{"skill":{"slug":"visual-grounding","displayName":"visual-grounding","summary":"Use GLM-4.7V's multimodal grounding capability to detect and locate objects/text in images. Activate when user asks to find, locate, detect, or ground specif...","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":184,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1773909658149,"updatedAt":1777272614995},"latestVersion":{"version":"1.0.0","createdAt":1773909658149,"changelog":"Initial release of visual-grounding skill using GLM-4.7V's multimodal capability:\n\n- Supports detection and localization of objects, text, and regions in images, with bounding box output.\n- Activates automatically on user prompts related to finding, locating, or grounding visual elements.\n- Provides step-by-step workflow: model API call, response parsing for bounding boxes, and result visualization with labeled boxes.\n- Includes utility functions for API interaction, coordinate parsing, normalization, and image annotation.\n- Offers quick reference and usage examples for easy integration.","license":"MIT-0"},"metadata":null,"owner":{"handle":"qijimrc","userId":"s17dxhxp6n7b66j7evz56mb7zn83w4q2","displayName":"Ji Qi","image":"https://avatars.githubusercontent.com/u/28889175?v=4"},"moderation":{"isSuspicious":true,"isMalwareBlocked":false,"verdict":"suspicious","reasonCodes":["suspicious.llm_suspicious"],"summary":"Detected: suspicious.llm_suspicious","engineVersion":"v2.4.0","updatedAt":1777272614995}}