App Promo Materials logo

App Promo Materials

Organization
glifxyz
app-promo-materials

Plan and make launch, store, ad and campaign graphics with Glif: real app screens turned into store listings and launch posts, or a coordinated set of product photos, ads, a short video and a jingle for any product. Use when: "App Store screenshots", "Play Store feature graphic", "launch graphics", "Product Hunt images", "social posts for the launch", "carousel", "promo banner", "static ad", "Meta ads", "ad creatives", "ad concepts", "angles to test", "UGC-style ads", "turn these reviews into ads", "product photos for my shop", "Amazon or Shopify listing images", "lifestyle shots of this product", "social media calendar", "a week of posts", "launch campaign", "poster series", "mood board", "storyboard this ad", "resize this ad for every format", "headline variations", "YouTube thumbnail", "X header", "email header". NOT for: logos and icons (use app-icons-and-logos), images inside the site or OG images (use web-visuals), demo videos (use app-demo-videos), one-off edits (use edit-images).

Overview

Publisherglifxyz
Repositoryglif-mcp-server
Skill nameapp-promo-materials
Stars
215
Forks
32
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 glifxyz on GitHub. Read the source before you install it.

Installation

Install the App Promo Materials 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.
    https://github.com/glifxyz/glif-mcp-server/tree/main/skills/app-promo-materials
  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/glifxyz/glif-mcp-server.git /tmp/glif-mcp-server
mkdir -p .claude/skills
cp -r /tmp/glif-mcp-server/skills/app-promo-materials .claude/skills/app-promo-materials
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable App Promo Materials 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 App Promo Materials 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 App Promo Materials 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.

Turn a product into polished promo graphics. For an app, that means real screens. For anything else, it means the user's product photos and references. The user's explicit instructions come first, within host safety rules.

1. Pick the deliverables

Pin down the subject, audience, mood, formats and any references. Ask only about gaps that would change the result. Then pick deliverables from these menus, or the user's own list.

Store and launch sizes:

DeliverableSize (px)
iPhone App Store screenshots1320×2868 or 1290×2796, portrait
iPad App Store screenshots2064×2752, portrait
Google Play feature graphic1024×500
Product Hunt gallery1270×760
YouTube thumbnail1280×720
X post1600×900
LinkedIn post1200×627
Square post1080×1080
Feed post or carousel card (4:5)1080×1350, 3 to 6 cards
Story or Reel cover (9:16)1080×1920
X header1500×500

Store rules change. Check App Store Connect and Play Console for the sizes they currently require. App Store screenshots must be PNG or JPEG with no transparency.

Campaign sets:

  • Ad creative: UGC-style creator video (9:16, script, captions), product ad video, carousel (3 to 6 cards), static banners, unboxing.
  • Product photos: studio hero on white, flat-lay, lifestyle scene, multi-angle set, detail close-up, what's in the box. Ask how many (2, 4 or 8) and keep the product identical to the user's photo.
  • Social calendar: a week or a month of posts with captions and hashtags.
  • Series: a repeatable format, such as a daily 40-second short. Save the recipe so each episode continues the same project.

Make the winner first, then resize it for each placement without cropping.

2. Gather real material

Promo graphics must show the real product. Don't invent screens, features, reviews, awards, press logos or partner logos. Turning real reviews into ads is fine when the user supplies them.

  • Use the user's screenshots and product photos if they have them.
  • For an app without screenshots, run it and capture screens with Playwright at the device size. For a 1320×2868 iPhone shot, use a 440×956 viewport with deviceScaleFactor: 3.
  • Use demo data. Never capture real customer data, emails or keys.

Upload each screen, product photo and the logo with upload_file (with shell access, pass filename and run the returned command), only when the user agrees to send them to Glif. In the brief, say: "Place the uploaded logo and screenshots exactly. Don't redraw them."

3. Write the copy and angles

Draft the angles in text first; that's free. Write one short headline per graphic, 2 to 6 words, about a benefit the screen or product really shows. For ads, write 3 to 5 headline options so the user can test them. Offer about 4 variants per piece, not dozens, unless the user asks. For video, offer a storyboard of stills before animating.

Show the copy before generating. Check names and claims against the code, README or product page. Thumbnails need one honest hook that matches the video, readable at about 120 px wide.

4. Settle the look, then make the set

A request for these graphics is approval to spend credits. If the user only asked to plan or preview, show the draft and wait. Do not ask again after a clear request.

  1. If there's no settled style yet, ask Glif for 2 or 3 layout directions on one hero graphic, such as the first App Store screenshot or the lead ad. The user picks.
  2. Continue the same project (project_id) and make the full set in that style, in one compose_project call. For each graphic, give:
    • filename, exact pixel size and the attached screen or photo it uses
    • the exact headline text, in quotes
    • layout: device frame or floating screen, headline position, background
    • shared style: brand colors (hex), fonts or mood

For a video or audio item in the set, such as a UGC clip or a jingle, write its brief in the same call the way the audio-and-video skill does: shots with camera and action, the exact script in quotes, or music mood, tempo and length. Download those results with the same curl step and check them with ffprobe.

Describe creative goals; Glif picks the models. Leave intelligence unset unless the user asks for lite, smart or genius. Ask Glif to report each output's size.

Useful follow-ups in the same project:

  • Resize: "Recompose this finished graphic for every size in the list. Don't crop the product or the text."
  • Headline variants: the same visual with each headline option.
  • Animated version: a short MP4 loop of a social card.
  • Reference layout: the user supplies an ad they like. Copy its structure only, never another brand's assets, logos or footage.

Share the projectUrl. Follow each run with get_job_status, passing the jobId as job_id. Show new media as it arrives without repeats. A pending status is not a reason to run again, and never retry a failure on your own.

5. Check and save

Download into a folder outside the shipped site, such as marketing/, with curl -fsSL "<media url>" -o <path>. Use one folder per channel, like marketing/app-store/01-home.png.

Check every file:

  • exact pixel size (file, sips -g pixelWidth -g pixelHeight or magick identify)
  • spelling of every headline, letter by letter
  • the screen or product inside matches the real thing, and the logo is unchanged
  • App Store files have no alpha channel. Flatten them locally if needed.

If a headline is misspelled or a screen got redrawn, ask Glif to fix that one file in the same project. Or set the text locally: build a small HTML page with the Glif background, the real screenshot and the headline, then screenshot it with Playwright at the exact size.

List what you made and where it is. Uploading to stores or posting is the user's call.

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 App Promo Materials AI skill do?

Plan and make launch, store, ad and campaign graphics with Glif: real app screens turned into store listings and launch posts, or a coordinated set of product photos, ads, a short video and a jingle for any product. Use when: "App Store screenshots", "Play Store feature graphic", "launch graphics", "Product Hunt images", "social posts for the launch", "carousel", "promo banner", "static ad", "Meta ads", "ad creatives", "ad concepts", "angles to test", "UGC-style ads", "turn these reviews into ads", "product photos for my shop", "Amazon or Shopify listing images", "lifestyle shots of this pr...

Why use App Promo Materials on TypingMind?

Because you install it once and use it with any model. App Promo Materials 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 App Promo Materials in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glifxyz/glif-mcp-server/tree/main/skills/app-promo-materials. 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 App Promo Materials?

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 App Promo Materials?

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

Is the App Promo Materials AI skill free?

Yes. It is published on GitHub by glifxyz 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 👇