Image Gen logo

Image Gen

Organization
sinaptik-ai
image-gen

Use this skill when the user asks to create, edit, or manipulate images programmatically — including diagrams, charts, infographics, thumbnails, social media graphics, image processing (resize, crop, filter, watermark), or generating visual assets from data. Trigger when the output is a .png, .jpg, .svg, or .gif file.

Overview

Publishersinaptik-ai
Repositorystarpod
Skill nameimage-gen
Stars
80
Forks
20
Bundled files
2
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.

  • 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 sinaptik-ai on GitHub. Read the source before you install it.

Installation

Install the Image Gen 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/sinaptik-ai/starpod/tree/main/crates/starpod/skills/image-gen
  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/sinaptik-ai/starpod.git /tmp/starpod
mkdir -p .claude/skills
cp -r /tmp/starpod/crates/starpod/skills/image-gen .claude/skills/image-gen
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Image Gen 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 Gen 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 Gen 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 Generation & Processing

Quick Reference

TaskToolScript
Batch resizePillowpython scripts/resize.py img.jpg --width 800
Add watermarkPillowpython scripts/watermark.py img.jpg "DRAFT"
Data chartsmatplotlib + seabornSee below
Diagrams / flowchartsmatplotlib + patches, or SVGSee below
Image processingPillow (PIL)See below
Social media graphicsPillow with text + shapesSee below
Simple icons / logosSVG (write XML directly)See below
Animated GIFsPillow frame assemblySee below

Pillow — Image Processing

Resize and crop

python
from PIL import Image

img = Image.open("input.jpg")

# Resize maintaining aspect ratio
img.thumbnail((800, 600))
img.save("resized.jpg")

# Exact resize (may distort)
img_resized = img.resize((800, 600))

# Crop (left, upper, right, lower)
cropped = img.crop((100, 50, 500, 400))
cropped.save("cropped.jpg")

# Center crop to square
w, h = img.size
size = min(w, h)
left = (w - size) // 2
top = (h - size) // 2
square = img.crop((left, top, left + size, top + size))

Filters and adjustments

python
from PIL import ImageFilter, ImageEnhance

# Blur / sharpen
blurred = img.filter(ImageFilter.GaussianBlur(radius=3))
sharpened = img.filter(ImageFilter.SHARPEN)

# Brightness, contrast, saturation
enhancer = ImageEnhance.Brightness(img)
bright = enhancer.enhance(1.3)  # 1.0 = original

enhancer = ImageEnhance.Contrast(img)
contrast = enhancer.enhance(1.5)

# Convert to grayscale
gray = img.convert("L")

Compositing and watermarks

python
from PIL import Image, ImageDraw, ImageFont

img = Image.open("photo.jpg")
draw = ImageDraw.Draw(img)

# Text watermark
font = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 36)
draw.text((20, img.height - 50), "© 2025", fill=(255, 255, 255, 128), font=font)

# Overlay image (logo in corner)
logo = Image.open("logo.png").resize((100, 100))
img.paste(logo, (img.width - 110, 10), logo)  # third arg = mask for transparency

img.save("watermarked.jpg")

Pillow — Creating Graphics from Scratch

Banner / social media graphic

python
from PIL import Image, ImageDraw, ImageFont

W, H = 1200, 630  # Open Graph size
img = Image.new("RGB", (W, H), "#1E2761")
draw = ImageDraw.Draw(img)

# Background accent shape
draw.rectangle([(0, H - 80), (W, H)], fill="#F96167")

# Title text
font_title = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans-Bold.ttf", 64)
font_sub = ImageFont.truetype("/usr/share/fonts/truetype/dejavu/DejaVuSans.ttf", 28)
# Install fonts if missing: apt install fonts-dejavu-core

# Center title
bbox = draw.textbbox((0, 0), "Project Launch", font=font_title)
tw = bbox[2] - bbox[0]
draw.text(((W - tw) // 2, 200), "Project Launch", fill="white", font=font_title)

# Subtitle
bbox = draw.textbbox((0, 0), "Coming Q2 2025", font=font_sub)
tw = bbox[2] - bbox[0]
draw.text(((W - tw) // 2, 300), "Coming Q2 2025", fill="#CADCFC", font=font_sub)

img.save("banner.png")

Grid / contact sheet

python
from PIL import Image
import glob

images = [Image.open(f) for f in sorted(glob.glob("photos/*.jpg"))[:9]]
thumb_size = (300, 300)
cols, rows = 3, 3
padding = 10
bg_color = "#0A0A0A"

canvas_w = cols * thumb_size[0] + (cols + 1) * padding
canvas_h = rows * thumb_size[1] + (rows + 1) * padding
canvas = Image.new("RGB", (canvas_w, canvas_h), bg_color)

for i, img in enumerate(images):
    img.thumbnail(thumb_size)
    r, c = divmod(i, cols)
    x = padding + c * (thumb_size[0] + padding)
    y = padding + r * (thumb_size[1] + padding)
    canvas.paste(img, (x, y))

canvas.save("grid.png")

Diagrams with matplotlib

Flowchart

python
import matplotlib.pyplot as plt
import matplotlib.patches as mpatches

fig, ax = plt.subplots(figsize=(10, 8))
ax.set_xlim(0, 10)
ax.set_ylim(0, 10)
ax.axis('off')

def add_box(ax, x, y, text, color='#1E2761', w=2.5, h=0.8):
    rect = mpatches.FancyBboxPatch((x - w/2, y - h/2), w, h,
        boxstyle="round,pad=0.1", facecolor=color, edgecolor='white', linewidth=1.5)
    ax.add_patch(rect)
    ax.text(x, y, text, ha='center', va='center', fontsize=11,
            color='white', fontweight='bold')

def add_arrow(ax, x1, y1, x2, y2):
    ax.annotate('', xy=(x2, y2), xytext=(x1, y1),
        arrowprops=dict(arrowstyle='->', color='#888888', lw=1.5))

add_box(ax, 5, 9, "Start")
add_arrow(ax, 5, 8.6, 5, 7.8)
add_box(ax, 5, 7.4, "Process Data")
add_arrow(ax, 5, 7.0, 5, 6.2)
add_box(ax, 5, 5.8, "Analyze Results")
add_arrow(ax, 5, 5.4, 5, 4.6)
add_box(ax, 5, 4.2, "Generate Report", color='#2C5F2D')

plt.tight_layout()
plt.savefig('flowchart.png', dpi=150, bbox_inches='tight', facecolor='#0A0A0A')

SVG — Simple Vector Graphics

python
svg = '''<svg xmlns="http://www.w3.org/2000/svg" width="400" height="300" viewBox="0 0 400 300">
  <rect width="400" height="300" fill="#0A0A0A"/>
  <circle cx="200" cy="150" r="80" fill="none" stroke="#C0C0C0" stroke-width="2"/>
  <text x="200" y="155" text-anchor="middle" fill="#E8E8E8"
        font-family="system-ui" font-size="18" font-weight="bold">
    Logo Text
  </text>
</svg>'''

with open("icon.svg", "w") as f:
    f.write(svg)

Animated GIF

python
from PIL import Image, ImageDraw

frames = []
W, H = 400, 400

for i in range(30):
    img = Image.new("RGB", (W, H), "#0A0A0A")
    draw = ImageDraw.Draw(img)
    x = int(i / 29 * (W - 60))
    draw.ellipse([x, 170, x + 60, 230], fill="#F96167")
    frames.append(img)

frames[0].save("animation.gif", save_all=True, append_images=frames[1:],
               duration=50, loop=0, optimize=True)

Common Image Sizes

Use caseSize (px)
Open Graph / social share1200 × 630
Twitter card1200 × 675
Instagram post1080 × 1080
Instagram story1080 × 1920
YouTube thumbnail1280 × 720
Favicon32 × 32 or 64 × 64
App icon512 × 512

Quality Rules

  • Always set DPI: plt.savefig(..., dpi=150) minimum
  • Use tight layout: bbox_inches='tight' to avoid clipping
  • Label everything: axes, legends, titles on charts
  • Consistent palette: pick 3–5 colors and reuse them
  • Check contrast: text must be readable against background
  • Save PNG for graphics (lossless), JPEG for photos (smaller)

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 Image Gen AI skill do?

Use this skill when the user asks to create, edit, or manipulate images programmatically — including diagrams, charts, infographics, thumbnails, social media graphics, image processing (resize, crop, filter, watermark), or generating visual assets from data. Trigger when the output is a .png, .jpg, .svg, or .gif file.

Why use Image Gen on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sinaptik-ai/starpod/tree/main/crates/starpod/skills/image-gen. 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 Image Gen?

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 Gen?

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

Is the Image Gen AI skill free?

Yes. It is published on GitHub by sinaptik-ai 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 👇