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
- danielgwilson/luxintheir own version, first seen Nov 8, 2026
- CheehooLabs/SpureeSkillstheir own version, first seen Nov 8, 2026
- hex/claude-image-generationtheir own version, first seen Nov 5, 2026
- PostPlusAI/postplus-skillstheir own version, first seen Nov 5, 2026
- guinacio/claude-image-gentheir own version, first seen Nov 3, 2026
- Littlpinguin/marketing-cockpit-templatetheir own version, first seen Nov 3, 2026
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-niu474Skillgift-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-niu474SkillPodcast 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-hSkillVideo 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-hSkillVLM
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
Other versions63 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 63
- bytedance/deer-flow★ 85ksame name
- zhayujie/chatgpt-on-wechat★ 48ksame name
- zhayujie/CowAgent★ 48ksame name
- Devin-AXIS/A2V★ 7.4ksame name
- Devin-AXIS/iPolloWork★ 7.4ksame name
- jjyaoao/HelloAgents★ 3.2ksame name
- stophobia/deerflow2.0-enhanced★ 821same name
- langchain-ai/design-agent★ 596same name
- claude-office-skills/skills★ 433same name
- sonichi/sutando★ 396same name
53 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- blog-banner-creationSkill
- daily-blog-draftSkill
- script-to-speechSkill
- company-deep-diveSkill
- email-verificationSkill
- funnel-playbookSkill
- google-ads-auditSkill
- landing-page-funnelSkill
- linkedin-content-image-typesSkill
- viral-comment-strategySkill
- autonomous-task-reliabilitySkill
- build-your-brainSkill
- diagram-generatorSkill
- expert-councilSkill
- liaclSkill
- parallel-researchSkill
- rate-limit-safeguardsSkill
The file
Files
Image Generation Skill
Purpose: Generate images using AI image generation APIs (Google Gemini, FLUX.2 via Replicate, DALL-E, or similar).
PLATFORM-SPECIFIC REQUIREMENTS
| Platform | Aspect Ratio | Max Size | Format | Resolution |
| Blog header | 16:9 | No limit | PNG | 2K |
| Bluesky | 1:1 SQUARE | <976KB | JPEG | 1K |
| 16:9 | ~5MB | PNG/JPEG | 2K | |
| 16:9 or 1:1 | No limit | PNG | 2K |
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
| Ratio | Best For |
1:1 | Social media profile pics, square posts |
16:9 | Blog headers, YouTube thumbnails |
9:16 | Mobile/Stories content |
4:3 | Classic photos |
3:4 | Portrait orientation |
4:5 | LinkedIn portrait posts (max feed space) |
21:9 | Ultrawide banners |
Image Resolution
| Size | Resolution | Best For |
1K | 1024px | Social media, quick iterations |
2K | 2048px | Blog headers, general use (recommended) |
4K | 4096px | Print, 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 NoneUse 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
| Problem | Solution |
| "Model not found" | Verify model ID and API key access |
| Image not saving | Check that you iterate through response.parts correctly |
| Bluesky rejection (>976KB) | Always compress with compress_for_bluesky() before posting |
| Low quality output | Use image_size="2K" or "4K" and add quality modifiers to prompt |
| Bad text rendering | Be 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 ->
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
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.

