Identify objects, scenes, text, colors, and composition in images.
npx skills add https://github.com/zunyiqingfeng-code/skills --skill vision-analyzer
Please help me install this Agent Skill. Skill: vision-analyzer Source: https://github.com/zunyiqingfeng-code/skills/tree/main/vision-analyzer Command: npx skills add https://github.com/zunyiqingfeng-code/skills --skill vision-analyzer
OpenCode users often need to quickly understand visual information from images in chat, such as screenshots, charts, or photos, but manual analysis is time-consuming and error-prone. This skill provides automatic image understanding, text extraction, and multi-language descriptions to accelerate decision-making.
Install the vision-analyzer, then simply mention an image path or URL in your chat to trigger an automatic visual analysis.
High-intent search queries and answers about installing and using this skill.
Image analysis from a remote URL involves fetching the visual data, recognizing objects and scenes, and extracting text via OCR. This skill processes both local files and remote URLs, returning multilingual descriptions with configurable detail levels.
Multilingual visual analysis for UI screenshots supports output in zh, en, ja, ko, fr, es, and de. The skill identifies objects, scenes, text, colors, and composition, translating these visual insights into your configured language.
OpenAI Vision API integration supports local image files for data extraction and visual analysis. The skill uses an OpenAI-based Vision API with a local-fallback option, enforcing image size and format constraints while caching results.
Automated image analysis for dashboards enforces strict image size and format constraints, requiring valid local files or accessible remote URLs. The skill includes robust error handling and an offline OCR fallback when the primary Vision API is unavailable.
Triggering automatic visual analysis from chat messages requires mentioning an image path or URL directly in the conversation. The skill automatically detects the reference, fetches the image, and returns rich multilingual analysis including text extraction and scene understanding.
noobmastercnAnalyze image content and perform OCR using a vision model.
DaddyElonMusk69Extract text from PDFs with OCR for scanned pages.
NITISH-gitbitClassify images and match text-image pairs using the CLIP model.
johnlindquistAnalyze images and extract text using Gemini Pro's vision API.
