Cover Image logo

Cover Image

Community
sugarforever
cover-image

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".

Overview

Publishersugarforever
Repository01coder-agent-skills
Skill namecover-image
Stars
139
Forks
37
Bundled files
17
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.

  • 17 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sugarforever on GitHub. Read the source before you install it.

Installation

Install the Cover Image 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/sugarforever/01coder-agent-skills/tree/main/skills/cover-image
  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/sugarforever/01coder-agent-skills.git /tmp/01coder-agent-skills
mkdir -p .claude/skills
cp -r /tmp/01coder-agent-skills/skills/cover-image .claude/skills/cover-image
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cover Image 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 Cover Image 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 Cover Image 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.

Cover Image Generator

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

Usage

bash
# 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

OptionDescription
--style <name>Specify cover style (see Style Gallery below)
--composition <name>Specify layout composition (see Composition Gallery below)
--no-titleGenerate cover without title text (visual only)

Style Gallery

Core Styles

StyleDescriptionBest For
elegant (Default)Refined, sophisticated, understatedBusiness, thought leadership, professional
techModern, clean, futuristic with glow effectsAI, coding, digital, algorithms
warmFriendly, approachable, human-centeredPersonal growth, lifestyle, education
boldHigh contrast, attention-grabbing, energeticOpinion pieces, controversial, urgent
minimalUltra-clean, zen-like, maximum whitespacePhilosophy, focus, essentialism
playfulFun, creative, whimsical doodlesTutorials, beginner guides, casual
natureOrganic, calm, earthy tonesSustainability, wellness, outdoor
retroVintage, nostalgic, aged texturesHistory, retrospectives, classic topics

Extended Styles

StyleDescriptionBest For
gradientSmooth color transitions, dreamy, modernProduct launches, announcements, branding
editorialMagazine-quality, sophisticated typographyLong-form essays, deep dives, journalism
blueprintTechnical drawing aesthetic, grid paperArchitecture, system design, engineering
watercolorSoft washes, organic bleed, painterlyArt, culture, creative writing, poetry
geometricSharp shapes, tessellations, mathematicalData science, math, structured thinking
neonDark background with vivid glowing elementsNightlife, gaming, cyberpunk, startup
paper-cutLayered paper cutout depth effectStorytelling, children's content, craft
ink-washEast Asian brush ink aesthetic (水墨风)Chinese culture, philosophy, calligraphy

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

Composition Gallery

Compositions define how elements are arranged in the cover image.

CompositionDescriptionWhen to Use
hero-center (Default)Single focal visual centered, title above or belowGeneral purpose, strong single concept
splitLeft/right or top/bottom split, visual one side, text otherComparison, before/after, dual concepts
floatingElements scattered with depth, floating in spaceAbstract topics, multiple related concepts
frameDecorative border framing the central contentFormal, announcement, certificate-like
diagonalDynamic diagonal division or flowMovement, progress, transformation
spotlightDark background with a single illuminated subjectFocus, highlight, key insight
panoramicWide scene spanning the full widthLandscape, journey, timeline
mosaicGrid of small related visuals forming a bigger pictureCollection, variety, ecosystem
vignetteSoft fade from edges to center focusIntimate, personal, memoir-style
layeredOverlapping planes creating depthComplex 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 SignalsSelected Style
AI, coding, tech, digital, algorithm, APItech
Personal story, emotion, growth, life, journeywarm
Controversial, urgent, must-read, warning, breakingbold
Simple, zen, focus, essential, less is moreminimal
Fun, easy, beginner, casual, tutorial, step-by-stepplayful
Nature, eco, wellness, health, organic, outdoornature
History, classic, vintage, old, traditionalretro
Product, launch, release, announcement, brandgradient
Essay, analysis, deep dive, investigation, revieweditorial
System design, architecture, blueprint, infrastructureblueprint
Art, painting, creative, poetry, culturewatercolor
Data, math, statistics, geometry, patternsgeometric
Gaming, startup, nightlife, crypto, hackerneon
Story, folktale, illustration, craft, childrenpaper-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:

ConditionSelected Composition
Single strong concept/metaphorhero-center
Article compares two thingssplit
Article covers multiple tools/ideasfloating or mosaic
Personal/intimate topicvignette
Journey/timeline/progress narrativediagonal or panoramic
One key insight or revelationspotlight
Complex multi-layered topiclayered
Formal/announcement toneframe

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:

  1. Scan content for style and composition signals
  2. Match signals to most appropriate style + composition
  3. 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:

markdown
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:

  1. Check available image generation skills
  2. 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)

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 Cover Image AI skill do?

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".

Why use Cover Image on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sugarforever/01coder-agent-skills/tree/main/skills/cover-image. 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 Cover Image?

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 Cover Image?

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

Is the Cover Image AI skill free?

Yes. It is published on GitHub by sugarforever 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 👇