agentleFS
puretechnycpuretechnyc/purebrain-skills/skills/content/image-generation/SKILL.md

image-generation

Skill0 starsChanged 6 months agoMITView on GitHub

Generate images for blog banners, social posts, LinkedIn graphics, and marketing materials using AI image generation APIs. Multi-platform sizing, compression workflows, and prompt engineering patterns.

  • Reads credentials

63 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use gift-evaluator, Podcast Generate and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • dav-niu474Skill

    gift-evaluator

    The PRIMARY tool for Spring Festival gift analysis and social interaction generation. Use this skill when users upload photos of gifts (alcohol, tea, supplements, etc.) to inquire about their value, authenticity, or how to respond socially. Integrates visual perception, market valuation, and HTML card generation.

    Also in 5 projects that use this

  • dav-niu474Skill

    Podcast Generate

    Generate podcast episodes from user-provided content or by searching the web for specified topics. If user uploads a text file/article, creates a dual-host dialogue podcast (or single-host upon request). If no content is provided, searches the web for information about the user-specified topic and generates a podcast. Duration scales with content size (3-20 minutes, ~240 chars/min). Uses z-ai-web-dev-sdk for LLM script generation and TTS audio synthesis. Outputs both a podcast script (Markdown) and a complete audio file (WAV).

    Also in 5 projects that use this

  • huang-x-hSkill

    Video Generation

    Implement AI-powered video generation capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to generate videos from text prompts or images, create video content programmatically, or build applications that produce video outputs. Supports asynchronous task management with status polling and result retrieval.

    Also in 6 projects that use this

  • huang-x-hSkill

    VLM

    Implement vision-based AI chat capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to analyze images, describe visual content, or create applications that combine image understanding with conversational AI. Supports image URLs and base64 encoded images for multimodal interactions.

    Also in 6 projects that use this

  • +1 more from huang-x-h
  • +7 more from dav-niu474

The file

Files
SKILL.md

Image Generation Skill

Purpose: Generate images using AI image generation APIs (Google Gemini, FLUX.2 via Replicate, DALL-E, or similar).


PLATFORM-SPECIFIC REQUIREMENTS

PlatformAspect RatioMax SizeFormatResolution
Blog header16:9No limitPNG2K
Bluesky1:1 SQUARE<976KBJPEG1K
Twitter16:9~5MBPNG/JPEG2K
LinkedIn16:9 or 1:1No limitPNG2K

Bluesky Compression (MANDATORY for posts)

Bluesky REJECTS images >976KB. Always compress:

from PIL import Image

def compress_for_bluesky(input_path: str, output_path: str):
    """Compress image for Bluesky (<976KB requirement)."""
    img = Image.open(input_path)
    if img.mode in ('RGBA', 'P'):
        img = img.convert('RGB')
    img.save(output_path, "JPEG", quality=85, optimize=True)
    print(f"Compressed: {output_path}")

Quick Start (Google Gemini)

from google import genai
from google.genai import types
import os

client = genai.Client(api_key=os.environ['GOOGLE_API_KEY'])

# Generate image
response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents="A digital art piece showing interconnected nodes in a constellation pattern",
    config=types.GenerateContentConfig(
        response_modalities=['IMAGE'],
        image_config=types.ImageConfig(
            aspect_ratio="16:9",
            image_size="2K"
        ),
    )
)

# Save image
for part in response.parts:
    if part.inline_data is not None:
        image = part.as_image()
        image.save("output.png")
        print("Image saved!")

Aspect Ratios

RatioBest For
1:1Social media profile pics, square posts
16:9Blog headers, YouTube thumbnails
9:16Mobile/Stories content
4:3Classic photos
3:4Portrait orientation
4:5LinkedIn portrait posts (max feed space)
21:9Ultrawide banners

Image Resolution

SizeResolutionBest For
1K1024pxSocial media, quick iterations
2K2048pxBlog headers, general use (recommended)
4K4096pxPrint, high-quality needs

Text in Images

Modern AI image generators (especially Gemini) excel at text rendering. Use this capability.

Great uses for text in images:

  • Quote cards: Include the quote directly in the image
  • Titles/Headlines: Blog titles, thread hooks
  • Infographics: Labels, data points, explanations
  • Branding: Your brand name, tagline
  • Call-to-action: "Read more", "Thread below"

How to request text:

prompt = """Quote card with the text "Memory is our moat" in bold white typography.
Dark blue gradient background.
Text should be LARGE and CENTERED.
Professional design, clean composition."""

Be explicit: "Write 'HELLO' in bold serif font" creates clearer results than vague requests.


Style Keywords That Work Well

  • Photography terms: "35mm prime lens", "macro close-up", "film grain", "bokeh"
  • Quality modifiers: "8K quality", "high detail", "professional photography"
  • Lighting descriptors: "Rembrandt lighting", "golden hour", "backlit", "dramatic"

Complete Function

import os
from pathlib import Path
from google import genai
from google.genai import types

def generate_image(
    prompt: str,
    output_path: str = "output.png",
    aspect_ratio: str = "16:9",
    image_size: str = "2K"
):
    """
    Generate an image using an AI image generation API.

    Args:
        prompt: Text description of the image to generate
        output_path: Where to save the image
        aspect_ratio: 1:1, 16:9, 9:16, 4:3, 3:4, 21:9
        image_size: "1K", "2K", or "4K"

    Returns:
        Saved file path, or None if generation failed
    """
    client = genai.Client(api_key=os.environ['GOOGLE_API_KEY'])

    response = client.models.generate_content(
        model="gemini-3-pro-image-preview",
        contents=prompt,
        config=types.GenerateContentConfig(
            response_modalities=['IMAGE'],
            image_config=types.ImageConfig(
                aspect_ratio=aspect_ratio,
                image_size=image_size
            ),
        )
    )

    for part in response.parts:
        if part.inline_data is not None:
            image = part.as_image()
            image.save(output_path)
            print(f"Saved to: {output_path}")
            return output_path

    print("No image generated")
    return None

Use Case Examples

Blog Header (16:9, 2K)

generate_image(
    prompt="Blog header for article about AI and marketing. Abstract neural network with glowing nodes. Modern tech aesthetic. Include title 'The Future of Marketing' in bold white.",
    output_path="blog-header.png",
    aspect_ratio="16:9",
    image_size="2K"
)

Social Media Post (1:1, 1K)

generate_image(
    prompt="Square social media graphic showing AI collaboration. Abstract, modern, professional.",
    output_path="social-image.png",
    aspect_ratio="1:1",
    image_size="1K"
)

Quote Card

generate_image(
    prompt='Quote card with text "Data without insight is just noise" in elegant typography. Dark background, golden text, professional design.',
    output_path="quote-card.png",
    aspect_ratio="1:1",
    image_size="2K"
)

Troubleshooting

ProblemSolution
"Model not found"Verify model ID and API key access
Image not savingCheck that you iterate through response.parts correctly
Bluesky rejection (>976KB)Always compress with compress_for_bluesky() before posting
Low quality outputUse image_size="2K" or "4K" and add quality modifiers to prompt
Bad text renderingBe very explicit about text content, font style, and placement

Built by PureBrain -- AI-powered marketing operations.

Want the full suite of 183+ production-tested skills? Start your trial ->

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.