功能描述

Generate diverse creative illustrations via OpenAI Images API. Create book illustrations, editorial art, children's book art, concept illustrations, and artistic scenes. Use when user needs creative visual content for stories, articles, presentations, or artistic projects (e.g., "illustrate a fairy tale scene", "create editorial art about technology", "design children's book illustrations", "generate concept art for a story").

使用说明 (SKILL.md)

Creative Illustration Factory

Name: fame graphic
Author: adebayoabdushaheed-a11y

Generate professional illustrations for books, editorial content, children's stories, and creative projects.

Setup

Needs env: OPENAI_API_KEY

Quick Start

Generate a simple illustration:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "a cozy cottage in an enchanted forest"

Generate with specific style:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "a robot learning to paint" \
  --style "watercolor" \
  --mood "whimsical"

Generate a story sequence:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "Alice discovers a tiny door" \
  --subject "Alice shrinks down" \
  --subject "Alice enters Wonderland" \
  --style "whimsical illustration" \
  --mood "magical"

Illustration Types

Book Illustrations

chapter-opener - Full-page chapter opening scene
character-intro - Character introduction portrait
landscape-scene - Wide landscape establishing shot
action-moment - Dynamic action or pivotal moment
emotional-scene - Emotional or dramatic scene
cover-art - Book cover illustration style

Editorial / Magazine Art

conceptual-art - Abstract conceptual illustration
info-graphic - Informational illustration style
portrait-editorial - Editorial portrait
spot-illustration - Small spot illustration
full-page-spread - Magazine full-page spread

Children's Book Art

picture-book - Classic picture book illustration
whimsical - Playful and imaginative style
educational - Educational book illustration
bedtime-story - Soft, calming bedtime story art
adventure-map - Adventure map or treasure map

Concept Art

environment-concept - Environmental concept art
character-concept - Character design concept
prop-concept - Object or prop design
storyboard - Storyboard panel style
mood-board - Mood board aesthetic

Styles

Traditional Media

watercolor - Watercolor painting with soft edges
oil-painting - Rich oil painting texture
charcoal-sketch - Charcoal drawing style
ink-wash - Ink wash / sumi-e style
pastel - Soft pastel drawing
colored-pencil - Colored pencil illustration
gouache - Gouache opaque watercolor
acrylic - Acrylic painting style
lino-cut - Linocut printmaking style
woodcut - Woodcut print aesthetic

Digital Styles

digital-painting - Digital painting
vector-illustration - Clean vector art
flat-design - Flat design aesthetic
isometric - Isometric perspective
pixel-art - Retro pixel art
concept-art - Game/film concept art style
cel-shaded - Cel shaded animation style
low-poly - Low poly 3D aesthetic

Book & Print Styles

picture-book - Classic picture book
storybook-illustration - Vintage storybook art
editorial-illustration - Magazine editorial
newspaper-engraving - Newspaper engraving style
poster-art - Vintage poster design
woodblock-print - Japanese woodblock print
screen-print - Screen print aesthetic

Mood

whimsical - Playful and imaginative
magical - Magical and enchanting
mysterious - Mysterious and intriguing
peaceful - Calm and serene
dramatic - Dramatic and intense
nostalgic - Warm and nostalgic
gloomy - Dark and atmospheric
vibrant - Bright and energetic
romantic - Soft and romantic
quirky - Quirky and eccentric

Parameters

--subject - Illustration subject/description (repeatable for batch)
--type - Illustration type (default: illustration)
--style - Artistic style (default: watercolor)
--mood - Mood/atmosphere (default: peaceful)
--palette - Color palette suggestion
--composition - Composition guidance (e.g., "wide shot", "close-up")
--count - Number of variants per subject (default: 1)
--out-dir - Output directory (default: ~/Projects/tmp/creative-illustration-*)
--size - Image size: 1024x1024, 1792x1024, 1024x1792 (default: 1024x1024)
--quality - high/standard (default: high)
--model - OpenAI image model (default: gpt-image-1.5)
--api-key - OpenAI API key (or use OPENAI_API_KEY env)

Advanced Examples

Children's book page:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "a curious rabbit with a pocket watch" \
  --type "picture-book" \
  --style "watercolor" \
  --mood "whimsical" \
  --palette "pastel"

Editorial concept art:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "AI and humanity working together" \
  --type "conceptual-art" \
  --style "vector-illustration" \
  --mood "optimistic" \
  --composition "symbolic"

Story sequence:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "Hero finds an ancient map" \
  --subject "Hero deciphers mysterious symbols" \
  --subject "Hero discovers a hidden passage" \
  --subject "Hero enters the forgotten temple" \
  --style "storybook-illustration" \
  --mood "mysterious" \
  --palette "earth tones"

Full custom prompt:

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --prompt "A magical treehouse library nestled among ancient redwoods, spiral staircase winding up the trunk, lanterns hanging from branches, books floating in mid-air, warm golden light streaming through leaves, detailed watercolor illustration style, whimsical and enchanting"

Color Palettes

pastel - Soft pastel colors
earth tones - Natural browns, greens, golds
vibrant - Bright saturated colors
muted - Desaturated, subtle colors
monochrome - Single color variations
jewel tones - Rich ruby, emerald, sapphire
autumn - Orange, red, yellow, brown
winter - Blue, white, silver, purple
tropical - Bright greens, teals, pinks
vintage - Warm sepia, faded tones

Composition

wide shot - Wide establishing scene
close-up - Intimate close-up
panoramic - Panoramic landscape
rule-of-thirds - Balanced rule of thirds
centered - Centered subject
diagonal - Dynamic diagonal composition
triangular - Triangular composition
circular - Circular / spiral composition
symmetrical - Perfectly symmetrical
asymmetrical - Asymmetrical balance

Output

*.png - Illustration images
prompts.json - All prompts used
index.html - Illustration gallery

Project Templates

Children's Book (4-6 images)

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "Girl finds a magical seed" \
  --subject "Seed grows into a glowing plant" \
  --subject "Plant reveals a tiny fairy" \
  --subject "Fairy shows girl a secret garden" \
  --subject "Girl shares garden with friends" \
  --type "picture-book" \
  --style "watercolor" \
  --mood "whimsical"

Magazine Editorial (1-2 images)

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "The future of sustainable cities" \
  --type "conceptual-art" \
  --style "vector-illustration" \
  --mood "optimistic" \
  --count 2

Fantasy Story Chapter Opener (1 image)

python3 ~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py \
  --subject "The dragon's treasure hoard under ancient runes" \
  --type "chapter-opener" \
  --style "oil-painting" \
  --mood "dramatic" \
  --palette "jewel tones"

安全使用建议

What to check before installing or running this skill: - The SKILL.md and script require an OpenAI API key (OPENAI_API_KEY or --api-key). The registry metadata did not declare this — treat that as an oversight and only supply a key with appropriate (limited) permissions or use a throwaway key. - The script honors OPENAI_BASE_URL / OPENAI_API_BASE. If those environment variables are set in your environment, the script will send prompts and your API key to whatever host they point to. Ensure those vars are trustworthy or unset them before running. - The package contains a Python script but also a Node package.json (likely unnecessary). This packaging mismatch is sloppy; review the included scripts/illustrate.py yourself to confirm behavior (it is readable and sends HTTP POST requests to an images/generations endpoint and writes files locally). - The manifest lists files twice — this is likely a packaging error but worth noting. - Run the script in an isolated environment (no sensitive env vars present), or inspect/edit the code to harden API base handling before use. If you are uncomfortable, don't provide your primary OpenAI key — create a limited test key or run in a network-restricted environment. If you want, I can point out the exact lines in scripts/illustrate.py that perform network requests and file writes, or produce a short checklist to safely run the skill.

功能分析

Type: OpenClaw Skill Name: afame Version: 1.0.0 The skill bundle is designed to generate illustrations via the OpenAI Images API. The `SKILL.md` provides clear instructions for the agent without any prompt injection attempts. The `illustrate.py` script correctly retrieves the OpenAI API key from environment variables or arguments and sends it to the OpenAI API endpoint (defaulting to `https://api.openai.com`). While the script allows overriding the API base URL via `OPENAI_BASE_URL` environment variables, this is a standard configuration option for API clients and does not indicate malicious intent from the skill itself. Output files are written to a user-owned temporary directory, and no other high-risk behaviors like data exfiltration of unrelated files, persistence mechanisms, or obfuscation were found.

能力评估

ℹ Purpose & Capability

The name/description and the included Python script align: the code builds prompts and posts to an OpenAI Images endpoint to generate illustrations. However, package.json declares a Node engine and lists SKILL.md as the main file while the implementation is Python — this is an odd packaging mismatch and likely unnecessary. The skill manifest also did not declare the OPENAI_API_KEY env var even though SKILL.md and the script require it.

ℹ Instruction Scope

SKILL.md's runtime instructions are narrowly scoped to running the included Python script and supplying an OpenAI API key (or --api-key). It does reference local paths (~/Projects/agent-scripts/skills/creative-illustration/scripts/illustrate.py and a default ~/Projects/tmp output dir) which may not exist on the host — these are convenience examples but could reveal assumptions about the user's home layout. The instructions do not request other unrelated files or secrets.

✓ Install Mechanism

No install spec is provided (instruction-only behavior), and the only code is a Python script included in the bundle. There are no downloads or external installers. The duplication of files in the manifest (SKILL.md, package.json, scripts/illustrate.py each listed twice) is sloppy but not inherently malicious.

⚠ Credentials

The skill requires an OpenAI API key (SKILL.md: OPENAI_API_KEY and the script accepts --api-key), but the skill registry metadata did not list any required env vars — that's an inconsistency that should be corrected. The script also honors OPENAI_BASE_URL / OPENAI_API_BASE to change the API base: while useful for enterprise proxies, this lets a configured base be repointed to an arbitrary endpoint, which could be used to collect prompts/keys if set by an attacker or misconfigured environment. Only an OpenAI API key (and optional API base override) appears necessary; no other credentials are requested.

✓ Persistence & Privilege

The skill does not request persistent or elevated platform privileges (always:false). It writes output files to a local out-dir but does not attempt to modify other skills or system configuration. Autonomous invocation is enabled by default (platform default) but there is no always:true or other escalated persistence.

版本历史

v1.0.0

Initial release of Creative Illustration Factory. - Generate diverse creative illustrations using the OpenAI Images API for books, editorials, children's stories, and concept art. - Supports a wide range of illustration types, styles, moods, color palettes, and compositions. - Command-line tool allows batch processing, custom prompts, and multiple output formats (PNG images, prompts.json, index.html gallery). - Includes detailed setup instructions, usage examples, and project templates for common use cases. - Configurable image size and quality, with support for specific OpenAI image models and API keys.

元数据

Slug afame

版本 1.0.0

许可证 —

累计安装 2

当前安装数 1

历史版本数 1

常见问题

fame graphic 是什么？

Generate diverse creative illustrations via OpenAI Images API. Create book illustrations, editorial art, children's book art, concept illustrations, and artistic scenes. Use when user needs creative visual content for stories, articles, presentations, or artistic projects (e.g., "illustrate a fairy tale scene", "create editorial art about technology", "design children's book illustrations", "generate concept art for a story"). 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 2276 次。

如何安装 fame graphic？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install afame」即可一键安装，无需额外配置。

fame graphic 是免费的吗？

是的，fame graphic 完全免费（开源免费），可自由下载、安装和使用。

fame graphic 支持哪些平台？

fame graphic 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 fame graphic？

由 adebayoabdushaheed-a11y（@adebayoabdushaheed-a11y）开发并维护，当前版本 v1.0.0。

fame graphic