Showcase Video logo

Showcase Video

CommunityPopular
rehan-remade
showcase-video

Record and cut a short showcase video of a game mod, or a compilation of clips, ready to post on X/YouTube. Records the game window with only the game's own audio, picks moments from contact sheets, and edits with one-line animated titles, creator credits, transitions, music, watermark and fade-out via an EDL JSON. Use when the user wants a demo video, trailer, clip or montage of a mod, or wants to combine existing clips into a styled video.

Overview

Publisherrehan-remade
Repositoryuniversal-modder
Skill nameshowcase-video
Stars
3.4K
Forks
293
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 rehan-remade on GitHub. Read the source before you install it.

Installation

Install the Showcase Video 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/rehan-remade/universal-modder/tree/main/.agents/skills/showcase-video
  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/rehan-remade/universal-modder.git /tmp/universal-modder
mkdir -p .claude/skills
cp -r /tmp/universal-modder/.agents/skills/showcase-video .claude/skills/showcase-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Showcase Video 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 Showcase Video 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 Showcase Video 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.

Showcase video

A mod isn't finished until you can show it in 30 seconds. The toolchain is um win record (capture), um video contact (look), um video compile (edit), all ffmpeg + Pillow.

1. Make the take repeatable

  • Script the action. Use a mod-side timeline or command sequence (spawn enemies, fire the weapon, cue the boss), a scenario with triggers and camera moves, or a WinDrive command list. The first clean take should be reproducible exactly, so you can reshoot after a fix.
  • Restore the world before each take. Explosions crater worlds; units die. Keep a pristine copy with um backup and restore it every take.
  • Clean frame. Hide debug text, fix the camera zoom (the Terraria showcase used 1.5x so 1080p frames read like a 720p cut), run at full speed when unfocused, and hide the cursor (capture uses capture_cursor=0).

2. Record the window + the game's own audio

bash
um win record --exe Game.exe --out C:\caps\take1 --seconds 40      # -> take1.mkv, take1.audio.raw, take1.json
um video first-frame C:/caps/take1.mkv                              # where gameplay starts (skips loading screens)
um video mux C:/caps/take1.mkv C:/caps/take1.audio.raw C:/caps/take1.json take1.mp4 [--offset 0.25]
  • Video: ffmpeg gfxcapture of that window only (GPU frames, no desktop). It encodes with NVENC, AMF or QSV when available. NVENC H.264 maxes out at 4096 px wide, so the recorder scales above that; for 32:9 screens, crop to the centre 16:9 with --crop.
  • Audio: WASAPI process loopback of the game's PID (um/ps1/ProcLoopback.ps1). Only the game is recorded; no Spotify, no notifications. It's timestamped so the file position is wall time. Muxing uses the recorded offset. Fine-tune with a visual/audio sync event (a flash vs its boom) and pass --offset.
  • Inside a mod (optional): start and stop recording from the mod for frame-exact takes. Never block the game's main thread while stopping ffmpeg: send q, then wait off-thread. Write .mkv so a killed recorder still leaves a playable file (see examples/terraria-tmodloader/reference/InModRecorder.cs).

3. Look before you cut

bash
um video probe clip.mp4
um video contact clip.mp4 sheet.png --every 1.5 --cols 6     # a timestamped grid; read it, pick in/out points
um video contact clip.mp4 zoom.png --start 20 --end 30 --every 0.5

Pick the peak moments: the explosion, the boss reveal, the unit in formation. Write in/out times into the EDL.

4. Edit with an EDL

um video compile edl.json out.mp4 (--preview renders half size and fast). The full format is in um video --help.

json
{
  "size": [1920, 1080], "fps": 30,
  "theme": {"accent": "#B6FF3B"},
  "transition": {"type": "fade", "duration": 0.3},
  "clip_volume": 0.8,
  "music": {"path": "music.mp3", "volume": 0.5},
  "watermark": {"path": "logo.png", "height": 54, "corner": "br"},
  "segments": [
    {"clip": "take1.mp4", "in": 9.0, "dur": 3.0, "hook": "Terraria, but with a tactical nuke."},
    {"clip": "take1.mp4", "in": 24.2, "dur": 4.5, "title": "Tactical Nuke", "transition": {"type": "pixelize"}},
    {"clip": "take2.mp4", "in": 3.0, "dur": 5.0, "title": "Drone Mothership boss"},
    {"card": {"title": "Fal Arsenal", "sub": "a Terraria mod"}, "dur": 2.5}
  ]
}
  • Transitions: any ffmpeg xfade type (fade, pixelize, slideleft, smoothleft, circleopen, zoomin, radial...) or cut.
  • Fills: for non-16:9 clips, fill: blur (blurred backdrop), crop or pad.
  • Per clip: speed and volume, zoom to punch in past UI, crop [x, y, w, h] to reframe.
  • Music: um fal music "..." --seconds 60 makes a bed. Set bpm and use beats instead of dur to cut on the beat; um video beats music.mp3 estimates tempo and first beat.

Style that works (from real feedback)

  • Titles: one line naming what's on screen ("Wonder: the Transamerica Pyramid", "Robotaxis and Delivery Drones"). No small explanatory captions about how it was made; that goes in the post text.
  • Pace: get into gameplay within 2-3 s; menus and setup stay under 3 s. Clips run 3-5 s each. End on the mod name or URL and fade out.
  • Sound: keep the game's audio. It sells impacts. Music under a compilation, clip audio around 0.5-0.8.
  • Compilations of other people's clips: credit every creator on screen (credit: "@handle") and in the post, and ask permission when it's promotional. Don't imply their clips were made with your tool. Download only public posts, and only what you'll use.
  • Last step: look at a contact sheet of the finished video before sharing it.

Frequently asked questions

What does the Showcase Video AI skill do?

Record and cut a short showcase video of a game mod, or a compilation of clips, ready to post on X/YouTube. Records the game window with only the game's own audio, picks moments from contact sheets, and edits with one-line animated titles, creator credits, transitions, music, watermark and fade-out via an EDL JSON. Use when the user wants a demo video, trailer, clip or montage of a mod, or wants to combine existing clips into a styled video.

Why use Showcase Video on TypingMind?

Because you install it once and use it with any model. Showcase Video 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 Showcase Video in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rehan-remade/universal-modder/tree/main/.agents/skills/showcase-video. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Showcase Video?

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 Showcase Video?

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

Is the Showcase Video AI skill free?

Yes. It is published on GitHub by rehan-remade 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 👇