image-generation
Generate images from text descriptions and save them to the vault. Activate this skill when users want to create illustrations, diagrams, visual content, or any AI-generated images.
Best use case
image-generation is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate images from text descriptions and save them to the vault. Activate this skill when users want to create illustrations, diagrams, visual content, or any AI-generated images.
Teams using image-generation should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/image-generation/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How image-generation Compares
| Feature / Agent | image-generation | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate images from text descriptions and save them to the vault. Activate this skill when users want to create illustrations, diagrams, visual content, or any AI-generated images.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Image Generation Generate images from text descriptions using the `generate_image` tool and embed them in vault notes. ## How to Use Call the `generate_image` tool with these parameters: - **`prompt`** (required) — A detailed text description of the image to generate. - **`target_note`** (optional) — Path to a note that determines which attachment folder the image is saved to. If omitted, the currently active note is used. ### Critical Two-Step Workflow The `generate_image` tool **only generates and saves the image file** — it does NOT insert the image into any note. To embed the image in a note: 1. Call `generate_image` with your prompt 2. Use the returned `wikilink` (e.g., `![[generated-image.png]]`) and insert it into the target note with `write_file` Always complete both steps when the user wants an image in a specific note. ## Prompt Engineering Tips Write detailed, specific prompts for the best results: - **Be descriptive** — "A serene mountain lake at sunset with snow-capped peaks reflected in still water" is much better than "a lake" - **Specify style** — Include keywords like: photorealistic, watercolor, minimalist, sketch, oil painting, digital art, flat illustration, isometric - **Include composition** — Mention perspective: close-up, wide angle, aerial view, eye-level, birds-eye view - **Set the mood** — Describe lighting and atmosphere: warm golden hour light, dramatic shadows, soft diffused lighting, moody fog - **State what to avoid** — If certain elements shouldn't appear, mention that in the prompt ### Example Prompts - "A minimalist flat illustration of a bookshelf filled with colorful books, soft pastel colors, clean lines, white background" - "Photorealistic close-up of a mechanical keyboard with cherry blossom keycaps, shallow depth of field, warm desk lamp lighting" - "Watercolor painting of a cozy reading nook with an armchair, stack of books, and a steaming cup of tea, warm autumn tones" ## Common Use Cases - **Note illustrations** — Visual headers or concept diagrams for notes - **Creative projects** — Story illustrations, mood boards, concept art - **Blog and presentation images** — Custom visuals for published content - **Visual thinking** — Generating images to explore ideas or concepts ## Tips - Use `target_note` when the user specifies which note should contain the image — this ensures the file is saved to the correct attachment folder per the user's Obsidian settings. - If the user asks for multiple images, generate them one at a time and confirm each result before proceeding. - When the user gives a vague request like "add an image to my note", ask what they'd like the image to depict before generating.
Related Skills
vault-semantic-search
Search vault notes by meaning using semantic search (RAG). Activate this skill when users want to find notes by concept or topic rather than exact keywords, or when keyword search tools return poor results.
recall-sessions
Search past agent conversations to recall prior discussions, decisions, and context. Activate this skill when users ask about previous conversations, want to resume past work, or reference earlier decisions.
obsidian-properties
Work with Obsidian note properties (frontmatter). Activate this skill when users want to add, modify, or organize properties, understand property types, format YAML frontmatter, or use properties with templates, search, or Bases.
obsidian-bases
Create and configure Obsidian Bases — database-like views of notes. Activate this skill when users want to create bases, write filters, formulas, or set up table/cards/list/map views.
gemini-scribe-help
Answer questions about Gemini Scribe plugin features, settings, and usage. Activate this skill when users ask how to use the plugin, configure settings, or troubleshoot issues.
deep-research
Conduct comprehensive, multi-source research and generate cited reports. Activate this skill when users want in-depth research on a topic, need synthesis across web and vault sources, or want a structured research report saved to their vault.
audio-transcription
Transcribe audio and video files into structured notes. Activate this skill when users want to transcribe recordings, meetings, podcasts, voice memos, or any audio/video content in their vault.
ui-ux-guidelines
UI/UX best practices for obsidian-gemini plugin development. Covers modal sizing, text overflow, message formatting, collapsible UI, animations, icons, file chips, session state, CSS containment, and theme compatibility. Use this skill when building or modifying UI components.
release-process
Full release workflow for obsidian-gemini: update release notes, run checks, bump version with npm, create a GitHub release, and verify. Use this skill when preparing a new plugin release.
obsidian-plugin-development
Build, modify, and debug Obsidian plugins using the TypeScript API. Use this skill when working with Obsidian plugin source code, the obsidian npm package, plugin UI (views, modals, settings, commands, ribbons), vault file operations, editor manipulation, workspace management, metadata cache, events, markdown rendering, or the Obsidian CLI. Covers plugin lifecycle, best practices, common patterns, and the full TypeScript API surface.
obsidian-cli
Use the Obsidian CLI to debug, inspect, and test Obsidian plugins during development. Covers plugin reloading, console inspection, runtime evaluation, and common debugging recipes for the gemini-scribe plugin.
gemini-api-dev
Use this skill when building applications with Gemini models, Gemini API, working with multimodal content (text, images, audio, video), implementing function calling, using structured outputs, or needing current model specifications. Covers SDK usage (google-genai for Python, @google/genai for JavaScript/TypeScript, com.google.genai:google-genai for Java, google.golang.org/genai for Go), model selection, and API capabilities.