mcpbeat Sign in

Cover Image Agent Skill

Generate elegant cover images for articles. Analyzes content and creates eye-catching hand-drawn style cover images with multiple style and composition options. Use when user asks to "generate cover image", "create article cover", or "make a cover for article".

5k tokens
context cost
the whole folder, loaded on every use
18
files
instructions only
0
copies elsewhere
how many repositories repackaged it
130
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/sugarforever/01coder-agent-skills --skill cover-image

What comes with it

10 479 bytes besides the instruction
references/base-prompt.md
references/styles/blueprint.md
references/styles/bold.md
references/styles/editorial.md
references/styles/elegant.md
references/styles/geometric.md
references/styles/gradient.md
references/styles/ink-wash.md
references/styles/minimal.md
references/styles/nature.md
references/styles/neon.md
references/styles/paper-cut.md
references/styles/playful.md
references/styles/retro.md
references/styles/tech.md
references/styles/warm.md
references/styles/watercolor.md

The instruction itself

21 sections, as written by the author

Cover Image Generator

Generate hand-drawn style cover images for articles with rich style and composition options.

Usage

# From markdown file (auto-select style based on content)
/cover-image path/to/article.md

# Specify a style
/cover-image path/to/article.md --style tech
/cover-image path/to/article.md --style gradient

# Specify a composition
/cover-image path/to/article.md --composition hero-center

# Without title text
/cover-image path/to/article.md --no-title

# Combine options
/cover-image path/to/article.md --style editorial --composition split --no-title

# From direct text input
/cover-image
[paste content or describe the topic]

Options

| Option | Description |

|--------|-------------|

| --style <name> | Specify cover style (see Style Gallery below) |

| --composition <name> | Specify layout composition (see Composition Gallery below) |

| --no-title | Generate cover without title text (visual only) |

Core Styles

| Style | Description | Best For |

|-------|-------------|----------|

| elegant (Default) | Refined, sophisticated, understated | Business, thought leadership, professional |

| tech | Modern, clean, futuristic with glow effects | AI, coding, digital, algorithms |

| warm | Friendly, approachable, human-centered | Personal growth, lifestyle, education |

| bold | High contrast, attention-grabbing, energetic | Opinion pieces, controversial, urgent |

| minimal | Ultra-clean, zen-like, maximum whitespace | Philosophy, focus, essentialism |

| playful | Fun, creative, whimsical doodles | Tutorials, beginner guides, casual |

| nature | Organic, calm, earthy tones | Sustainability, wellness, outdoor |

| retro | Vintage, nostalgic, aged textures | History, retrospectives, classic topics |

Extended Styles

| Style | Description | Best For |

|-------|-------------|----------|

| gradient | Smooth color transitions, dreamy, modern | Product launches, announcements, branding |

| editorial | Magazine-quality, sophisticated typography | Long-form essays, deep dives, journalism |

| blueprint | Technical drawing aesthetic, grid paper | Architecture, system design, engineering |

| watercolor | Soft washes, organic bleed, painterly | Art, culture, creative writing, poetry |

| geometric | Sharp shapes, tessellations, mathematical | Data science, math, structured thinking |

| neon | Dark background with vivid glowing elements | Nightlife, gaming, cyberpunk, startup |

| paper-cut | Layered paper cutout depth effect | Storytelling, children's content, craft |

| ink-wash | East Asian brush ink aesthetic (水墨风) | Chinese culture, philosophy, calligraphy |

Detailed style definitions: references/styles/<style>.md

Compositions define how elements are arranged in the cover image.

| Composition | Description | When to Use |

|-------------|-------------|-------------|

| hero-center (Default) | Single focal visual centered, title above or below | General purpose, strong single concept |

| split | Left/right or top/bottom split, visual one side, text other | Comparison, before/after, dual concepts |

| floating | Elements scattered with depth, floating in space | Abstract topics, multiple related concepts |

| frame | Decorative border framing the central content | Formal, announcement, certificate-like |

| diagonal | Dynamic diagonal division or flow | Movement, progress, transformation |

| spotlight | Dark background with a single illuminated subject | Focus, highlight, key insight |

| panoramic | Wide scene spanning the full width | Landscape, journey, timeline |

| mosaic | Grid of small related visuals forming a bigger picture | Collection, variety, ecosystem |

| vignette | Soft fade from edges to center focus | Intimate, personal, memoir-style |

| layered | Overlapping planes creating depth | Complex topics, multi-layered ideas |

Composition Tips

  • hero-center + title: Place visual slightly left, title right
  • hero-center + no-title: Center the visual fully, let it breathe
  • split: Use contrasting colors or concepts on each side
  • floating: 3-5 elements max, vary sizes for depth
  • diagonal: Direction implies progress (bottom-left → top-right = growth)
  • spotlight: Keep background very dark, subject vivid
  • mosaic: Use 4-9 tiles, maintain consistent style across tiles
  • layered: Use opacity/blur to create foreground/background separation

Auto Style Selection

When no --style is specified, analyze content to select the best style:

| Content Signals | Selected Style |

|----------------|----------------|

| AI, coding, tech, digital, algorithm, API | tech |

| Personal story, emotion, growth, life, journey | warm |

| Controversial, urgent, must-read, warning, breaking | bold |

| Simple, zen, focus, essential, less is more | minimal |

| Fun, easy, beginner, casual, tutorial, step-by-step | playful |

| Nature, eco, wellness, health, organic, outdoor | nature |

| History, classic, vintage, old, traditional | retro |

| Product, launch, release, announcement, brand | gradient |

| Essay, analysis, deep dive, investigation, review | editorial |

| System design, architecture, blueprint, infrastructure | blueprint |

| Art, painting, creative, poetry, culture | watercolor |

| Data, math, statistics, geometry, patterns | geometric |

| Gaming, startup, nightlife, crypto, hacker | neon |

| Story, folktale, illustration, craft, children | paper-cut |

| 中国, 文化, 哲学, 书法, 国风, 传统 | ink-wash |

| Business, professional, strategy, analysis (default) | elegant |

Auto Composition Selection

When no --composition is specified:

| Condition | Selected Composition |

|-----------|---------------------|

| Single strong concept/metaphor | hero-center |

| Article compares two things | split |

| Article covers multiple tools/ideas | floating or mosaic |

| Personal/intimate topic | vignette |

| Journey/timeline/progress narrative | diagonal or panoramic |

| One key insight or revelation | spotlight |

| Complex multi-layered topic | layered |

| Formal/announcement tone | frame |

File Management

With Article Path

Save to imgs/ subdirectory in the same folder as the article:

path/to/
├── article.md
└── imgs/
    ├── prompts/
    │   └── cover.md
    └── cover.png

Without Article Path

Save to current working directory:

./
├── cover-prompt.md
└── cover.png

Workflow

Step 1: Analyze Content

Extract key information:

  • Main topic: What is the article about?
  • Core message: What's the key takeaway?
  • Tone: Serious, playful, inspiring, educational?
  • Keywords: Identify style-signaling words
  • Structure: Is it a comparison? A journey? A deep dive?
  • Visual metaphors: What real-world objects/scenes represent the topic?

Step 2: Select Style & Composition

If --style or --composition specified, use those. Otherwise:

  • Scan content for style and composition signals
  • Match signals to most appropriate style + composition
  • Default to elegant style + hero-center composition if no clear signals

Step 3: Generate Cover Concept

Title (if included, max 8 characters):

  • Distill the core message into a punchy headline
  • Use hooks: numbers, questions, contrasts, pain points
  • Skip if --no-title flag is used

Visual Elements:

  • Style-appropriate imagery and icons
  • 1-2 symbolic elements representing the topic
  • Metaphors or analogies that fit the style

Composition Layout:

  • Apply the selected composition template
  • Consider title placement within the composition
  • Ensure visual hierarchy: primary element > secondary > decorative

Step 4: Create Prompt File

Prompt Format:

Cover theme: [topic in 2-3 words]
Style: [selected style name]
Composition: [selected composition name]

[If title included:]
Title text: [8 characters or less, in content language]
Subtitle: [optional, in content language]

Visual composition:
- Main visual: [description matching style]
- Layout: [composition-specific layout description]
- Primary element: [what draws the eye first]
- Secondary elements: [supporting visuals]
- Decorative elements: [style-appropriate accents]

Color scheme:
- Primary: [style primary color]
- Background: [style background color]
- Accent: [style accent color]

Style notes: [specific style characteristics to emphasize]
Composition notes: [specific layout guidance]

[If no title:]
Note: No title text, pure visual illustration only.

Step 5: Generate Image

Image Generation Skill Selection:

  • Check available image generation skills
  • If multiple skills available, ask user to choose

Generation:

Call selected image generation skill with prompt file and output path.

Step 6: Output Summary

Cover Image Generated!

Topic: [topic]
Style: [style name]
Composition: [composition name]
Title: [cover title] (or "No title - visual only")
Location: [output path]

Preview the image to verify it matches your expectations.

Notes

  • Cover should be instantly understandable at small preview sizes
  • Title (if included) must be readable and impactful
  • Visual metaphors work better than literal representations
  • Maintain style consistency throughout the cover
  • Image generation typically takes 10-30 seconds
  • Title text language should match content language
  • When in doubt, elegant + hero-center is a safe default
  • Combine unexpected style+composition pairs for unique results (e.g., ink-wash + split)

Other skills for the same job

different authors, same section of the catalogue
Canvas Design
by anthropics
vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

1388k tokens
Algorithmic Art
by anthropics
vendor ×10

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

15k tokens scripts
Image Enhancer
by frostant
×6

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

635 tokens
Video Downloader
by CommandCodeAI
×4

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

671 tokens
Histolab
by christophacham
×3

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

18k tokens
Omero Integration
by christophacham
×3

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

32k tokens
Pydicom
by christophacham
×3

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

13k tokens scripts
Transformers
by christophacham
×3

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take sugarforever/cover-image from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.