Select Text, Then Act — effect skill for cursors & clicks

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/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://varg.ai/how-to/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

The arrow becomes an I-beam, drags a selection across a phrase, and a menu or AI action appears on it.

What it does

Built on Text Select Cursor by HeyGen (HyperFrames), Apache-2.0. The write-up and recipes below are varg's.

Selection grows character by character in the accent color; a small popover ("Rewrite", "Explain") blooms at the selection end.

When: Writing tools, AI editors, docs and code review features.

Watch out: Do not select a whole paragraph instantly; the drag is what makes it believable.

Timing: Drag 0.5–0.8 s, popover 0.2 s scale from 0.9, choose + apply 0.6 s.

Also called: text selection, highlight and rewrite, context menu

In HyperFrames

npx hyperframes add cursor-text-select
npx hyperframes add cursor-context-menu

In Remotion

const n = Math.floor(interpolate(frame,[0,18],[0,phrase.length],{extrapolateRight:'clamp'}));
<mark style={{background:'#93C5FD'}}>{phrase.slice(0,n)}</mark>{phrase.slice(n)}

In CapCut

Record it for real; zoom 160% on the selection; add a pop SFX when the menu appears.

Ready-made components

Where this comes from

Use when

Not for

Install

Example output

https://s3.varg.ai/how-to/previews/aee37c1d18a8/take-select-text-then-act.mp4 — The Text Select Cursor component rendered as installed (npx hyperframes add cursor-text-select), defaults only (credit: Rendered by varg · HyperFrames Text Select Cursor, https://hyperframes.heygen.com/catalog/components/cursor-text-select)

More cursors & clicks skills

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.