Analyze images and PDFs with the Google Gemini API.
npx skills add https://github.com/einverne/dotfiles --skill gemini-vision
Please help me install this Agent Skill. Skill: gemini-vision Source: https://github.com/einverne/dotfiles/tree/main/claude/skills/gemini-vision Command: npx skills add https://github.com/einverne/dotfiles --skill gemini-vision
Extracting meaningful information from images and documents often requires specialized AI models and complex setup, making it difficult for developers to integrate advanced vision capabilities. This skill provides a streamlined way to leverage Google Gemini's advanced vision capabilities for tasks like image understanding, object detection, and document analysis, simplifying AI integration.
Use the gemini-vision skill to describe the image located at 'path/to/my_image.jpg'.
High-intent search queries and answers about installing and using this skill.
Image analysis with Gemini Vision API extracts meaningful information by processing images through Google's advanced vision model. The skill handles captioning, classification, visual question answering, object detection, and segmentation across single or multiple images (up to 3,600 per request) and PDFs, with automatic API key management and format validation.
Yes, the skill processes PDF documents supporting up to 1,000 pages for extracting text and analyzing visual elements. This enables analysis of large reports, contracts, and scanned documents while handling document understanding tasks like data extraction from invoices or forms.
Gemini Vision supports PNG, JPEG, and PDF formats with selectable models—gemini-2.5-flash (default), Pro, and Lite variants—letting you optimize for speed, capability, or cost based on your image analysis requirements.
The skill manages GEMINI_API_KEY authentication through a 3-step lookup process, handling credential retrieval automatically so you can focus on image analysis without manual key configuration.
The skill enforces supported image format constraints and file size limitations, validating inputs before processing. PDFs support up to 1,000 pages and requests handle up to 3,600 images, with error handling for format or size violations.
Object detection and segmentation capabilities depend on the selected Gemini model. The skill supports bounding boxes for object detection and pixel-level masks for segmentation, enabling precise visual understanding and detailed analysis for inspection photos or automated counting tasks.
einverneAnalyze images and PDFs with the Google Gemini API.
Weiwei-MaoAnalyze scientific data files across 200+ formats and generate Markdown reports.
akrindevAutomates high-volume AI tasks using the Gemini Batch API and JSONL files.
jleechanorgIntegrates vision and language models for image-grounded conversational AI.
