motion-graphics

An agent skill by heygen-com, from heygen-com/hyperframes. Tags: design, generative, slides, social-listening, video.

What it does

A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI animation (scroll, cursor, callouts), or fusing a real image's geometry into a chart. Usually under 10s (up to ~30s), no narration or live-action subject; renders to MP4 or transparent overlay. Longer / narrated / multi-scene → /general-video. Unclear → /hyperframes.

Install

With the skills CLI, which installs into Claude Code, Codex, Cursor and other agents:

npx skills add heygen-com/hyperframes --skill motion-graphics

Or copy the skill folder into Claude Code's skills directory by hand (~/.claude/skills for every project, or .claude/skills inside one):

git clone --depth 1 https://github.com/heygen-com/hyperframes
cp -r hyperframes/skills/motion-graphics ~/.claude/skills/motion-graphics

Safety box score

Grade D, elevated risk: 47 of 100 risk points, rated 2026-10-19. The grade rates what the skill and its scripts can reach on the machine of whoever installs it, across eight categories from shell execution to secrets access. How the score works.

This skill is a local video-production workflow, but it reaches out to external services for search, map tiles, and optional AI-based localization, and it runs several native tools to render assets. The main risks are network exposure of source material, optional API-key use, and a fairly autonomous build process that minimizes intermediate human review.

Category levels, from 0 (none) to 3 (high)
Category	Level	Why
Code & shell execution	2 (moderate)	It runs local commands and native tools throughout the workflow, including `npx hyperframes ...` plus `ffmpeg`, `ffprobe`, and browser automation in `grounding/locate.mjs` and `categories/maps/bake-basemap.mjs`.
Network access	2 (moderate)	It fetches remote dependencies and content, including `https://cdn.jsdelivr.net/...`, ArcGIS/CARTO tiles, and an optional Gemini API call in `grounding/locate.mjs`.
Filesystem reach	1 (low)	Most writes are project-local under `videos/<project-name>/`, but the scripts also touch home-cache/temp paths like `~/.cache/puppeteer/chrome-headless-shell` and `/tmp/locate-font.ttf`.
Secrets & credentials	1 (low)	The skill explicitly supports `GEMINI_API_KEY` / `GOOGLE_API_KEY` and uses `process.env.GEMINI_API_KEY` in `grounding/locate.mjs` for the `auto` path.
Privilege & persistence	2 (moderate)	It tells the user to install system tools with `brew install node ffmpeg` and may install a browser via `npx puppeteer browsers install chrome-headless-shell`.
Instruction hijack surface	2 (moderate)	The workflow pushes strong autonomy and reduced review, e.g. `This workflow is autonomous by design — at most one clarifying question ... build through verification without intermediate review`.
Irreversible actions	1 (low)	It can search, source, and render assets on its own, but it does not directly post, deploy, pay, or delete; the render step is still user-gated.
Transparency	0 (none)	The shipped files are readable markdown and JavaScript; there are no bundled binaries, minified blobs, or decoded-at-runtime code in the skill itself.

Before installing

Read `categories/maps/bake-basemap.mjs` if you plan basemap work; it contacts ArcGIS/CARTO/jsDelivr and writes frames under the chosen output dir.
Leave `GEMINI_API_KEY` unset unless you want the image sent to Gemini via `grounding/locate.mjs auto`.
Confirm `node` and `ffmpeg` are already installed before running the workflow, since the skill expects them system-wide.
If you want a no-network path, avoid the basemap lane and the search-driven `webpage`/`news`/`tweet`/`asset-fusion` routes.

Rated 2026-10-19 by an automated review of 23 files from the skill's repository.

Source

Repository: heygen-com/hyperframes (all skills from this repository)
Path: skills/motion-graphics/SKILL.md
Branch: main
Updated: 2026-09-19

ad-creative — When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text.
faceless-explainer — Turn arbitrary text — an article, notes, a topic, a brief — into a faceless explainer video: there is no site or footage to capture.
general-video — Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces.
hyperframes-creative — Non-animation creative direction for HyperFrames videos.
product-launch-video — Turn a product or marketing URL, pasted script, or brief into a product launch / promo video — SaaS promos, feature reveals, product demos.
talking-head-recut — Package an existing talking-head / interview / podcast video with timed, designed GRAPHIC OVERLAY cards — kinetic titles, lower-thirds, data callouts, quotes.