- Home
- Skills
- Mobile Development
- Storefront Shots
Works with the AI Agents you already use
Storefront Shots
Turn a folder of raw app screenshots into every required App Store and Google Play asset, for every locale, in one command.
$14.99
Storefront Shots
Example session with this skill installed
I have raw pngs in /assets/raw. Generate screenshots for my app "FocusFlow" with the tagline "Deep work, simplified" in English and Arabic. Use the clean style and target all iPhone sizes.
- Read your context and instructions
- Compiled the storefront shots
I have configured the build for FocusFlow. I created config.json with your brand assets and identified 5 base images. Since Arabic was requested, I have initialized a string table at strings/ar.json with machine-translated drafts for your review.
Screenshot Generation Results
| Target | Locale | Status | Notes |
|---|---|---|---|
| iPhone 6.9 | en | PASS | 5 assets generated |
| iPhone 6.9 | ar | PASS | RTL layout applied; check contact sheet |
| iPhone 6.5 | en | PASS | 5 assets generated |
| iPhone 6.5 | ar | PASS | RTL layout applied |
| Play Feature | en | PASS | 1024x500 generated |
| Preflight | - | WARN | ar locale contains 6 machine_translated flags |
Preflight Summary
The renderer completed successfully. All assets meet the 1290x2796 and 1284x2778 requirements. Text contrast ratios exceed 4.5:1. Note that the Arabic tagline was machine-translated; these files are flagged as MACHINE_TRANSLATED in the manifest and should be reviewed in output/contact-sheets/ar.png.
Next steps
- Review the Arabic layouts in
output/contact-sheets/ar.pngto ensure RTL text shaping is correct. - Update
strings/ar.jsonby moving reviewed keys to the_reviewedarray. - Run the generate script again to clear the preflight flags for final submission.
Connects securely to your tools. The creator never sees your data.
About this skill
Give it real screenshots, an app name, a tagline, captions, and locales. Get iPhone, iPad, and Android sizes, localized overlay text and captions with right to left support, validation against current store specs, and output organized per locale, with contact sheets and a preflight report. Change a tagline, rerun, and the whole set rebuilds.
Why it matters Preparing a release by hand means resizing, retyping, and rechecking the same screenshots for every size and every language, and a rejected asset delays the release. This skill does the mechanical set in one command, then checks it before you upload.
What it does
- Generates required sizes from base images: iPhone 6.9 inch, iPhone 6.5 inch, iPad 13 inch, Android phone, and Play feature graphic.
- Applies localized overlay text and captions, with right to left shaping for Arabic, Hebrew, Persian, and Urdu, and brand names kept in left to right order.
- Validates every asset in preflight: readable file, correct format, exact dimensions or accepted alternate, RGB with no alpha, no text overflow, contrast passes, no machine translated or fallback or missing glyph flags, and asset counts within store limits.
- Organizes output per locale, with contact sheets, a diff against the previous run, a preflight report and JSON, a manifest, and a changes list.
- Rebuilds the whole set after a tagline or caption change, keeping the previous output for comparison.
Requirements Python 3.9 or newer, Pillow installed, optional fonttools for glyph coverage checks. Arabic and Hebrew need Pillow built with libraqm, standard wheels include it. No network access is needed to render.
Honest limits
- Version 1 needs screenshots supplied by you. It does not generate app imagery, and it does not composite screenshots you do not have.
- Store specs are dated in references/store-specs.md. If the spec version is older than 90 days, the skill warns before rendering, and you should confirm against the official Apple and Google docs before a major release.
- Upscaling is capped at 110 percent. A source that is too small renders smaller than its slot, with a warning in the report.
- Text that does not fit even at the minimum size fails preflight with the overflow percentage, instead of being clipped.
- Machine translated strings are flagged and fail preflight until a native reviewer confirms them. Missing strings fall back to the base language, flagged, and failing until supplied. Nothing is shipped silently as if translated.
- Mixed orientations must be run as separate portrait and landscape sets.
- A corrupt image is skipped and reported, the rest of the set still builds.
Example prompt Generate App Store and Google Play screenshots from my screenshots folder, for English, Spanish, German, Japanese, and Arabic, with this app name, tagline, and captions. Check preflight before I upload.
What is in the package SKILL.md, LICENSE, references including store specs and typography rules, templates, samples, and Python scripts for generation, localization, and preflight.
Requires source screenshots. No device frames. Upscaling capped at 110%. Orientation mixing not supported. Fonts are not bundled. Machine translations require manual native review.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 23 days ago