check one frame per panel and move the crop if the action sits off-centre.
What I learned the hard way
- A logo over footage vanishes on light frames. Every label (logo plus model name) sits on its own dark rounded tile in the top-left of its panel.
- Safe zone. The headline sits between y 360 and 520. No word or logo goes below y 1420 or into the right 120px, where the app draws its buttons and caption.
- Label with the full model name, version included. "Opus 5.5", not "Claude".
- End the caption on a question. Mine asked "Which one would you post?" and gave my own pick.
Step 4: Check and export
Pull one frame from the middle. Can you read every label at phone size? Is each logo the right company? Then run the checks in reel-export before you upload.
© charlie947, 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 skills/model-showdown of charlie947/motion-graphics-skills.
Open the folder on GitHubat commit dfc4284
Compare with similar skills
Model Showdown 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Model Showdown this skillcharlie947/motion-graphics-skills | 180 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Motion Video in Remotionooiyeefei/ccc | 495 | — | ~2.9k | Automated safety check: Pass | MIT | |
| Viral Tech Reel Editortornikebolokadze1-cyber/awesome-ai-pulse-georgia | 143 | — | ~3k | Automated safety check: Pass | CC0-1.0 | |
| Motion Adnodetool-ai/nodetool | 560 | — | ~3.4k | Automated safety check: Pass | AGPL-3.0 | |
| DesignOhh-889/skyroc | 795 | 9 repos | ~3.1k | Automated safety check: Pass | MIT | |
| Motion Adfabricioctelles/skills | 106 | — | ~4.1k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Viral Tech Reel Editor
tornikebolokadze1-cyber/awesome-ai-pulse-georgia
End-to-end viral tech reel production for Instagram Reels and TikTok using 2026 trend grammar — retention-first pacing, punch-ins, 3D cinematic AI-generated shots, motion design graphics, proof…
Motion Ad
nodetool-ai/nodetool
Make a short sound-off motion-graphics ad (a 15s Facebook, Instagram or TikTok ad, 4:5 or 9:16) from a product's real screenshots and photos, with every claim checked against the page it links to.
Design
Ohh-889/skyroc
Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations…
Motion Ad
fabricioctelles/skills
Produce a short motion-graphics video ad — a 15s Facebook/Instagram/TikTok spot — as a rendered MP4.
Influencer Discovery
tigerless-labs/influencer-discovery
Find the bloggers/creators who can help promote your work, capture their contact info, and append them to the target sheet in Google Sheets.
More from charlie947/motion-graphics-skills
All 9 skills in this repoMotion Effects
charlie947/motion-graphics-skills
Build any of 16 premium motion effects from scratch in your own brand, as one 8-second looping HTML file with window.seek(seconds) so it exports frame-exact to MP4 or GIF.
Animated Chart
charlie947/motion-graphics-skills
Make a looping animated chart for LinkedIn or a newsletter in code with Claude Code.
Apple Launch Film
charlie947/motion-graphics-skills
Rebuild an Apple-style Mac launch film entirely in code with Claude Code.
Launch Video
charlie947/motion-graphics-skills
Make a 30-45 second product launch video in code with Claude Code, the kind SaaS companies post on launch day.
Loop Cover
charlie947/motion-graphics-skills
Turn a newsletter or blog cover into a seamless looping GIF at 896 x 640, 180 frames at 20fps.
Milestone Reveal
charlie947/motion-graphics-skills
Make a 12-second looping milestone clip in code with Claude Code.
Related
Categories
Questions about Model Showdown
What does Model Showdown do?
Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos. Model Showdown is an agent skill from charlie947/motion-graphics-skills. Give the same motion brief to three AI models, keep each first try, render all three the same way and stack them into one comparison video with model names and logos.
When should I use Model Showdown?
Model Showdown fits situations like: someone says compare three models; same prompt three AIs; which AI is the best motion designer; side by side comparison video.
How do I install Model Showdown in Claude Code?
Run `npx skills add charlie947/motion-graphics-skills --skill model-showdown -a claude-code`. Or copy the skill folder (skills/model-showdown in charlie947/motion-graphics-skills) into .claude/skills/model-showdown in your project. Claude Code loads it when a task matches its description.
How do I install Model Showdown in Codex?
Run `npx skills add charlie947/motion-graphics-skills --skill model-showdown -a codex`. Or copy the skill folder (skills/model-showdown in charlie947/motion-graphics-skills) into .agents/skills/model-showdown in your project. Codex loads it when a task matches its description.
Can I use Model Showdown 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 charlie947/motion-graphics-skills --skill model-showdown -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-showdown, .gemini/skills/model-showdown, .github/skills/model-showdown and .opencode/skills/model-showdown in your project.
What does Model Showdown need to run?
Going by SKILL.md and its folder, Model Showdown needs the command-line tools its instructions call (ffmpeg).
Does Model Showdown access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Model Showdown 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 Model Showdown use?
Model Showdown 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 Model Showdown use?
About 1.1k tokens (SKILL.md is roughly 4.3k 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 Model Showdown?
Skills that share tags, products or a category with Model Showdown: Motion Video in Remotion (ooiyeefei/ccc, 495 stars), Viral Tech Reel Editor (tornikebolokadze1-cyber/awesome-ai-pulse-georgia, 143 stars), Motion Ad (nodetool-ai/nodetool, 560 stars) and Design (Ohh-889/skyroc, 795 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Model Showdown?
charlie947 (a GitHub user) maintains it in charlie947/motion-graphics-skills, which has 180 GitHub stars. The repository was last updated on October 10, 2026.
Source: charlie947/motion-graphics-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.