shared-product-motion-video

shared-product-motion-video is a skill for Claude Code, Codex from Desquared/agents-rules-skills. It costs 180 tokens per session (2,706 once invoked), scanned A, original, MIT.

A production guide and workflow for making short product marketing or tutorial videos in a specific Desquared visual style. It covers storyboards, real product screens, cursor interactions, hand-drawn annotations, sound, and MP4 output.

In plain words
What is it for?
Use it to make launch promos, teasers, explainers, and step-by-step feature tutorials using the real product interface.
Why use it?
It gives a coding agent concrete constraints for turning a product or feature into a consistent promo or screen-based lesson instead of an improvised video.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to make launch promos, teasers, explainers, and step-by-step feature tutorials using the real product interface.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/desquared/agents-rules-skills/shared-product-motion-video
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Desquared/agents-rules-skills --skill shared-product-motion-video
Clone the repo
git clone --depth 1 https://github.com/Desquared/agents-rules-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for shared-product-motion-video

README.md
[![agentmods](https://agentmods.dev/badge/skills/desquared/agents-rules-skills/shared-product-motion-video/github.svg)](https://agentmods.dev/skills/desquared/agents-rules-skills/shared-product-motion-video)
Your own site
<a href="https://agentmods.dev/skills/desquared/agents-rules-skills/shared-product-motion-video"><img src="https://agentmods.dev/badge/skills/desquared/agents-rules-skills/shared-product-motion-video/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for shared-product-motion-video

Your own site · 80×15
<a href="https://agentmods.dev/skills/desquared/agents-rules-skills/shared-product-motion-video"><img src="https://agentmods.dev/badge/skills/desquared/agents-rules-skills/shared-product-motion-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 180 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,706 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00180 $0.02706
Opus 5.5 $0.00072 $0.01082
Sonnet 5.5 $0.00036 $0.00541
Haiku 4.5 $0.00018 $0.00271

Measured 17d ago against content hash 733b3a778431, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

shared-product-motion-video scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 17d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (assets/starter-kit/scripts/fetch-fonts.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/shared-product-motion-video/SKILL.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Product motion video (house style)

Produce short product films that look like a person annotating the real product on a warm notebook page: off-white paper with a faint dot grid, heavy black headlines that pop in word by word, pastel highlighter tags, pen marks that draw themselves around the thing that matters, the product's real UI inside device frames and desktop windows, a cursor that visibly clicks, and a quiet synthesised soundtrack whose clicks and chimes land on the frame.

Two formats:

  • Promo: at most 40 s, sells one idea through a hook, a brand lockup, one proof per scene, an outcome and an end card.
  • Tutorial: 50 to 120 s, teaches one task in numbered steps on real footage, no voice.

The style was extracted from three shipped Desquared films (a 40 s promo and two tutorials of 51 s and 57 s). Every number in this skill comes from their source code, not from taste.

Non-negotiables

  1. Real product UI only. Render it from code or capture it clean (references/capture.md). Never a mock-up, a redraw or lorem ipsum. Every number on screen is computed from the product.
  2. Everything is a function of time. Each frame is computed from t through a window and a named easing curve, so any still can be rendered on its own. Check stills before rendering the film.
  3. One timing source for picture and sound. A sound is declared next to the picture it belongs to, in the same scene-local time, never typed a second time.
  4. The film works muted. Captions carry the story; there is no voiceover by default.
  5. Nothing paid by default. Music and effects are synthesised; fonts are open licence. Ask before adding any paid text-to-speech, stock music or render service.

The style in one screen

Full values and rationale: references/house-style.md (look), references/motion.md (motion, pacing, cursor), references/sound.md (sound).

Area Rule
Canvas 1920 x 1080, 30 fps. Laid out on a 960 x 540 dp page at density 2 (1 dp = 2 px)
Paper #FBFAF7; dots #E3E1DB, radius 0.9 dp, every 24 dp, drifting 3 dp/s
Ink text #191919, body #6F6E69, faint #A5A39E, hairline #E6E4DF, cards white
Highlighters yellow #FBE7A1, blue #D6E8F5, green #DDEEDC, pink #F7DDE6, purple #E9E1F5, orange #FBE3CF: one per section tag, rotating by scene
UI inks #2F6FDE selection, focus, ripples; #2E8B57 ticks and success
Brand colour only the app icon and at most one accent
Type Display (Inter Display, or SF Pro Display) Black/Bold, tracking -0.02em, line 1.06; Text (Inter) line 1.4; one word per scene in italic serif (Newsreader); mono (JetBrains Mono) for tags, paths and code
Sizes (sp) hook 66 to 74 Black; wordmark 70; tutorial title 62; caption title 36 to 40 Bold; detail 15; note 16 italic; tags 11 mono; nothing to read under 11
Grid margin 60 dp; caption column x 60, y 150, 300 wide; product area x 372, 560 wide; step dots at y 24 right-aligned to 936
Entrances rise 18 dp + fade over 0.4 to 0.6 s, easeOutCubic; words 0.5 s each, 0.09 s apart, easeOutBack 1.4
Landings cards, phones, chips pop with easeOutBack 1.8 to 2 over 0.5 to 0.55 s, siblings 0.12 to 0.28 s apart
Moves camera and cursor on easeInOutCubic; camera 1 to 1.6 s per key, max zoom 2.6x; cursor 0.4 to 0.6 s per hop
State changes damped spring bump from 0.86 to 0.9 up to 1 (damping 7, frequency 2.2 to 2.4)
Scene change the only transition: 0.3 s overlap, outgoing fades over 0.35 s (easeInCubic) while lifting 16 dp, with a whoosh
Click 0.3 s: cursor shrinks 12%, blue ripple 6 to 24 dp, the button dips 6 to 8%, click sound, then a 0.6 s rest
Typing 0.045 s/char in forms, 0.038 in a hero prompt, 0.032 in an assistant; block caret blinking at 1 Hz; one key tick per character
Doodles round-capped ink pen strokes 2.2 to 2.8 dp (strike 5 dp) that draw on: strike, underline, loop, arrow, sparkle, tick, star, yellow marker sweep. Two or three per scene, each aimed at a measured word or UI element, each with a scribble sound
Pacing promo scenes 3.6 to 5.6 s, tutorial steps 6.5 to 13 s; one idea per scene; every final state holds still at least 0.8 s
Sound 112 BPM maj9 bed with a groove for promos, 96 BPM calm bed for tutorials; whoosh, click, pop, key tick, scribble, chime on the picture; soft clip, -1 dBFS peak, aim -16 LUFS

Read the full file on GitHub · 130 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 17d ago First seen · 130 lines · 180 tokens per session scan A 733b3a778431

Subscribe to this mod's changes

shared-product-motion-video is a skill published in the GitHub repository Desquared/agents-rules-skills (4 stars, last pushed 13d ago), licensed MIT. It adds 180 tokens to every session and 2,706 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-30.

Related

Other skills, from other repositories

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens