Gplay Screenshot Automation logo

Gplay Screenshot Automation

Community
hanamizuki
gplay-screenshot-automation

Manage, validate, and upload Google Play listing screenshots and graphics with the gplay CLI. Use when organizing screenshots by locale and device type and pushing them to a Play listing via gplay images upload, sync import-images, or a release.

Overview

Publisherhanamizuki
Repositorysolopreneur
Skill namegplay-screenshot-automation
Stars
150
Forks
9
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by hanamizuki on GitHub. Read the source before you install it.

Installation

Install the Gplay Screenshot Automation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/hanamizuki/solopreneur.git /tmp/solopreneur
mkdir -p .claude/skills
cp -r /tmp/solopreneur/plugins/claude/android-dev/skills/gplay-screenshot-automation .claude/skills/gplay-screenshot-automation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gplay Screenshot Automation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Gplay Screenshot Automation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Gplay Screenshot Automation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Google Play Screenshot Management

Use this skill to organize, validate, and upload Android screenshots and store graphics to a Google Play listing with gplay. This skill covers the gplay-specific upload/validate flow — not screenshot capture.

Capturing the raw images is standard Android tooling and not gplay-specific: take them with adb shell screencap (then adb pull), or drive state-based captures with an Espresso / UI Automator instrumentation test, switching emulator locale via setprop persist.sys.locale when you need per-language shots. Produce PNGs organized by locale and device type, then use the commands below.

Directory layout

gplay expects a Fastlane-style tree. sync import-images and release --screenshots-dir both read this shape:

metadata/
  en-US/
    images/
      phoneScreenshots/
        1_home.png
        2_search.png
      tenInchScreenshots/
        1_home.png
      featureGraphic.png
  de-DE/
    images/
      phoneScreenshots/
        1_home.png

Screenshots upload in filename order, so prefix with 1_, 2_, etc. to control ordering on the store.

Image types

TypeUsage
phoneScreenshotsPhone screenshots (required, 2-8)
sevenInchScreenshots7-inch tablet screenshots
tenInchScreenshots10-inch tablet screenshots
tvScreenshotsAndroid TV screenshots
wearScreenshotsWear OS screenshots
featureGraphicFeature graphic (1024x500)
promoGraphicPromo graphic (180x120)
iconApp icon (512x512)
tvBannerTV banner (1280x720)

Google Play requires PNG or JPEG (PNG recommended), max 8 MB per image.

1) Validate before uploading

Always validate the directory first — this catches count/dimension/format issues before you spend an upload:

bash
# Validate all locales
gplay validate screenshots --dir ./metadata --output table

# Validate a single locale
gplay validate screenshots --dir ./metadata --locale en-US --output table

2) Upload

Option A — bulk import (preferred)

Imports every image in the Fastlane tree in one command. Requires an open edit:

bash
EDIT_ID=$(gplay edits create --package com.example.app | jq -r '.id')

gplay sync import-images \
  --package com.example.app \
  --edit "$EDIT_ID" \
  --dir ./metadata          # add --locale en-US to import one locale, --dry-run to preview

gplay edits validate --package com.example.app --edit "$EDIT_ID"
gplay edits commit   --package com.example.app --edit "$EDIT_ID"

Option B — individual images

Use when you need fine control over specific files:

bash
EDIT_ID=$(gplay edits create --package com.example.app | jq -r '.id')

gplay images upload \
  --package com.example.app \
  --edit "$EDIT_ID" \
  --locale en-US \
  --type phoneScreenshots \
  --file ./metadata/en-US/images/phoneScreenshots/1_home.png

gplay images upload \
  --package com.example.app \
  --edit "$EDIT_ID" \
  --locale en-US \
  --type featureGraphic \
  --file ./metadata/en-US/images/featureGraphic.png

gplay edits validate --package com.example.app --edit "$EDIT_ID"
gplay edits commit   --package com.example.app --edit "$EDIT_ID"

Option C — as part of a release

Upload screenshots alongside a bundle in one release flow:

bash
gplay release \
  --package com.example.app \
  --track production \
  --bundle app-release.aab \
  --screenshots-dir ./metadata \
  --release-notes @release-notes.json

3) Replace existing screenshots

delete-all clears a type for a locale before re-uploading. It defaults --confirm to false and will refuse without it, so --confirm is REQUIRED:

bash
EDIT_ID=$(gplay edits create --package com.example.app | jq -r '.id')

gplay images delete-all \
  --package com.example.app \
  --edit "$EDIT_ID" \
  --locale en-US \
  --type phoneScreenshots \
  --confirm

gplay images upload \
  --package com.example.app \
  --edit "$EDIT_ID" \
  --locale en-US \
  --type phoneScreenshots \
  --file ./metadata/en-US/images/phoneScreenshots/1_home.png

gplay edits validate --package com.example.app --edit "$EDIT_ID"
gplay edits commit   --package com.example.app --edit "$EDIT_ID"

4) Verify what's live

bash
gplay images list \
  --package com.example.app \
  --edit "$EDIT_ID" \
  --locale en-US \
  --type phoneScreenshots \
  --output table

Agent behavior

  • Confirm exact flags with --help before running commands.
  • Always run gplay validate screenshots before uploading.
  • Prefer gplay sync import-images over many individual gplay images upload calls.
  • Every write goes through an edit: create → upload/import → validate → commit.
  • images delete-all needs --confirm; without it the command refuses.
  • Use explicit long flags (--package, --edit, --locale, --type, --file).
  • Default to JSON for machine steps, --output table for human review.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Gplay Screenshot Automation AI skill do?

Manage, validate, and upload Google Play listing screenshots and graphics with the gplay CLI. Use when organizing screenshots by locale and device type and pushing them to a Play listing via gplay images upload, sync import-images, or a release.

Why use Gplay Screenshot Automation on TypingMind?

Because you install it once and use it with any model. Gplay Screenshot Automation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Gplay Screenshot Automation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hanamizuki/solopreneur/tree/main/plugins/claude/android-dev/skills/gplay-screenshot-automation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Gplay Screenshot Automation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Gplay Screenshot Automation?

As many as you like. As long as a model supports skills, you can use Gplay Screenshot Automation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Gplay Screenshot Automation AI skill free?

Yes. It is published on GitHub by hanamizuki under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇