AgriSkill-Agent: A Skill-Guided and Knowledge-Enhanced Agent Framework for Leaf Disease Diagnosis and Management

While visual recognition and multimodal language models have improved leaf disease identification, most systems remain focused on recognition rather than integrated diagnosis and management. Practical support must connect symptoms, lesion extent, evidence-grounded diagnosis, and crop-specific guidance. We present AgriSkill-Agent, a skill-guided and knowledge-enhanced single-agent framework for leaf disease diagnosis and management. A central large language model activates task-specific procedural skills to coordinate visual analysis, external knowledge, and structured reporting. The main contribution is a unified diagnosis-to-management workflow integrating stage-specific skill contracts, deterministic lesion measurement, literature retrieval, and a pesticide-use knowledge graph. Image-derived measurements remain separate from language-model interpretation, while literature and structured pesticide-use knowledge provide traceable support. We evaluated AgriSkill-Agent on 140 image-based cases across 10 crops. The framework achieved higher diagnostic accuracy and produced more complete and better-grounded reports than direct multimodal baselines. Ablation analysis indicated that procedural skills primarily improved workflow compliance and report completeness, whereas external knowledge strengthened management grounding. Overall, AgriSkill-Agent provides a structured and traceable approach for integrating visual evidence, diagnostic reasoning, and agricultural knowledge in AI-assisted crop disease diagnosis and management.