image-generation
The image-generation skill creates illustrations for technical articles and documentation using a multi-provider workflow. It prioritizes a built-in Codex tool, falling back to OpenAI or Gemini APIs via a local Python script when necessary.
Is image-generation safe to install?
Review the source first: our audit of image-generation's source files found 1 shell command, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes local Python scripts and performs file system operations, including reading existing image directories and writing new image files to the workspace.
How we audit skills: our security review methodology.
Who is this skill for?
Technical writers, developers, and content creators who need to generate diagrams, concept illustrations, or visual aids for documentation and blog posts.
What can you do with it?
- Generating architecture diagrams for technical documentation
- Creating concept illustrations for blog posts
- Producing visual explanations for workflows or system designs
- Generating raster images for project-specific assets
How good is this skill?
Quality score: 9/10. The documentation is clear, provides specific workflows for different providers, and includes actionable guidance for prompt engineering and file management.
What does the skill file contain?
# Image Generation Skill Generate illustration images for blog posts, documentation, and technical articles. The workflow is provider-aware: 1. **Codex built-in path first** — when the current agent is Codex and the built-in `image_gen` tool is available, use it directly. This path does not require `OPENAI_API_KEY`. 2. **OpenAI API fallback** — outside Codex, or when the built-in tool is unavailable, use the local script with `OPENAI_API_KEY` if present. 3. **Gemini fallback** — if OpenAI API generation is unavailable or fails, use the same script with `GEMINI_API_KEY` and the existing Gemin...
Frequently asked questions
Which AI models does this skill support?
It uses the Codex built-in tool, OpenAI's gpt-image-2, and Google's gemini-3.1-flash-image-preview.
How does the skill determine where to save the generated image?
It follows a priority order: it checks the current markdown file for existing image paths, looks for common project directories like images/ or assets/, or defaults to the current working directory.
Can I customize the image style?
Yes, the skill applies a default minimalist style prefix, but you can override this using the --style-prefix or --no-style options.
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
copywriting
123.0KUsers who need to write or improve marketing copy for web pages and require a structured, conversion-oriented approach
The copywriting skill provides a framework for generating and refining marketing copy for websites, including homepages, landing pages, and product pages. It guides the agent to gather product marketing context from local files, apply conversion-focused writing principles, and structure content for clarity and persuasion.
programmatic-seo
83.5KContent strategists, SEO specialists, and marketers building large-scale, data-driven website content
The programmatic-seo skill provides a framework for generating SEO-optimized pages at scale using templates and data. It guides users through keyword research, data sourcing, template design, internal linking, and indexation strategies while emphasizing content uniqueness to avoid search engine penalties.
ad-creative
64.0KPerformance marketers, growth teams, and advertisers who need to produce ad copy at scale or optimize existing ad creative
The ad-creative skill generates, iterates, and scales ad copy for paid advertising platforms including Google, Meta, LinkedIn, TikTok, and Twitter. It provides frameworks for creating ad headlines, descriptions, and primary text based on product context and performance data.