Skill UI

Coordinates Exa MCP-driven web_search_exa and get_code_context_exa calls for up-to-date web results, code snippets, and company or people intel whenever the user requests research, competitive analysis, or development context.

This command evaluates and ranks results from finished AgentHub agents. It supports metric-based evaluation by running configured commands, LLM-based judging by comparing diffs and quality, or a hybrid mode. It identifies the winner based on performance metrics or qualitative analysis to assist in selecting the best agent for merging.

This bridge provides bidirectional integration between Home Assistant (HA) and advanced AI pipelines. It streams HA camera feeds into the AI system for sophisticated analysis (detection, VLM, REID). Conversely, the analysis results—such as detected objects, descriptions, and person identities—are sent back to HA as image_processing entities, enabling powerful automation and smart notifications.

This skill enables users to add and manage structured evaluation results within Hugging Face model cards. It supports extracting evaluation tables from README files, importing benchmark scores via the Artificial Analysis API, and executing custom model evaluations using vLLM or lighteval backends. It ensures compatibility with the model-index metadata format for standardized model releases.