Bento Feature Grid — effect skill for grids & carousels
For AI agents: find the right skill in one call —
curl -s "https://skills.varg.ai/api/search?q=<what the person wants>"returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add.mdto its path. Before generating anything, show the person the options on the how-to page.
Features land in a grid of differently sized rounded tiles — one hero tile, smaller supporting ones.
- Type: Effect · Grids & carousels
- Slug:
bento-feature-grid - Status: live
- Publisher: HeyGen (community)
- License: Apache-2.0
- Source: https://github.com/heygen-com/hyperframes/tree/main/registry/blocks/mk-placeholder-grid
- Works in: Claude Code, Claude.ai, Codex, Cursor, OpenClaw, Gemini CLI, Any MCP client, varg Studio
- Requires: HyperFrames (npx hyperframes), Remotion, CapCut (by hand)
- Cost: Free — the take renders locally; generated footage, if any, bills by the model
What it does
Built on Rounded Media Grid by HeyGen (HyperFrames), Apache-2.0. The write-up and recipes below are varg's.
Apple-style bento: 1 large + 3–5 small tiles, generous gaps, each tile one idea (icon, number or mini UI); tiles assemble in a stagger.
When: Recap of features near the end, or the "everything you get" beat.
Watch out: Do not fill every tile with text; one visual and ≤ 5 words per tile.
Timing: Tiles 0.4–0.5 s each, 60–100 ms stagger hero-first; hold 2–3 s; optional slow camera drift.
Also called: bento, feature tiles, summary grid
In HyperFrames
npx hyperframes add mk-placeholder-grid
Use the hero-plus-two / 3×2 layouts; drop media into slots; tl.from(".cell",{y:30,opacity:0,stagger:0.08}).
In Remotion
<div style={{display:'grid',gridTemplateColumns:'2fr 1fr 1fr',gridTemplateRows:'1fr 1fr',gap:24}}>
{tiles.map((t,i)=>{const s=spring({frame:frame-i*3,fps,config:{damping:200}}); return <Tile style={{opacity:s,transform:`translateY(${(1-s)*30}px)`, gridArea:t.area}}/>})}
</div>
In CapCut
Templates → search "bento"/"grid collage"; or Layout split-screen templates with rounded masks.
Ready-made components
- Rounded Media Grid (hyperframes): npx hyperframes add mk-placeholder-grid
- Grid Card Assemble (hyperframes): npx hyperframes add grid-card-assemble
- Dynamic Grid (hyperframes): npx hyperframes add dynamic-grid
Where this comes from
- SaaSFrame: understanding the bento layout trend
- freeCodeCamp: bento grids in web design
- zero on X: Apple-keynote launch film prompt (Screen Studio zoom, no crossfades)
Use when
- Recap of features near the end, or the "everything you get" beat.
Not for
- Do not fill every tile with text; one visual and ≤ 5 words per tile.
Install
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg - Codex:
npx skills add vargHQ/skills --skill varg-video-edit-library -a codex -y - Cursor:
npx skills add vargHQ/skills --skill varg-video-edit-library -a cursor -y
Example output
https://s3.varg.ai/how-to/previews/5ecf67ae908d/take-bento-feature-grid.mp4 — The Rounded Media Grid component rendered as installed (npx hyperframes add mk-placeholder-grid), defaults only (credit: Rendered by varg · HyperFrames Rounded Media Grid, https://hyperframes.heygen.com/catalog/blocks/mk-placeholder-grid)
More grids & carousels skills
- Camera Drifts Across a Bento: An oversized grid of screenshots fills the frame and the camera drifts diagonally across it.
- Tilted Screenshot Wall: A wall of screenshots seen at an isometric angle, columns scrolling up and down at different speeds.
- Stacked Cards Fan Out: A pile of cards or photos shuffles, then fans or settles one forward into focus.
- App Screens on a Rail: Two to five app screens ride a horizontal rail: one centered and sharp, neighbors smaller and receded.
- Cards Orbit in a Ring: Image cards ride a circle, larger in front and smaller behind, sweeping fast-slow-fast.
- Rapid Screenshot Burst: Full-screen images slam in one on top of another on the beat, landing on the final hero shot.
Run the generation on varg
varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.
- Claude Code:
claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg(skill + hosted MCP) - Codex, Cursor, Gemini CLI, OpenClaw:
npx skills add vargHQ/skills --skill varg-ai -a <agent> -y - Grok and any agent that reads SKILL.md:
npx skills add vargHQ/skills --skill varg-ai, or point it at the skill's SKILL.md - Claude.ai, ChatGPT, any MCP client: connect
https://mcp.varg.ai/mcp - API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt