Image

Community

wentorai

image

Image processing workflow guide for format selection, resizing, cropping, compression, metadata, transparency, color profiles, and destination-specific exports. Covers web, social, ecommerce, photography, branding, screenshots, and accessibility.

Overview

Publisher	wentorai
Repository	`Research-Claw`
Skill name	`image`
Stars	859
Forks	117
Bundled files	Instructions only
Links	Skill source Repository

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 wentorai on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/wentorai/Research-Claw/tree/main/skills/image
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.

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/wentorai/Research-Claw.git /tmp/Research-Claw
mkdir -p .claude/skills
cp -r /tmp/Research-Claw/skills/image .claude/skills/image

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image 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 Image 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 Image 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.

Image

Image processing workflow guide for destination-specific exports.

When to Use

Use when the main artifact is an image file or visual asset, especially when:

Format choice matters
Resizing, cropping, compression needed
Metadata, transparency, color profile concerns
Destination-specific requirements (web, social, ecommerce, print)

Quick Reference

Situation	Load File	Why
Web optimization, responsive images, lazy loading, SVG	web.md	Avoid CLS/LCP mistakes, oversized assets
Color profiles, metadata, RAW, print workflows	photography.md	Protect color intent, print readiness
Social platform dimensions, safe zones, banners	social.md	Prevent unsafe crops, recompression surprises
Product photos, marketplace standards	ecommerce.md	Preserve zoom detail, white-background compliance
Logos, favicons, SVGs, app icons	branding.md	Protect small-size legibility, SVG consistency
UI screenshots, docs captures, redaction	screenshots.md	Avoid blurry captures, privacy leaks
Alt text, text-in-image risk, charts	accessibility.md	Keep images usable and compliant
ImageMagick and Pillow commands	commands.md	Use concrete commands once decision is clear

Fast Workflow

Identify asset type: photo, screenshot, UI capture, logo, diagram, social card, product image, print source
Identify destination: web page, social upload, marketplace gallery, print handoff, internal archive
Decide preservation: vector, layered, or RAW vs flattened
Inspect file: dimensions, aspect ratio, orientation, transparency, color profile, metadata
Load destination-specific file if needed
Make minimum safe transformation: crop, resize, convert, compress, strip/preserve metadata, export
Validate in destination context

Asset-Type Defaults

Asset Type	Best Starting Point	Watch Out For
Photo	WebP or AVIF for web, JPEG fallback, layered/RAW master	Color profile shifts, overcompression
Product photo	JPEG or WebP, high-res clean master	White background, edge cleanup, zoom detail
Screenshot/UI	PNG or lossless WebP	JPEG blur, privacy leaks, unreadable text
Logo/icon	SVG master, PNG fallbacks only	Tiny details, unsupported SVG pipelines
Social/OG card	PNG or high-quality JPEG	Unsafe crop, tiny text, double compression
Diagram/chart	SVG when possible, PNG when raster needed	Thin lines, low contrast
Print image	TIFF or high-quality JPEG with correct profile	Wrong profile, wrong physical size, no bleed

Core Rules

1. Choose Workflow by Destination

Web delivery, social export, ecommerce prep, print output, and archive preservation are different jobs
Screenshot, product photo, logo, infographic, and print asset should not use same format/compression
If destination is specialized, read matching file before locking decisions

2. Pick Formats by Content

Content	Format
Photos	AVIF or WebP (modern web), JPEG (compatibility)
Screenshots, UI, diagrams, text-heavy	PNG or lossless WebP
Logos, icons, simple illustrations	SVG when supported
Transparency needed	PNG, WebP, or AVIF (not JPEG)
Animation	WebP, MP4, or WebM (not GIF)
Master/archive	TIFF, PSD, layered formats, RAW

3. Preserve Color, Transparency, Detail

Web assets: sRGB unless destination needs otherwise
Stripping ICC profiles can shift colors
Transparent assets need alpha-safe formats
Repeated lossy saves compound damage

4. Resize, Crop, Compress in Right Order

Decide aspect ratio
Crop
Resize
Compress

Do not upscale by default
Retina: 2x is normal, 3x should be deliberate
Social cards, ecommerce slots crop aggressively — protect focal area

5. Metadata and Orientation

EXIF orientation can rotate images unexpectedly
Public web assets should strip GPS and unnecessary camera metadata
Copyright, author metadata may need preservation

6. Practical Budgets

Image Type	Size Budget
Hero image	Under 200 KB
Content image	Under 100 KB
Thumbnail	Under 30 KB
Raster icon	Under 5 KB

Reserve layout space with explicit dimensions
Do not lazy-load LCP/hero image

7. Validate Against Destination

Platform specs are not interchangeable
Ecommerce: background consistency, edge cleanliness, zoom detail
Social: safe composition for different feed crops
Print: physical size, bleed, color handling

8. Batch Safely

Work from originals, not already-optimized outputs
Spot-check before batch processing
Keep per-destination exports separated from masters

Common Traps

Mistake	Consequence
Saving transparent images as JPEG	Lost alpha channel
JPEG for screenshots	Blurry text
Wrong aspect ratio with correct dimensions	Unsafe crop
Recompressing same JPEG multiple times	Quality degradation
Stripping metadata blindly	Broken orientation, lost licensing info
Forgetting sRGB	Color shifts between tools
Using SVG where platform doesn't support it	Broken display
Embedding critical text in images	Accessibility issues, hard to update
Rasterizing logo too early	Blurry exports forever

When to Use This Skill

Optimize images for web delivery
Prepare product photos for ecommerce
Create social media assets
Export for print
Process screenshots for documentation
Handle logos and icons correctly
Ensure image accessibility

Related Skills

image-edit — Masking, cleanup, inpainting, targeted edits
image-generation — AI image generation
photography — Capture, color, print workflows
svg — Vector graphics workflows
ecommerce — Marketplace product requirements

Frequently asked questions

What does the Image AI skill do?

Why use Image on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/wentorai/Research-Claw/tree/main/skills/image. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Image?

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 Image?

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

Is the Image AI skill free?

It is published on GitHub by wentorai. 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

Pretext

NousResearch

OrganizationPopular

Build creative browser demos with DOM-free text layout.

Sketch

Throwaway HTML mockups: 2-3 design variants to compare.

Tldraw Offline

Drive and script tldraw offline canvases with an agent.

Brand Guidelines

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Image

When to Use

Quick Reference

Fast Workflow

Asset-Type Defaults

Core Rules

1. Choose Workflow by Destination

2. Pick Formats by Content

3. Preserve Color, Transparency, Detail

4. Resize, Crop, Compress in Right Order

5. Metadata and Orientation

6. Practical Budgets

7. Validate Against Destination

8. Batch Safely

Common Traps

When to Use This Skill

Related Skills

Frequently asked questions

Related AI Skills

Set up your own AI workspace now