Nodes Wire Up on a Canvas — effect skill for AI agent flows

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.

Nodes pop onto a canvas and connectors draw between them as the camera pulls back to show the whole pipeline.

What it does

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

Rounded nodes with icons and labels; bezier connectors draw from output to input; a pulse travels the finished path.

When: Workflow builders, multi-step AI pipelines, automations.

Watch out: Do not show the whole graph first; build it in narration order, then reveal the full canvas.

Timing: Node pop 0.25 s, connector draw 0.4–0.6 s, pulse 0.8 s per edge; final pull-back 1 s.

Also called: node graph, workflow canvas, pipeline graph

In HyperFrames

npx hyperframes add flowchart

Or constellation-hub for feature nodes brightening in narration order.

In Remotion

const len = path.getTotalLength();
const off = interpolate(frame,[edge.at,edge.at+15],[len,0],{extrapolateLeft:'clamp',extrapolateRight:'clamp'});
<path d={d} strokeDasharray={len} strokeDashoffset={off}/>

In CapCut

Record the real canvas; zoom on each node as it is added, then a long ease-out zoom to 100% for the overview.

Ready-made components

Where this comes from

Use when

Not for

Install

Example output

https://static.heygen.ai/hyperframes-oss/docs/images/catalog/blocks/flowchart.mp4 — Preview of the Flowchart component that builds this take (credit: Flowchart · hyperframes, https://hyperframes.heygen.com/catalog/blocks/flowchart)

More AI agent flows 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.