# Star Rating Sweep — effect skill for quotes & reviews

> **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.

Five stars fill left to right to the real score while the number counts up beside them.

- **Type:** [Effect](https://varg.ai/how-to/effects.md) · [Quotes & reviews](https://varg.ai/how-to/browse/skills/quotes.md)
- **Slug:** `star-rating-sweep`
- **Status:** live
- **Publisher:** HeyGen (community)
- **License:** Apache-2.0
- **Source:** https://github.com/heygen-com/hyperframes/tree/main/registry/components/star-rating-fill
- **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 [Star Rating Fill](https://github.com/heygen-com/hyperframes/tree/main/registry/components/star-rating-fill) by HeyGen (HyperFrames), Apache-2.0. The write-up and recipes below are varg's.

A row of outline stars; the fill layer sweeps to 4.8 and keeps the partial last star; "4.8 · 2,300 reviews" beside it.

**When:** App and marketplace products; end of a testimonial run; pricing scenes.

**Watch out:** Do not round up to a perfect 5.0; buyers distrust it and purchase likelihood peaks around 4.2–4.5.

**Timing:** Sweep 0.8–1.0 s, power2.out; number counts in the same window; hold 1.5 s.

**Also called:** rating stars, review score, app store rating

### In HyperFrames

```bash
npx hyperframes add star-rating-fill
```
Set `data-variable-values='{"rating":4.8,"count":"2,300 reviews"}'`; the fractional star is preserved.

### In Remotion

```tsx
const r = interpolate(frame,[0,24],[0,4.8],{extrapolateRight:'clamp',easing:Easing.out(Easing.cubic)});
<div style={{width:`${r/5*100}%`, overflow:'hidden'}}>★★★★★</div>
```

### In CapCut

Stickers → search "5 stars"; reveal with Mask → Linear keyframed left to right; add a Text counter manually per frame or use a counter text template.

### Ready-made components

- [Star Rating Fill](https://skills.varg.ai/component/hf.star-rating-fill/) (hyperframes): npx hyperframes add star-rating-fill
- [Social Proof Card](https://skills.varg.ai/component/hf.social-proof-card/) (hyperframes): npx hyperframes add social-proof-card
- [Counter](https://skills.varg.ai/component/animata.counter/) (animata): npx shadcn@latest add https://animata.design/r/text/counter.json

### Where this comes from

- [PowerReviews / Spiegel Research Center: from reviews to revenue](https://www.powerreviews.com/from-reviews-to-revenue/)
- [Retail TouchPoints: purchase likelihood peaks at 4.2–4.5 stars](https://www.retailtouchpoints.com/topics/customer-experience/purchase-likelihood-highest-for-products-rated-between-4-2-and-4-5-out-of-5-stars)

## Use when

- App and marketplace products; end of a testimonial run; pricing scenes.

## Not for

- Do not round up to a perfect 5.0; buyers distrust it and purchase likelihood peaks around 4.2–4.5.

## 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/56bf7c1b5c82/take-star-rating-sweep.mp4 — The Star Rating Fill component rendered as installed (npx hyperframes add star-rating-fill), defaults only (credit: Rendered by varg · HyperFrames Star Rating Fill, https://hyperframes.heygen.com/catalog/components/star-rating-fill)

## More quotes & reviews skills

- [Tweet as Proof Card](https://varg.ai/how-to/skills/tweet-proof-card.md): A real post from a user animates in as a card: avatar, name, text, then counts tick up.
- [Quote at Reading Pace](https://varg.ai/how-to/skills/quote-at-reading-pace.md): One strong customer sentence reveals word by word, then the name, role and avatar settle under it.
- [Wall of Love Marquee](https://varg.ai/how-to/skills/wall-of-love-marquee.md): Two or three rows of review cards drift in opposite directions, fading at the edges.
- [Community Post as Proof](https://varg.ai/how-to/skills/community-post-proof.md): A real community post or comment card pops over the footage with its upvotes counting up.
- [Reviews Arrive as Notifications](https://varg.ai/how-to/skills/reviews-as-notifications.md): Short reviews land as system notifications that stack and push each other down.
- [Pull Quote Beside the Speaker](https://varg.ai/how-to/skills/pull-quote-beside-speaker.md): While a customer talks on camera, their key sentence appears as large type in the empty side of the frame.

## 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