Product Video logo

Product Video

Community
sanky369
product-video

Plan an animated product video end-to-end: pick the video type, define the animation style and pacing, write a beat-by-beat shot list, and produce ready-to-run keyframe prompts. Use whenever the user wants a product video, product animation, launch video, promo or ad video, animated product reveal, 360 spin, feature showcase, or 'a short video for my product' — even if they only say 'I need a video for the launch' or 'make my product look good in motion'. Also use to storyboard a video another tool will render. Produces a Product Video Production Spec: concept, beat sheet with timings and transitions, keyframe prompt list for fal-ai/nano-banana-pro, and audio/CTA direction.

Overview

Publishersanky369
Repositoryvibe-building-skills
Skill nameproduct-video
Stars
31
Forks
7
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 sanky369 on GitHub. Read the source before you install it.

Installation

Install the Product 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/sanky369/vibe-building-skills/tree/main/skills/creative/product-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/sanky369/vibe-building-skills.git /tmp/vibe-building-skills
mkdir -p .claude/skills
cp -r /tmp/vibe-building-skills/skills/creative/product-video .claude/skills/product-video
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product 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 Product 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 Product 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.

Product Video

Turn a product and a goal into a complete Product Video Production Spec — one chosen video concept, a beat-by-beat shot list with timings, an animation and pacing plan, and generation-ready keyframe prompts. The governing principle: one video communicates one thing. Every beat either builds toward the single message (the reveal, the benefit, the transformation) or it gets cut. You produce the plan and the keyframes; rendering the motion happens downstream.

When to use / when not to

  • Use for product-centric motion content: reveals, feature showcases, product-in-action, transformations, 360 spins.
  • If the video is fronted by a person (presenter, testimonial, UGC) → use skills/creative/talking-head.
  • If the video will be rendered programmatically in Remotion (UI demos, code tutorials, data viz) → use skills/creative/remotion-script-writer; you can still run this skill first to define concept and beats, then hand the beat sheet over.
  • If the user needs static assets (posts, banners) → skills/creative/social-graphics.
  • If there is no brand style guide yet and the user cares about brand consistency → run skills/creative/creative-strategist first; its style guide feeds this skill.

Intake

Ask in one tight batch, only what's missing:

  1. Product — what is it and what's the one thing the video must communicate (new launch? a feature? a benefit? a before/after)?
  2. Where it runs — TikTok/Reels/Shorts, product page, YouTube pre-roll, trade show loop? (This decides aspect ratio, duration, pacing.)
  3. What the viewer should do after — the CTA.
  4. Brand style — is there a skills/creative/creative-strategist style guide or existing brand assets to match?

Infer from context instead of asking: aspect ratio from platform, mood from product category, style from any existing brand materials in the project. Don't stall: if the product and goal are clear, state your assumptions for the rest ("Assuming Reels, 12s, vertical, energetic — say otherwise") and proceed.

Workflow

1. Choose the video type (decision rule, not a menu)

If the message is…TypeDurationBeat structure
"This exists / it's new"Reveal5–15shidden/obscured → reveal animation (fade, slide, rotate) → hero shot
"It does these 2–4 things"Feature Showcase15–30sfeature 1 highlight → feature 2 → feature 3 → full product
"Here's the benefit in use"In Action10–20sproduct in environment → product being used → outcome shown
"Look at the change"Transformation10–15sbefore state → morph → after state
"Just show the object" (e-commerce, listings)360 Spin5–10scontinuous smooth rotation, clean background

Commit to one type with a one-line reason. Offer a single backup only if two genuinely fit. Never showcase more than 4 features — cut to the strongest.

2. Set pacing from platform

  • Fast (5–10s, quick snappy cuts): social feeds, ads, anything skippable. Hook in the first 2 seconds.
  • Medium (10–20s, smooth transitions): product pages, marketing site, email embeds.
  • Slow (20–30s, deliberate luxurious moves): premium/luxury products, storytelling. Only choose slow if the product's price point earns the patience.

Aspect ratio by placement: 9:16 vertical (TikTok/Reels/Shorts/Stories), 16:9 (YouTube, web hero), 1:1 or 4:5 (feed posts). These map directly to --aspect-ratio values in the CLI.

3. Pick one animation style

Match to brand personality — pick exactly one and use its phrase verbatim in every keyframe prompt so frames stay consistent:

Brand feelStylePrompt phrase
Elegant, calmSmooth Fade"smooth fade transitions, gentle pacing, elegant"
Modern, energeticDynamic Slide"dynamic slide transitions, elements slide in, energetic pacing"
Cinematic, boldZoom & Rotate"zoom and rotate moves, dynamic pacing, cinematic"
Sophisticated, fluidMorphing"smooth morphing transitions, fluid animation, sophisticated"
High-techParticle Effects"particle effects, product materializes/dissolves, high-tech"

4. Write the beat sheet

Break the duration into 3–6 beats. For each beat: time range, what's on screen, camera/motion, and the transition out. Every beat must advance the single message; the last beat always holds the product + CTA for ≥2 seconds.

5. Write keyframe prompts

One keyframe per beat (two for a transformation's before/after). Each prompt = subject + state at that beat + the animation-style phrase + lighting + the same style/lighting descriptors across all frames (consistency is what makes frames read as one video). All keyframes use identical background and lighting descriptions unless the beat explicitly changes location.

If FAL_API_KEY (or FAL_KEY) is set, generate the keyframes now with the repo CLI — model fal-ai/nano-banana-pro via docs/fal_api.py:

bash
python docs/creative_cli.py custom \
  --category "video-keyframes" --name "beat-1-hero" \
  --prompt "<keyframe prompt>" --aspect-ratio 9:16 --resolution 2K

If no key is set, deliver the prompts as ready-to-run commands. Note: nano-banana-pro generates still keyframes only — the motion between them is produced downstream (Remotion, a video generation tool, or an editor).

6. Self-check against the quality bar, then deliver the spec.

Required output format

Always deliver this structure:

markdown
# Product Video Production Spec — [Product]

## Overview
- **Message (one sentence):** ...
- **Type:** Reveal | Feature Showcase | In Action | Transformation | 360 Spin — [one-line reason]
- **Platform / placement:** ... · **Aspect ratio:** ... · **Duration:** ...s · **Pacing:** Fast/Medium/Slow
- **Animation style:** [style + verbatim prompt phrase]
- **CTA:** ...

## Beat sheet
| # | Time | On screen | Camera / motion | Transition out |
|---|------|-----------|-----------------|----------------|
| 1 | 0–3s | ... | ... | ... |
| 2 | 3–7s | ... | ... | ... |
(final beat: product + CTA, held ≥2s)

## Keyframes
### KF-1 (beat 1) — [label]
> [full nano-banana-pro prompt]
`python docs/creative_cli.py custom --category "video-keyframes" --name "kf-1" --prompt "..." --aspect-ratio [ratio] --resolution 2K`
(repeat per beat; identical style/lighting descriptors across all)

## Audio direction
- Music: [genre/energy matched to pacing] · Sound design: [key moments] · VO: [none, or one line per beat]

## Production notes
- [render path: Remotion via skills/creative/remotion-script-writer / video gen tool / editor]
- [anything beat-specific: logo timing, text overlays, loop point for trade-show/spin videos]

Quality bar (check before delivering)

  • One message; if you can't state it in one sentence, restart at step 1.
  • Hook lands within the first 2 seconds for Fast pacing, 4 for Medium.
  • Beat count 3–6; no beat shorter than 1.5s; timings sum exactly to the stated duration.
  • Every keyframe prompt contains the same animation-style phrase and the same lighting/background descriptors (unless the beat changes location) — inconsistent frames are the #1 failure mode.
  • Prompts specify "smooth", "fluid" motion language — never leave motion quality implicit.
  • CTA present in the final beat, held ≥2 seconds.
  • No invented performance claims ("this format gets 3x engagement") — pacing/duration guidance above is heuristic, label it as such if asked.

Integration

  • skills/creative/creative-strategist → feeds in: the style guide (colors, mood, lighting language) that all keyframe prompts must obey.
  • skills/creative/product-photography → feeds in: existing hero-shot prompts/lighting setups reused as the video's hero frame for consistency.
  • skills/creative/image-generation → consumes: keyframe prompts, if the user wants deeper control over generation than the CLI one-liners.
  • skills/creative/remotion-script-writer → consumes: the beat sheet + keyframes, when the video will be rendered as a Remotion composition.
  • skills/creative/social-graphics → consumes: hero keyframes as source imagery for supporting static posts.

Frequently asked questions

What does the Product Video AI skill do?

Plan an animated product video end-to-end: pick the video type, define the animation style and pacing, write a beat-by-beat shot list, and produce ready-to-run keyframe prompts. Use whenever the user wants a product video, product animation, launch video, promo or ad video, animated product reveal, 360 spin, feature showcase, or 'a short video for my product' — even if they only say 'I need a video for the launch' or 'make my product look good in motion'. Also use to storyboard a video another tool will render. Produces a Product Video Production Spec: concept, beat sheet with timings and t...

Why use Product Video on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sanky369/vibe-building-skills/tree/main/skills/creative/product-video. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Product 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 Product Video?

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

Is the Product Video AI skill free?

Yes. It is published on GitHub by sanky369 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 👇