TypingMindTypingMindThe best frontend for AI
Images Media logo

Images Media

Community
flitzrrr
images-media

Image strategy, visual concepts, technical optimization, SVG, icons, lazy loading, and the strategic use of images and media in web design.

Overview

Publisherflitzrrr
Repositoryfrontend-design-skills
Skill nameimages-media
Stars
9
Forks
2
Bundled files
Instructions only
LicenseMIT
Links
Skill sourceRepository
  • 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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Images Media 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/flitzrrr/frontend-design-skills/tree/main/skills-src/images-media
  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/flitzrrr/frontend-design-skills.git /tmp/frontend-design-skills
mkdir -p .claude/skills
cp -r /tmp/frontend-design-skills/skills-src/images-media .claude/skills/images-media
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Images Media 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 Images Media 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 Images Media 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.

Images and Media

Every image must serve a purpose — convey information, evoke emotion, provide orientation, or strengthen the brand. Images without purpose are dead weight.

Scope

Use this skill when you:

  • Develop an image strategy for a website
  • Design hero sections or image galleries
  • Optimize images technically (formats, compression, srcset)
  • Use icons and SVGs or build an icon system
  • Write or review alt texts
  • Make decisions between stock photos and custom imagery

Principles

1. Images Are Content, Not Decoration

Every image serves a purpose. Images without purpose are dead weight and slow down the page.

2. Quality Over Quantity

A few high-quality, authentic images are more impactful than many generic stock photos.

3. Image Strategy Before Image Selection

Define the visual concept first (style, mood, color palette), then select images.

4. Performance Is Non-Negotiable

Images account for 50-70% of page weight. Optimization delivers the greatest performance gains.

5. Authenticity Over Perfection

Real people in real situations are more convincing than staged stock photo scenes.

Rules

DO: Develop an Image Strategy

  • DEFINE a visual concept before selecting images.
  • ESTABLISH target audience, desired emotion, and brand image as selection criteria.
  • SELECT images with a consistent style (color palette, cropping, lighting).
  • ENSURE continuity: maintain a consistent visual language across the entire website.

DO: Use Images Functionally

Every image serves at least one of these four functions:

  • Layout element: Header images, backgrounds, patterns for mood.
  • Orientation element: Anchors for new sections, breaking up text-heavy areas.
  • Content element: Visualization of complex topics, product photos.
  • Emotional element: Brand building, mood creation, recognition.

DO: Show People

  • USE authentic people in real situations.
  • AVOID staged, obviously posed scenes.
  • SHOW diversity in age, gender, and ethnicity where contextually appropriate.

DO: Optimize Images Technically

  • COMPRESS in WebP (standard) or AVIF (progressive).
  • DELIVER via srcset at least 3 variants (400px, 800px, 1200px).
  • USE picture for art direction (different crops per viewport).
  • SET width and height attributes to prevent CLS.
  • IMPLEMENT loading="lazy" below the fold.
  • KEEP file sizes under 200KB (hero max. 400KB).

DO: Write Meaningful Alt Texts

  • DESCRIBE the image content precisely for screen readers and SEO.
  • AVOID starting with "Image of..."
  • SET alt="" only for purely decorative images.
  • USE descriptive file names (team-meeting-office.webp instead of IMG_4523.webp).

DO: Use Icons Consistently

  • ALWAYS combine icons with text labels.
  • USE a consistent icon set across the entire website.
  • PREFER SVG icons for sharpness and small file size.

DO: Prefer SVGs

  • USE SVG for logos, icons, illustrations, and simple graphics.
  • INLINE SVGs for interactivity (hover color changes, animation).
  • USE SVG sprites for frequently used icons.

DON'T: Use Generic Stock Photos

  • AVOID cliche images (smiling business people, handshakes, light bulbs).
  • INVEST in custom photo shoots or curated premium stock sources with consistent editing.

DON'T: Embed Unoptimized Images

  • DO NOT serve images at original resolution.
  • DO NOT use JPEG/PNG when WebP/AVIF is available.
  • DO NOT lazy-load hero images and logos (they must load immediately).

DON'T: Place Text in Images Without a Fallback

  • DO NOT embed important text information exclusively in images.
  • Text in images is not accessible, not searchable, and not responsive.

Patterns

Hero Image with Overlay

On homepages and landing pages: large-scale image with a semi-transparent overlay for text readability. Headline, subline, and CTA on top. No lazy loading for the hero.

Image Gallery / Project Showcase

Uniform grid with consistent aspect ratios (16:9 or 4:3). Hover effect with additional info. Lightbox for detail view. Lazy loading below the fold.

Image Cards

Card with image (upper half), title, excerpt, and CTA (lower half). Consistent aspect ratio. object-fit: cover for uniform rendering.

Responsive Image with Art Direction

picture element with different source elements. Mobile: tight portrait crop. Desktop: full landscape crop. For code examples, see references/responsive-images.md.

Icon System

For 10+ icons: consistent set (line style or filled, not mixed). SVG sprite for performance. Uniform size (e.g., 24px baseline). Icons always with text label or aria-label.

Anti-Patterns

Stock Photo Monotony

All images from the same platform, generic and interchangeable. Users recognize stock photos immediately. Solution: Custom photos or curated premium stock photos with consistent editing.

Massive Unoptimized Images

Original camera photos (3-10MB) embedded directly. Solution: Build pipeline with automatic compression, resizing, and format conversion.

Decorative Image Overload

Too many images with no informational value. Solution: Every image must pass the "What for?" test. White space is often more effective.

Missing Alt Texts

Images without an alt attribute or with "image1.jpg". Accessibility violation and SEO disadvantage. Solution: Descriptive alt texts for content images, alt="" for decorative ones.

Inconsistent Visual Language

Photos with different styles and quality levels mixed together. Solution: Image strategy with a defined color treatment, style, and quality standard.

Checklist

Strategy

  • Image strategy with style, mood, and color palette defined
  • Visual language consistent across all pages
  • Every image serves at least one function
  • Generic stock photos avoided

Technical Optimization

  • WebP or AVIF as primary format
  • srcset with at least 3 sizes
  • loading="lazy" below the fold
  • Hero image without lazy loading
  • width and height attributes set
  • Files under 200KB (hero max. 400KB)
  • SVG for logos, icons, illustrations

Accessibility

  • Alt texts for all content images
  • alt="" for purely decorative images
  • No important text exclusively in images
  • Sufficient contrast for text on images

Legal

  • Usage rights and licenses verified
  • Image credits properly attributed

Cross-References

  • responsive-design -- Responsive images, srcset, picture element
  • ui-design -- Visual hierarchy and image placement
  • branding-identity -- Visual language as part of brand identity
  • accessibility -- Alt texts, contrast, text in images
  • color-theory -- Image color palette in context of the color concept

Frequently asked questions

What does the Images Media AI skill do?

Image strategy, visual concepts, technical optimization, SVG, icons, lazy loading, and the strategic use of images and media in web design.

Why use Images Media on TypingMind?

Because you install it once and use it with any model. Images Media 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 Images Media in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/flitzrrr/frontend-design-skills/tree/main/skills-src/images-media. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Images Media?

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 Images Media?

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

Is the Images Media AI skill free?

Yes. It is published on GitHub by flitzrrr 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.

Related AI Skills

View all
affaan-m logo

Api Design

affaan-m
CommunityPopular

Patrones de diseño REST API incluyendo nomenclatura de recursos, códigos de estado, paginación, filtrado, respuestas de error, versionado y rate limiting para APIs de producción.

39.1K
261.1K
Instructions
View
affaan-m logo

Accessibility

affaan-m
CommunityPopular

WCAG 2.2 レベル AA 標準を用いてインクルーシブなデジタルプロダクトを設計・実装・監査します。Web 用のセマンティック ARIA および Web・ネイティブプラットフォーム（iOS/Android）のアクセシビリティトレイトを生成するために使用します。

39.1K
261.1K
Instructions
View
NousResearch logo

Archify

NousResearch
OrganizationPopular

Validated interactive HTML diagrams, upstream-maintained.

53.5K
250.4K
Instructions
View
NousResearch logo

Auteur

NousResearch
OrganizationPopular

Design and build cinematic, award-level web pages.

53.5K
250.4K
25 files
View

Set up your own AI workspace now

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