Gemini Seo Image Assets logo

Gemini Seo Image Assets

Community
Innei
gemini-seo-image-assets

Use when a web project needs Google AI Studio or Gemini-generated favicon and Open Graph images, exported icon variants, and matching SEO metadata wiring.

Overview

PublisherInnei
RepositorySKILL
Skill namegemini-seo-image-assets
Stars
81
Forks
2
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

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

Installation

Install the Gemini Seo Image Assets 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/Innei/SKILL.git /tmp/SKILL
mkdir -p .claude/skills
cp -r /tmp/SKILL/skills/content/gemini-seo-image-assets .claude/skills/gemini-seo-image-assets
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Gemini Seo Image Assets 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 Gemini Seo Image Assets 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 Gemini Seo Image Assets 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.

Gemini SEO Image Assets

Overview

Generate image-first SEO assets with Gemini 3.1, then finish the exact typography, icon sizes, manifest, and metadata locally.

Core rule: let Gemini generate composition and texture; do not rely on Gemini for exact text rendering.

When to Use

  • A site has missing or generic favicon.ico, apple-touch-icon, or og-image.
  • A web app needs route-level title, description, og:*, twitter:*, and canonical wiring.
  • The user explicitly wants Gemini or Google AI Studio involved in the asset creation flow.

Do not use this skill when:

  • The project already has a strict vector logo or brand system that should be edited directly.
  • The task is only to tweak existing metadata strings without generating new raster assets.
  • Exact logotypes or multilingual text must come directly from the model output.

Workflow

1. Inspect the project surface

Confirm these before generating anything:

CheckWhy it matters
Root layout / head entryNeeded for icons, manifest, theme-color, global meta
Route metadata APIDetermines where title, description, robots, and canonical belong
public/ assetsPrevents accidental overwrite and reveals existing filenames
Build commandRequired for verification after wiring

2. Load credentials and choose the model

  • Read .env.local first, then .env.
  • Accept any one of these auth paths (see gemini-image-generation skill for the full _make_client() helper):
    • AI Studio: GOOGLE_AI_STUDIO_API_KEY / GEMINI_API_KEY / GOOGLE_API_KEY
    • Vertex Express: VERTEX_AI_KEY
    • Vertex ADC: GOOGLE_GENAI_USE_VERTEXAI=true + GOOGLE_CLOUD_PROJECT/LOCATION
  • Default model: gemini-3.1-flash-image-preview (same name on both surfaces).
  • If the user asks for a newer or latest Gemini image model, verify the current official name before use.

Minimal request shape:

json
{
  "contents": [{ "parts": [{ "text": "..." }] }],
  "generationConfig": {
    "responseModalities": ["IMAGE"],
    "imageConfig": {
      "aspectRatio": "1:1",
      "imageSize": "2K"
    }
  }
}

Vertex caveat: imageSize is not accepted on Vertex endpoints (raises ValidationError: Extra inputs are not permitted). Omit imageSize when routing through VERTEX_AI_KEY / Vertex ADC; the model returns its default resolution and you post-process to the target exports.

3. Generate two base images

Always generate background/base artwork, not final text-complete share cards.

AssetAspect ratioPurposeRule
Favicon source1:1Master square artwork for all icon exportsNo text, strong silhouette, readable at 16px
OG background16:9Base for 1200x630 social previewReserve calm negative space for local title overlay

Use the prompt templates in references/prompts.md. Adapt the palette, mood, and product nouns to the project.

4. Post-process locally

Do the deterministic steps on the local machine:

  • Crop/fit the favicon master to a square source such as 1024x1024.
  • Export:
    • favicon.ico
    • favicon-16x16.png
    • favicon-32x32.png
    • apple-touch-icon.png
    • android-chrome-192x192.png
    • android-chrome-512x512.png
  • Fit the OG base to 1200x630.
  • Add title, subtitle, tagline, or other exact copy with local drawing tools or code.
  • Prefer local fonts and color tokens from the project instead of asking Gemini to render exact text.

5. Wire SEO metadata

Preferred structure:

LayerResponsibility
Root layouticons, manifest, theme-color, color-scheme, app name
Shared SEO helperbuilds title, description, robots, og:*, twitter:*, canonical
Route modulescall the helper with route-specific values

Recommended rules:

  • Home or marketing entry pages may be index,follow.
  • Quiz, shell, preview, and result routes are usually noindex,nofollow.
  • If the deployment origin is known, use VITE_SITE_URL to produce absolute canonical, og:url, and og:image.
  • If the origin is unknown, keep paths root-relative and let the runtime origin resolve them.

6. Validate before claiming completion

Run all of the following:

VerificationPurpose
Visual self-check or model-based image inspectionConfirms icon has no stray text and OG text is legible
TypecheckConfirms metadata helper and route integration compile
Production buildConfirms asset links and route modules build successfully

Guardrails

RuleReason
Do not trust Gemini for exact Chinese or brand textText rendering is the least reliable part of the model output
Keep favicon imagery simpleBrowser icons collapse under detail very quickly
Keep OG imagery quieter than the UISocial previews need text contrast and scanability
Do not hardcode a production domain in sourceCanonical origin often differs by environment
Do not overwrite user-owned assets blindlyExisting branding may already be in use

Reference Files

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 Gemini Seo Image Assets AI skill do?

Use when a web project needs Google AI Studio or Gemini-generated favicon and Open Graph images, exported icon variants, and matching SEO metadata wiring.

Why use Gemini Seo Image Assets on TypingMind?

Because you install it once and use it with any model. Gemini Seo Image Assets 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 Gemini Seo Image Assets in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Innei/SKILL/tree/main/skills/content/gemini-seo-image-assets. 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 Gemini Seo Image Assets?

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 Gemini Seo Image Assets?

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

Is the Gemini Seo Image Assets AI skill free?

It is published on GitHub by Innei. Check the repository for licensing terms. 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 👇