Stats
Actions
Tags
From kakutey-skills
Describe or analyze image content using Gemini 3 Flash. Use this skill when you need to understand what is in an image or pdf file (e.g., icons, screenshots, diagrams) to proceed with a task.
How this skill is triggered — by the user, by Claude, or both
Slash command
/kakutey-skills:image-describerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill allows you to analyze image files by providing a prompt and the file path. It uses the `gemini-3-flash-preview` model for fast and accurate vision analysis.
This skill allows you to analyze image files by providing a prompt and the file path. It uses the gemini-3-flash-preview model for fast and accurate vision analysis.
When you encounter an image file and need to understand its content:
describe.py script.python3 scripts/describe.py --prompt "Extract all text from this image." --image "screenshot.png"
python3 scripts/describe.py --prompt "Extract all text from this image." --image "screenshot.png"python3 scripts/describe.py --prompt "Identify the main UI components and their layout." --image "mockup.jpg"python3 scripts/describe.py --prompt "What does this icon represent?" --image "icon.svg"scripts/describe.py: Vertex AI SDK (google-genai) を使用して、画像や PDF を解析する Python スクリプト。npx claudepluginhub usa-tech-lab/kakutey-skills --plugin kakutey-skillsAnalyzes images with MiniMax vision tool for description, OCR, text extraction, UI mockup review, chart data parsing, diagrams. Auto-triggers on image shares or analysis requests.
Analyzes media files (PDFs, images, diagrams, screenshots) using a vision backend to extract structured data, descriptions, or summaries instead of literal file reading.
Describes UI screenshots, architecture diagrams, charts, photos, code screenshots, and terminal output using Read tool, documenting only visible elements.