AI Teaching Resource Generator

Problem to solve

Teachers often already have a clear topic and learning objectives, but still need to turn them into usable teaching materials: slide outlines, cases, exercises, classroom activities, and AIGC prompts. Writing everything from scratch is repetitive, while prompting a model directly can produce content that is inaccurate, poorly matched to student level, or hard to reuse. This skill treats teaching-resource generation as a structured workflow: diagnose needs, generate assets, review quality, and suggest iterations.

How it works

• Needs analysis: parses inputs such as topic, objectives, students, and domain to identify key concepts, target levels, and difficulty.
• Tool selection: suggests suitable generation approaches for different asset types, such as courseware outlines, visual materials, exercise sets, or specialized simulation platforms.
• Resource generation: calls scripts/generate_teaching_resources.py and returns a JSON resource list that may include outlines, case libraries, exercises, AIGC prompts, and usage advice.
• Quality review: checks accuracy, completeness, and suitability, and flags risks such as factual errors, value misalignment, or licensing concerns.
• Iteration guidance: provides classroom integration points, activity design, evaluation metrics, and incremental optimization for existing lesson plans.

Boundaries

It is best for teachers who have defined learning objectives and need structured or batch teaching resources. Single small requests can be handled directly by the model. Teachers should still verify critical knowledge points, professional wording, and classroom value. When copyright, data compliance, or subject accuracy matters, AI-generated content should not be treated as the final conclusion.