Launch Video logo

Launch Video

CommunityPopular
dzhng
launch-video

Make a showreel-grade motion-graphics launch video, with music, that introduces a CLI, library, or product from its repo. Use when asked for a launch, promo, sizzle, or showreel video, an animated intro for a project, or a video to post on X/social.

Overview

Publisherdzhng
Repositoryskills
Skill namelaunch-video
Stars
1.1K
Forks
66
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 dzhng on GitHub. Read the source before you install it.

Installation

Install the Launch 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/dzhng/skills/tree/main/skills/graphics/launch-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/dzhng/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/graphics/launch-video .claude/skills/launch-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Launch 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 Launch 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 Launch 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.

Launch Video

The bar is a showreel: the piece a motion designer puts on their résumé to prove how good they are — dynamic, ambitious, scored to music, a real professional production and never a demo or prototype. Go all out. The repo supplies the story; the craft is yours. Nothing here is a template: if the piece could be re-skinned for any other project, it has failed.

Workflow

  1. Find the story. Read the README, docs, benchmarks, and brand art. Done when you can state, each with a source: what it is in one line, how it works underneath (the audience is technical), and the proof worth landing. Flag any claim the repo cannot back instead of inventing its meaning.
  2. Direct before you build. Choose one visual concept grown from what the project is (its metaphors, its brand art, its mechanism): a world with its own look, camera, and signature move, rather than a sequence of panels. Then commit to one familiar real-world analogy for the mechanism (building a city, running a kitchen, a heist) and map every step onto it: name each step in the analogy's vocabulary, and give each one the everyday props that explain it at a glance (a surveyor's tripod, stakes, cranes, an inspection stamp). Digestible beats clever: a viewer should get each step from references they already know, without reading a word. Write it as a shot list on a music timeline. Done when every shot names its camera move and the one moment in it a motion designer would be proud of. A shot whose description is "a card/panel/list appears" gets redesigned.
  3. Build picture and score from one timing source. Every event time lives in one place that both the scenes and the soundtrack read, so hits land on hits. Synthesizing the music in code keeps that lock exact.
  4. Review as a director. Render a draft, tile each shot into contact sheets, and get a fresh-eyes critique from a subagent that has not seen your plan. Then ask each shot the showreel question. Fix and re-render until every shot passes, not a sample.
  5. Ship. Make the thumbnail (rules below), render the master (1080p60, high-quality H.264, 320k AAC), reveal it in Finder, and commit the project to the repo as a standalone package, with renders and generated audio ignored and a short README covering commands, the timing principle, and the claim sources and methodology kept outside the film.

Marketing, not a white paper

Lead with the product and a few memorable benefits. Keep methodology, sample sizes, missing-data allowances, benchmark caveats and source citations in the package README or linked report, not in the video or key art. Do not add fine print, asterisk footnotes, disclaimer blocks or defensive narration. If a claim needs narrowing to stay true, narrow the headline itself; never use tiny text to rescue a misleading headline. Review each frame for reading burden as well as visual quality.

Show, don't tell

Text is the last resort. Before any word goes on screen, find the picture that makes it unnecessary: an object that transforms, a world that changes, motion that performs the idea. Keep text only where nothing visual can carry it: the product's real commands, its name, and a claim that must be exact. The one exception is orientation: give each shot one header saying what is happening (it can be dynamic, like a live count that ticks with the action), or the best animation reads as random motion. When a draft leans on labels, captions, or subtitles to explain what is happening, redesign the shot instead of rewording the text.

The showreel question

Would a motion designer put this shot on their reel? Tells that it has slid into explainer or demo:

  • Animated slide deck. A static layout where elements slide in and hold. A reel's camera is always going somewhere, and its composition keeps changing.
  • Reading, not watching. Paragraphs, UI cards, body copy, or a subtitle under a headline (a headline that needs a subtitle is two ideas). A reel speaks in few-word hits at dramatic scale, and the visuals carry the mechanism.
  • Broken metaphor. An action that doesn't do what it depicts: a cut that ignores the pieces it claims to divide, a label nobody could read against its ground. Make the motion true to the objects on screen.
  • One trick. Every element springs in the same way. A reel shows range: depth and parallax, scale contrast, match cuts and transitions that carry an element into the next shot, speed ramps, lighting and color shifts, particles and physics, typography that moves as design.
  • Flat. Everything sits on one plane at one scale, with no foreground, background, or light.
  • Deaf. Motion ignores the music, or the music sits under the picture instead of driving it.
  • Prototype 3D. Untextured primitives under flat light with no lens: it reads as a tech demo. If the piece goes 3D, finish it like a game cinematic: physically based materials with surface detail and bevels that catch light, reflections and soft shadows, emissives that bloom, and a lens (ambient occlusion, depth of field, grain, aberration on impacts).

Rules

  • Rebuild, never screenshot. Break any UI down into parts that can move.
  • Judge effects in a rendered frame, never the live preview. Frame-by-frame renderers (Remotion's manual advance, for one) can silently drop a post stack or a canvas layer that looks fine live.
  • Claims stay exact. Verify headline claims against the source and keep their scope clear in the headline. Preserve supporting evidence in the docs; follow the marketing rule above for what belongs on screen.
  • You cannot listen. Verify the mix by measurement (integrated loudness around −11 to −14 LUFS, and a spectrogram showing risers and impacts at their cue times), and say in the handoff that the audio was checked by measurement, not by ear.
  • Thumbnail. Feeds (X) pick an early frame and skip a one-frame poster, so hold the preview for ~0.3s of pre-roll, then move it into the opening (shift the music by the same amount). Match the pre-roll background to the opening so playback doesn't flash. The best preview is the product doing its job (name, tagline, a completed command and its output); the headline number gets its payoff shot and a separate key-art still.

Frequently asked questions

What does the Launch Video AI skill do?

Make a showreel-grade motion-graphics launch video, with music, that introduces a CLI, library, or product from its repo. Use when asked for a launch, promo, sizzle, or showreel video, an animated intro for a project, or a video to post on X/social.

Why use Launch Video on TypingMind?

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

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

Which AI models can use Launch 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 Launch Video?

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

Is the Launch Video AI skill free?

Yes. It is published on GitHub by dzhng 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 👇