Product Film logo

Product Film

Community
Rieranthony
product-film

Make a showreel-grade product film (landing-page loop, launch video, promo, demo reel, social cut) in code with Remotion, built on the product's own design system, components and voice. Use when someone asks for a product video, landing video, promo, launch film, explainer or "motion design video" for their app, SaaS or codebase. It asks what to include, then covers design discovery, story, music sync, transitions, review loops and a verified final render.

Overview

PublisherRieranthony
Repositoryproduct-film-skill
Skill nameproduct-film
Stars
420
Forks
31
Bundled files
24
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.

  • 24 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Product Film 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/Rieranthony/product-film-skill/tree/main/plugins/product-film/skills/product-film
  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/Rieranthony/product-film-skill.git /tmp/product-film-skill
mkdir -p .claude/skills
cp -r /tmp/product-film-skill/plugins/product-film/skills/product-film .claude/skills/product-film
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Product Film 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 Film 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 Film 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 film

A film that looks like the product made it: its colors, type, components, logo and voice, cut to music. Built in Remotion inside (or beside) the product's codebase, so it reuses real components and stays editable.

Non-negotiables

  • Their design wins. Every rule comes from the product: its tokens, components, rules files, landing page and copy. Never carry another product's taste in, including anything in this skill that their design contradicts.
  • Ask, don't assume. What the film shows and how it is made are the user's call. Interview them before writing the story (reference/interview.md). Offer options drawn from what you found in their code, never generic ones.
  • Every frame is a pure function of time. No CSS transitions or keyframes, no timers, no Date.now(), no state carried between frames. A component that runs its own clock gets a frame-driven twin.
  • Measure, never guess. Beats come from the audio, positions from the DOM (debug overlay), colors from decoded pixels of the final files.
  • Honest claims. Show only what the product really does. Find its claims rules and approved lines before writing a word.
  • Ask first before committing, pushing or publishing. Keep every rendered version (out/<film>/v1, v2, ...).

Workflow

  1. Quick discovery. Just enough to ask good questions: rules files, tokens, components, the logo (and any mascot or animated mark), the landing page, the main features. See reference/discovery.md.
  2. Interview. Two rounds of AskUserQuestion: the brief, then the ingredients. A third round only if needed. See reference/interview.md.
  3. Brand kit → videos/BRAND.md. Finish discovery on what they chose and fill templates/BRAND.md.
  4. Story → videos/<film>-prompt.md. Read reference/story.md and reference/ingredients.md, then fill templates/film-prompt.md. Checkpoint with the user: beat sheet and 3 style frames.
  5. Music. Skip if the film is silent. See reference/music.md: scripts/beats.py, the per-bar stem map, scripts/audio-edit.py, SFX on measured peaks.
  6. Engine and scenes. Read reference/engine.md.
    • Copy templates/kit/ into videos/src/kit/.
    • One folder per film: cues.ts (the beat sheet as data), layout.ts, acts/, the composition.
  7. Review loop. See reference/review.md.
    • Stills at every handoff (scripts/stills.ts, --debug to measure).
    • Contact and handoff sheets, then a half-res draft.
    • Fix, repeat, and show the user frames as you go.
  8. Final render, verify, deliver. See reference/render.md: scripts/render.ts, then scripts/verify.py, then send the files.

Quality floor (always, whatever the ingredients)

  • Only the product's own surfaces, colors, borders and shades. Never invent card backgrounds, outlines or tints it does not use.
  • Readable at the delivery size. Fewer words beat smaller words. Cut labels that restate the picture.
  • Text is never covered by a cursor, a chip or a texture. It never crosses other text in a move. A line never re-centers while it builds: keep every word's slot.
  • Loading states keep their width. Use the product's own loading pattern.
  • Something happens on every beat. A bar where nothing moves reads as slow.
  • Scene boundaries land on bars. A loop's last frame equals its first. A landing loop must read muted.
  • No effects the product's language does not use: glows, particles, click rings, bouncy easing, shaders.

Traps that cost real time

  • Remotion stills do not forward console logs. Print measurements into the frame (templates/kit/debug.tsx).
  • npx remotion still re-bundles on every call. Use scripts/stills.ts: bundle once, render many frames.
  • Remotion's bundled ffmpeg has no tmix, select or tile. Use a full ffmpeg (uv run --with imageio-ffmpeg).
  • Color range: the Remotion master is limited range, BT.601, untagged. Blending it as full range lifts #0a0a0a to #171717, a gray box on a dark page. Decode frame 0 of every deliverable and check the numbers.
  • interpolateColors cannot parse color-mix(). Any color that animates is a hex token.
  • Async image components (Radix or base-ui avatars) can render empty in a frame. Twin them with Remotion <Img>.
  • Springs that retarget: sum one closed-form step per key, with keys sorted by time.
  • CSS dashed borders crawl while a box resizes. Draw dashes as SVG strokes at a fixed pitch.
  • WebGL or shader effects on their own clock paint a different picture each run. Prefer textures painted per frame.
  • In a monorepo:
    • pin every remotion and @remotion/* to one exact version
    • never let the video workspace re-resolve the app's Tailwind
    • alias the app's path imports in the webpack override
  • Stop only the processes you started; other sessions may be waiting on the machine.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Product Film AI skill do?

Make a showreel-grade product film (landing-page loop, launch video, promo, demo reel, social cut) in code with Remotion, built on the product's own design system, components and voice. Use when someone asks for a product video, landing video, promo, launch film, explainer or "motion design video" for their app, SaaS or codebase. It asks what to include, then covers design discovery, story, music sync, transitions, review loops and a verified final render.

Why use Product Film on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Rieranthony/product-film-skill/tree/main/plugins/product-film/skills/product-film. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Product Film?

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 Film?

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

Is the Product Film AI skill free?

Yes. It is published on GitHub by Rieranthony 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 👇