Reel Export logo

Reel Export

Community
charlie947
reel-export

Turn any horizontal or square motion video into a 1080 x 1920 Instagram Reel or TikTok that uploads cleanly. Headline and logos inside the safe zone, H.264, yuv420p, limited colour range, bt709, a silent audio track when there is no sound, and an ffprobe check before upload. Use when someone says "make this a reel", "vertical version", "export for Instagram", "TikTok version", "9:16 cut", "reel export" or has a 16:9 or 4:5 video that needs to go on a vertical feed.

Overview

Publishercharlie947
Repositorymotion-graphics-skills
Skill namereel-export
Stars
428
Forks
62
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by charlie947 on GitHub. Read the source before you install it.

Installation

Install the Reel Export AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/charlie947/motion-graphics-skills/tree/main/skills/reel-export
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/charlie947/motion-graphics-skills.git /tmp/motion-graphics-skills
mkdir -p .claude/skills
cp -r /tmp/motion-graphics-skills/skills/reel-export .claude/skills/reel-export
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Reel Export in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Reel Export on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Reel Export is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Reel export

Most motion is built wide. This turns it into a vertical file with a hook on top that the apps accept without washing out the colours.

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.

Step 1: Ask for four things, then wait

  1. The video. Any MP4, any size.
  2. The headline, two short lines, word for word. It is the hook people read with the sound off.
  3. Logos, as attached files, if the video names a product or company.
  4. The background colour around the video. Default: near-black #0B0B0F.

Step 2: The safe zone

The app draws its own buttons, caption and profile over the edges of a Reel. Keep every word and logo:

  • between y 360 and y 1420 (nothing in the bottom 500px)
  • out of the right 120px

Put the headline at the top of that zone, then the video under it. A 16:9 video scaled to 1080 wide is 608 tall, so it sits well at y 660.

Step 3: Build the overlay, then encode

Build a transparent 1080 x 1920 overlay.png in HTML with the headline and any logos, and screenshot it. Text you can style beats text burned in by ffmpeg. Then:

ffmpeg -y -i in.mp4 -loop 1 -i overlay.png -f lavfi -i anullsrc=r=48000:cl=stereo -filter_complex "color=c=0x0B0B0F:s=1080x1920:r=30[bg];[0:v]fps=30,scale=1080:-2,setsar=1[v];[bg][v]overlay=0:660:shortest=1[o];[o][1:v]overlay=0:0:shortest=1,scale=out_color_matrix=bt709:out_range=tv,format=yuv420p[out]" -map "[out]" -map 2:a -shortest -c:v libx264 -profile:v high -crf 18 -pix_fmt yuv420p -color_range tv -colorspace bt709 -color_primaries bt709 -color_trc bt709 -c:a aac -b:a 128k -movflags +faststart reel.mp4

This adds a silent AAC track. If the video has its own sound, swap -map 2:a for -map 0:a.

Step 4: Check before upload

ffprobe -v error -show_entries stream=codec_type,codec_name,width,height,pix_fmt,color_range,color_space -of compact reel.mp4

Pass means: video h264, 1080 x 1920, yuv420p, color_range=tv, bt709, plus one aac audio stream. If you see hevc or color_range=pc, encode again. Then pull one frame from the middle and look at it at phone size.

What I learned the hard way

  • A phone recording is often HEVC and full range. Uploaded as is, it can come out washed out or re-encoded badly. Always export a fresh H.264, limited-range file, including after any edit.
  • A logo over footage vanishes on light frames. Put each logo (and its label) on its own dark rounded tile.
  • faststart matters. Without -movflags +faststart the file cannot start playing until it has fully loaded.
  • Keep the hook to two lines. Mine were short enough to read in a second: "This Mac launch" / "is 100% code".

Frequently asked questions

What does the Reel Export AI skill do?

Turn any horizontal or square motion video into a 1080 x 1920 Instagram Reel or TikTok that uploads cleanly. Headline and logos inside the safe zone, H.264, yuv420p, limited colour range, bt709, a silent audio track when there is no sound, and an ffprobe check before upload. Use when someone says "make this a reel", "vertical version", "export for Instagram", "TikTok version", "9:16 cut", "reel export" or has a 16:9 or 4:5 video that needs to go on a vertical feed.

Why use Reel Export on TypingMind?

Because you install it once and use it with any model. Reel Export is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Reel Export in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/motion-graphics-skills/tree/main/skills/reel-export. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Reel Export?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Reel Export?

As many as you like. As long as a model supports skills, you can use Reel Export with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Reel Export AI skill free?

Yes. It is published on GitHub by charlie947 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇