Vertical Chat Exchange — effect skill for AI agent flows

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 .md to its path. Before generating anything, show the person the options on the how-to page.

A portrait chat plays out: the prompt types and sends, the answer streams and assembles a card or image.

• Type: Effect · AI agent flows
• Slug: vertical-chat-exchange
• Status: live
• Publisher: Jake Moran · HeyGen (community)
• License: Apache-2.0
• Source: https://github.com/heygen-com/hyperframes/tree/main/registry/blocks/chatgpt-exchange
• 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 ChatGPT Exchange by Jake Moran (hyperframes), Apache-2.0. The write-up and recipes below are varg's.

Phone-sized chat UI, bubbles pop with a tiny scale from the sender's corner, typing dots before replies.

When: Vertical cuts for TikTok, Reels and Shorts about AI features.

Watch out: Do not make bubbles readable only at full screen; use 1.5× normal type size for phones.

Timing: Bubble pop 0.12–0.2 s (scale 0.75→1), typing dots 0.6–1 s, gap 0.3 s between messages.

Also called: chat story, ChatGPT exchange, phone chat

In HyperFrames

npx hyperframes add chatgpt-exchange

Or message-thread-reveal / chat-thread for human conversations.

In Remotion

// npx shadcn@latest add @remocn/imessage-chat-flow
// or @remocn/chat-flow / @remocn/telegram-chat-flow

In CapCut

Text → Text templates → "chat"/"message"; one bubble per layer, Animation In "Pop up" 0.15 s.

Ready-made components

• ChatGPT Exchange (hyperframes): npx hyperframes add chatgpt-exchange
• Message Thread Reveal (hyperframes): npx hyperframes add message-thread-reveal
• UI iMessage Chat Flow (remocn): npx shadcn@latest add @remocn/imessage-chat-flow

Where this comes from

• CapCut: turn testimonials into quote graphics for short-form

Use when

• Vertical cuts for TikTok, Reels and Shorts about AI features.

Not for

• Do not make bubbles readable only at full screen; use 1.5× normal type size for phones.

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://static.heygen.ai/hyperframes/templates/promoted/254fe4bd8a3f00c1e70ac5e38a1bce25060f7590/chatgpt-exchange/preview.mp4 — Preview of the ChatGPT Exchange component that builds this take (credit: ChatGPT Exchange · hyperframes, https://hyperframes.heygen.com/catalog/blocks/chatgpt-exchange)

More AI agent flows skills

• Prompt Typed, Then Generate: A real task types into the prompt box, the Generate button is pressed, and the result starts to build.
• Answer Streams In: The assistant's reply arrives in uneven token bursts, the way a real model streams.
• Tool Calls as Status Rows: Each tool call appears as a row with an icon and label that goes spinner → check, building a visible plan.
• Nodes Wire Up on a Canvas: Nodes pop onto a canvas and connectors draw between them as the camera pulls back to show the whole pipeline.
• Beams Into the Agent Hub: Light pulses run along curved lines from tool icons into a central agent and back out to a result.
• Thinking… Shimmer Label: A muted "Thinking…" label with a moving shine shows the model working between prompt and answer.

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