agentleFS
puretechnycpuretechnyc/purebrain-skills/skills/content/blog-banner-creation/SKILL.md

blog-banner-creation

Skill0 starsChanged 6 months agoMITView on GitHub

Create branded blog header images with strict layout rules, safe zones, and brand color application. Python/Pillow implementation with 75% safe zone rule for mobile-safe rendering.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create branded blog header images that follow strict layout and branding rules to ensure consistency and mobile-safe rendering across all …

    line 13
  2. Distinctive:

    Before marking a blog banner complete:

    line 165

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Blog Banner Creation Skill

Purpose

Create branded blog header images that follow strict layout and branding rules to ensure consistency and mobile-safe rendering across all platforms.

CORE RULES

1. The 75% Safe Zone Rule

ALL important content MUST be within the center 75% of the image.

+--------------------------------------------------+
|                    12.5% margin                   |
|  +--------------------------------------------+  |
|  |                                            |  |
|  |           75% SAFE ZONE                    |  |
|  |    (All logos, text, important content)    |  |
|  |                                            |  |
|  +--------------------------------------------+  |
|                    12.5% margin                   |
+--------------------------------------------------+
  • Horizontal margins: 12.5% on left and right
  • Vertical margins: 12.5% on top and bottom
  • Why: Prevents cutoff on mobile devices and social media previews

2. Layout Hierarchy (Top to Bottom)

Within the 75% safe zone, content is arranged:

TOP-LEFT: [Brand Icon] Brand Logo (WITH SHADOW)
          (positioned LEFT or RIGHT, NOT centered)
          (shadow behind text for "lift" effect)

MIDDLE:   ARTICLE TITLE
          (LARGE font, main focus, CENTERED, word-wrapped if needed)
          (subtle shadow for readability)

BOTTOM:   (NOTHING - no tagline, title is the main content)

Key Points:

  • Logo icon should be LARGE (90px for 1920x1080)
  • Logo + icon NOT centered -- position to left or right
  • Shadow behind logo text creates visual lift
  • Title is the ONLY text in the middle -- no separate tagline

3. Sizing Guidelines

For a 1920x1080 image:

  • Brand icon: 90px (LARGE)
  • Logo text: 36px
  • Article title: 72px (LARGE, primary focus)
  • Shadow offset: 2-3px (for lift effect)

Scale proportionally for other image sizes.

4. Background Treatment

  • Apply semi-transparent dark gradient overlay for text readability
  • Stronger opacity at bottom, lighter at top
  • Cover any existing text from base image before adding new text

Implementation

from PIL import Image, ImageDraw, ImageFont
from pathlib import Path

def create_blog_header(
    article_title: str,
    brand_name: str = "YourBrand",
    bg_color: str = "#080a12",
    accent_color: str = "#2a93c1",
    cta_color: str = "#f1420b",
    width: int = 1920,
    height: int = 1080,
    output_path: str = "blog-header.png"
) -> Path:
    """Create blog header with correct branding.

    Args:
        article_title: The main title to display (will word-wrap if needed)
        brand_name: Your brand name for the logo area
        bg_color: Background color hex
        accent_color: Accent/secondary color hex
        cta_color: CTA/highlight color hex
        width: Image width in pixels
        height: Image height in pixels
        output_path: Where to save the output

    Returns:
        Path to the generated image
    """
    img = Image.new('RGB', (width, height), color=bg_color)
    draw = ImageDraw.Draw(img)

    # Calculate safe zone
    margin_x = int(width * 0.125)
    margin_y = int(height * 0.125)
    safe_left = margin_x
    safe_right = width - margin_x
    safe_top = margin_y
    safe_bottom = height - margin_y

    # Draw brand name in top-left of safe zone
    try:
        font_logo = ImageFont.truetype("Inter-Bold.ttf", 36)
        font_title = ImageFont.truetype("Inter-Bold.ttf", 72)
    except OSError:
        font_logo = ImageFont.load_default()
        font_title = ImageFont.load_default()

    # Logo with shadow
    draw.text((safe_left + 2, safe_top + 2), brand_name, fill='#333333', font=font_logo)
    draw.text((safe_left, safe_top), brand_name, fill=accent_color, font=font_logo)

    # Title centered in safe zone with word wrap
    title_y = safe_top + (safe_bottom - safe_top) // 3
    # Word wrap and center the title text
    max_width = safe_right - safe_left
    words = article_title.split()
    lines = []
    current_line = []
    for word in words:
        test_line = ' '.join(current_line + [word])
        bbox = draw.textbbox((0, 0), test_line, font=font_title)
        if bbox[2] - bbox[0] <= max_width:
            current_line.append(word)
        else:
            if current_line:
                lines.append(' '.join(current_line))
            current_line = [word]
    if current_line:
        lines.append(' '.join(current_line))

    for i, line in enumerate(lines):
        bbox = draw.textbbox((0, 0), line, font=font_title)
        line_width = bbox[2] - bbox[0]
        x = (width - line_width) // 2
        y = title_y + i * 90
        # Shadow
        draw.text((x + 3, y + 3), line, fill='#333333', font=font_title)
        # Text
        draw.text((x, y), line, fill='white', font=font_title)

    img.save(output_path)
    return Path(output_path)

Verification Checklist

Before marking a blog banner complete:

  • All content within 75% safe zone (12.5% margins)
  • Logo/brand positioned LEFT or RIGHT (NOT centered)
  • Shadow behind logo text for "lift" effect
  • Article title is LARGE, centered, and prominent
  • NO extra tagline -- title is the main content
  • Text is readable against background (shadows help)
  • No old/residual text showing through
  • Image dimensions match target platform requirements

Platform Size Reference

PlatformRecommended SizeRatio
Blog header1920x108016:9
LinkedIn1200x6271.91:1
Twitter/X1200x67516:9
Facebook1200x6301.91:1
Open Graph1200x6301.91:1

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.