Store Screenshots
AI agent skill for Claude Code & Codex — turns raw app screenshots into store-ready App Store & Google Play marketing images: device frames (iPhone·iPad·Galaxy·Fold·Flip),…
Install
git clone https://github.com/LeeHueeng/store-screenshotsInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →store-screenshots
Raw app screenshots in → store-ready marketing images out. An AI agent skill for Claude Code & OpenAI Codex that adds device frames, branded backgrounds, and benefit-driven copy — at exact App Store & Google Play sizes.
English · 한국어
Making App Store and Google Play screenshots by hand — opening Figma, hunting for device mockups, double-checking pixel sizes — gets old fast. This skill turns all of that into one request to your coding agent: point it at your raw screenshots (or let it drive your app and capture them itself), answer a few multiple-choice questions, approve the copy, and get a full set of store-ready PNGs.
✨ What it does
- 📱 Device frames — iPhone, iPad, Galaxy, Fold, Flip, drawn in pure CSS (no mockup downloads, no license worries)
- 🎨 Branded backgrounds — extracts your app's real design colors (
colors.xml,.xcassets, app icon); Modern/Minimal, Pop, and Dark presets included - ✍️ Marketing copy — reads each screen and proposes benefit-driven headlines and subcopy, and only proceeds after you approve
- 📐 Exact store sizes — App Store 1320×2868 / 1284×2778, iPad 2064×2752, Google Play 1080×1920, and more — every PNG is pixel-verified
- 🤖 Hands-free capture — no screenshots yet? The agent drives your app itself (adb on Android; deep links, idb, or Maestro on the iOS Simulator) with the status bar unified to 9:41 / 100% battery
🖼️ Example output
App Store iPhone 6.5″ size (1242×2688), generated with the "match my app's design" style
🚀 Install
git clone https://github.com/LeeHueeng/store-screenshots.git
# Claude Code
cp -r store-screenshots/store-screenshots ~/.claude/skills/
# Codex
mkdir -p ~/.agents/skills
cp -r store-screenshots/store-screenshots ~/.agents/skills/
| Agent | All projects | One project only |
|---|---|---|
| Claude Code | ~/.claude/skills/ |
/.claude/skills/ |
| Codex | ~/.agents/skills/ |
<repo root>/.agents/skills/ |
On older Codex versions the skills path may be
~/.codex/skills/.
💬 Usage
In Claude Code:
/store-screenshots ./screenshots
In Codex:
$store-screenshots ./screenshots
(or pick it from /skills)
Or just ask in plain language — "make my App Store screenshots".
How a run goes
- Collect originals — scans your folder for screenshots; if there are none, the agent operates the app itself and captures them.
- Android:
adbtap/screencap · iOS Simulator: deep links (simctl openurl) first, then idb, Maestro, or AppleScript - Status bar unified to 9:41 / 100% battery across every capture
- You never have to touch the device — you only pick options and approve copy
- On a re-run it first asks: reuse existing screenshots, or start fresh?
- Android:
- Questions (all multiple-choice) — platform (App Store / Google Play) → devices (iPhone, iPad, Galaxy, Fold, Flip) → style (match my app / modern-minimal / pop / dark) → how many slides → what to highlight
- Draft approval — a copy table plus one fully rendered first slide at real store size; full rendering starts only after your OK
- Render — frame, background, and copy composed in HTML/CSS, captured with headless Chrome
- Verify — every PNG's pixel size is checked against the store spec table
📦 Output
Similar plugs
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local…
Why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking like a caveman.
Production-grade engineering skills for AI coding agents.