메뉴
AI image generation using Google Gemini (Gemini) and OpenAI GPT-Image. Generate, edit, iterate, and create assets.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Orchestrate a complete AI/ML research project from a user's idea to a finished research artifact by coordinating bundled research skills: autoresearch, research-lookup, brainstorming-research-ideas, scientific-critical-thinking, scholar-evaluation, ml-training-recipes, academic-plotting, scientific-visualization, scientific-schematics, imagegen, scientific-writing, ml-paper-writing, systems-paper-writing, and user-interaction. Supports explicit modes, evidence levels, checkpointed user steering, micro-validation, full-experiment handoff, and final response contracts.
Defines the checkpoint protocol for the elegant-researcher-skill pipeline. Use at major research transition points to summarize artifacts, show options, apply mode-specific defaults, and continue without blocking routine decisions.
Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.
Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between projects, or seeking novel angles on existing work.
Look up current research information using saved source searches. Prefer direct parallel-cli search commands for fast web search when available; use research_lookup.py for API-routed Parallel Chat deep research or Perplexity academic searches. Use for finding papers, gathering research data, and verifying scientific information. Note: API-routed queries are transmitted to api.parallel.ai (PARALLEL_API_KEY) or openrouter.ai (OPENROUTER_API_KEY).
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.
| name | imagegen |
| description | AI image generation using Google Gemini (Gemini) and OpenAI GPT-Image. Generate, edit, iterate, and create assets. |
| triggers | ["generate an image","create an image","make an image","draw","create a picture","generate a picture","create artwork","generate art","make me an image","create icons","generate icons","create a logo","generate a logo","create a moodboard","generate moodboard","design inspiration","character design","character sheet","edit this image","modify this image","change this image","update this image","refine this image","iterate on this","compare image providers","generate social images","create thumbnails","make favicons","dall-e","dalle","imagen","gemini image","gpt image"] |
This skill enables AI-powered image generation, editing, and asset creation using Google Gemini (Gemini) and OpenAI GPT-Image.
Activate this skill when the user wants to:
| Command | Use For |
|---|---|
/imagegen:generate | Generate images from prompts |
/imagegen:edit | Edit existing images |
/imagegen:iterate | Refine images through multiple steps |
/imagegen:compare | Compare Google vs OpenAI |
/imagegen:assets | Generate project assets |
/imagegen:moodboard | Create design inspiration sets |
/imagegen:character | Create consistent character sheets |
/imagegen:config | Configure defaults |
For complex image generation tasks, delegate to the image-generator subagent which has access to all generation scripts and can handle multi-step workflows.
Google Gemini (Gemini)
gemini-2.5-flash-image, gemini-3-pro-image-previewGEMINI_API_KEY or GOOGLE_API_KEYOpenAI GPT-Image
gpt-image-1.5, gpt-image-1, gpt-image-1-miniOPENAI_API_KEY| Format | OpenAI | |
|---|---|---|
| Square | 1:1 | 1024x1024 |
| Landscape | 16:9 | 1536x1024 |
| Portrait | 9:16 | 1024x1536 |
| Wide | 21:9 | - |
User: "Generate an image of a sunset over mountains"
Action: Use /imagegen:generate --prompt "A sunset over mountains"
User: "Create app icons for my project"
Action: Use /imagegen:assets --type icons --prompt "[ask for description]"
User: "Edit this image to add rain"
Action: Use /imagegen:edit --image [path] --prompt "Add rain falling"
User: "I want to iterate on this design"
Action: Use /imagegen:iterate --image [path] --prompt "[refinement]"
User: "Which provider would be better for logos?"
Action: Explain Google is better for style variety, OpenAI for text, and suggest /imagegen:compare to test both.
Before generating, verify:
google-genai, openai, Pillow (for resizing)# Install packages
pip install google-genai openai Pillow
# Set API keys (user's responsibility)
export GEMINI_API_KEY=your_key
export OPENAI_API_KEY=your_key
Help users craft effective prompts: