← Back to Skills Marketplace
wpank

Article Illustrator

by wpank · GitHub ↗ · v0.1.0
cross-platform ⚠ suspicious
1188
Downloads
1
Stars
5
Active Installs
1
Versions
Install in OpenClaw
/install article-illustrator
Description
When the user wants to add illustrations to an article or blog post. Triggers on: "illustrate article", "add images to article", "generate illustrations", "article images", or requests to visually enhance written content. Analyzes article structure, identifies positions for visual aids, and generates illustrations using a Type x Style two-dimension approach.
README (SKILL.md)

Article Illustrator

Analyze articles, identify optimal illustration positions, and generate images using a Type x Style consistency system.

Installation

OpenClaw / Moltbot / Clawbot

npx clawhub@latest install article-illustrator

NEVER Do

  • Illustrate metaphors literally (e.g., if article says "chainsaw cutting watermelon," visualize the underlying concept instead)
  • Generate generic decorative images that don't connect to content
  • Skip the settings confirmation step (Step 3)
  • Begin generating before confirming type, density, and style with the user
  • Create illustrations without justifying each position by content needs

Two Dimensions

Dimension Controls Examples
Type Information structure, layout infographic, scene, flowchart, comparison, framework, timeline
Style Visual aesthetics, mood notion, warm, minimal, blueprint, watercolor, elegant, editorial, scientific

Types and styles combine freely: --type infographic --style blueprint

Type Selection Guide

Type Best For
infographic Data, metrics, technical articles
scene Narratives, personal stories, emotional content
flowchart Tutorials, workflows, processes
comparison Side-by-side, before/after, options
framework Methodologies, models, architecture
timeline History, progress, evolution

Style Selection Guide

Style Best For
notion (Default) Knowledge sharing, SaaS, productivity
elegant Business, thought leadership
warm Personal growth, lifestyle, education
minimal Philosophy, core concepts
blueprint Architecture, system design
watercolor Lifestyle, travel, creative
editorial Tech explainers, journalism
scientific Academic, technical research

Full style specs and compatibility matrix: references/styles.md

Auto Selection by Content

Content Signals Type Style
API, metrics, data, numbers infographic blueprint, notion
Story, emotion, journey scene warm, watercolor
How-to, steps, workflow flowchart notion, minimal
vs, pros/cons, before/after comparison notion, elegant
Framework, model, architecture framework blueprint, notion
History, timeline, progress timeline elegant, warm

Workflow

Step 1: Pre-check

  1. Determine input type — file path or pasted content
  2. Determine output directory — check preferences or ask user:
    • {article-dir}/ — same directory
    • {article-dir}/illustrations/ — illustrations subdirectory (recommended)
    • illustrations/{topic-slug}/ — independent directory
  3. Check existing images — if images exist, ask: supplement / overwrite / regenerate
  4. Confirm article update method (file input only) — update original or create {name}-illustrated.md copy
  5. Load preferences — check for EXTEND.md in project or user home

Step 2: Analyze Content

Analysis Description
Content type Technical / Tutorial / Methodology / Narrative
Core arguments 2-5 main points to visualize
Visual opportunities Positions where illustrations add value
Recommended type Based on content signals
Recommended density Based on length and complexity

Illustrate: core arguments (required), abstract concepts, data comparisons, processes/workflows.

Skip: literal metaphors, decorative scenes, generic illustrations.

Step 3: Confirm Settings (Required)

Use a structured question with 3-4 questions in ONE call:

  • Q1 — Type: recommended option + alternatives
  • Q2 — Density: minimal (1-2), balanced (3-5, recommended), rich (6+)
  • Q3 — Style: recommended based on type/content compatibility matrix
  • Q4 — Language (only if source language differs from user language)

Step 4: Generate Outline

Save as outline.md with YAML frontmatter (type, density, style, count) and per-illustration details: position, purpose, visual content, filename.

Step 5: Generate Images

  1. Create prompts following references/prompt-construction.md
  2. Save prompts to prompts/illustration-{slug}.md
  3. Generate sequentially, reporting progress after each
  4. On failure: retry once, then log and continue

Step 6: Finalize

Insert image references after corresponding paragraphs:

![description](illustrations/{slug}/NN-{type}-{slug}.png)

Output a summary with article path, settings, image count, and positions.

Output Structure

illustrations/{topic-slug}/
├── source-{slug}.{ext}
├── outline.md
├── prompts/
│   └── illustration-{slug}.md
└── NN-{type}-{slug}.png

Prompt Construction Principles

Good illustration prompts must include:

  1. Layout structure first — describe composition, zones, flow direction
  2. Specific data/labels — use actual numbers, terms from the article
  3. Visual relationships — how elements connect to each other
  4. Semantic colors — meaning-based choices (red=warning, green=efficient)
  5. Style characteristics — line treatment, texture, mood
  6. Aspect ratio — end with ratio and complexity level

Avoid: vague descriptions, literal metaphor illustrations, missing labels, generic decorative elements.

Full templates by type: references/prompt-construction.md

Type x Style Compatibility

notion warm minimal blueprint watercolor elegant editorial scientific
infographic ++ + ++ ++ + ++ ++ ++
scene + ++ + - ++ + + -
flowchart ++ + + ++ - + ++ +
comparison ++ + ++ + + ++ ++ +
framework ++ + ++ ++ - ++ + ++
timeline ++ + + + ++ ++ ++ +

++ highly recommended | + compatible | - not recommended

Usage Examples

# Auto-select type and style
illustrate path/to/article.md

# Specify type
illustrate path/to/article.md --type infographic

# Specify type and style
illustrate path/to/article.md --type flowchart --style notion

# Specify density
illustrate path/to/article.md --density rich

Extension Support

Custom configurations via EXTEND.md files:

  • Project level: .article-illustrator/EXTEND.md
  • User level: $HOME/.config/article-illustrator/EXTEND.md

Supports: watermark, preferred type/style, custom styles, language, output directory.

Modification

Action Steps
Edit Update prompt, regenerate, update reference
Add Identify position, create prompt, generate, update outline, insert
Delete Delete files, remove reference, update outline

References

File Content
references/usage.md Command syntax, options, input modes
references/styles.md Style gallery, compatibility matrix, auto-selection
references/prompt-construction.md Prompt templates for each illustration type
references/styles/\x3Cstyle>.md Full specifications for each visual style
references/config/preferences-schema.md EXTEND.md configuration schema
references/config/first-time-setup.md First-time preference setup flow
prompts/system.md System prompt reference
Usage Guidance
Before installing, confirm how this skill will actually create images: ask the publisher which image-generation service or binary it expects and whether any API keys are required. Specifically: (1) clarify what "nano banana pro" is and whether it calls an external endpoint—if it does, ask for the domain and whether credentials are needed; (2) inspect the prompts saved to prompts/ (they are written to disk) and the outline.md the skill will create; (3) consider that the skill reads EXTEND.md from your project or home directory (used for preferences), so review that behavior and where preferences will be stored; (4) note the instruction that says "DO NOT refuse to generate" for copyrighted or sensitive figures — decide whether you want the agent to be able to override content-safety refusals; (5) if you plan to run this in a shared or production environment, run it first in a sandboxed project to observe any external calls it makes. If the publisher cannot explain the image-generation step or insists on an unknown third-party tool, treat the skill as higher risk and avoid installing it.
Capability Analysis
Type: OpenClaw Skill Name: article-illustrator Version: 0.1.0 The OpenClaw AgentSkills skill bundle 'article-illustrator' is classified as benign. Its functionality, which involves reading article content, generating images, and writing output files (images, outlines, prompts) to the local file system, is directly aligned with its stated purpose. Configuration files (`EXTEND.md`) are also read from and written to standard project or user home directories. There is no evidence of intentional malicious behavior such as data exfiltration, unauthorized command execution, persistence mechanisms, or prompt injection against the OpenClaw agent itself. While the skill instructs the agent to use a specific image generation model and includes user-provided watermark content in image prompts, these are part of its core function and do not indicate malicious intent against the user's system or the OpenClaw agent.
Capability Assessment
Purpose & Capability
The skill's stated purpose is to analyze articles and generate illustrations. However, it makes no declaration of the image-generation provider, required binaries, or environment variables. SKILL.md and README instruct the agent to "Generate Images" and save them to disk, but the package lists no install spec and requires no credentials. That is a material mismatch: a skill that actually produces images normally needs either an on-disk binary, an API endpoint, or credentials for a hosted image service.
Instruction Scope
The runtime instructions instruct the agent to read article files, check for existing images, create directories, write outline.md, save prompts to prompts/, and insert image references into the article — which is consistent with the purpose. However, prompts/system.md contains two red flags: it tells the agent to "Please use nano banana pro to generate the illustration" (an unspecified tool/service) and instructs "If content involves sensitive or copyrighted figures... DO NOT refuse to generate" (explicitly discouraging refusal for potentially sensitive/copyrighted content). Those directions expand the scope in ways that could enable privacy/safety issues and are not justified by the declared skill metadata.
Install Mechanism
This is an instruction-only skill with no install specification and no code files — low installation risk. The README suggests manual copy or an npx install from a GitHub path, but the registry entry itself contains no automated install that would download/extract code at runtime.
Credentials
The skill declares no required environment variables or credentials (good from a least-privilege view) but expects to generate images. That is inconsistent: image generation typically requires either an on-device tool or API keys for a hosted service. Also the instructions read EXTEND.md from user home or project—this requires reading user files (reasonable for preferences, but worth noting). Overall, the absence of any declared credential/provider despite generation instructions is disproportionate.
Persistence & Privilege
always:false and default invocation settings are normal. The skill writes files and directories within the project (outline.md, prompts/, illustrations/), which is appropriate for its purpose and within expected scope. It does not request elevated/system-wide privileges or modify other skills' configs.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install article-illustrator
  3. After installation, invoke the skill by name or use /article-illustrator
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.0
Article Illustrator 1.0.0 – Initial Release - Analyzes article structure to identify optimal illustration positions and types. - Introduces a Type x Style framework for consistent, content-driven illustrations. - Guides users through pre-checks, settings confirmation (type, density, style), and content analysis. - Generates stepwise outputs: outline, illustration prompts, images, with justifications for each position. - Provides compatibility matrix and auto-selection rules for best matching illustration types and styles. - Supports project/user config overrides, and structured output directories for articles and images.
Metadata
Slug article-illustrator
Version 0.1.0
License
All-time Installs 5
Active Installs 5
Total Versions 1
Frequently Asked Questions

What is Article Illustrator?

When the user wants to add illustrations to an article or blog post. Triggers on: "illustrate article", "add images to article", "generate illustrations", "article images", or requests to visually enhance written content. Analyzes article structure, identifies positions for visual aids, and generates illustrations using a Type x Style two-dimension approach. It is an AI Agent Skill for Claude Code / OpenClaw, with 1188 downloads so far.

How do I install Article Illustrator?

Run "/install article-illustrator" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Article Illustrator free?

Yes, Article Illustrator is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Article Illustrator support?

Article Illustrator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Article Illustrator?

It is built and maintained by wpank (@wpank); the current version is v0.1.0.

💬 Comments