メニュー
Plan a teaching knowledge base for AI-agent support, including source types, metadata, RAG architecture, privacy boundaries, content governance, evaluation, and teacher-facing use cases.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Design and review active learning implementation support for university teachers, including classroom activity structures, preparation workflow, student participation, assessment alignment, and AI-agent support points.
Turn dissertation evidence into an AI agent design specification for supporting active learning implementation, including user scenarios, functions, interaction flow, boundaries, failure modes, and design rationale.
Synthesize confirmed co-design, design-elicitation, prototype-feedback, or participant-generated design outputs into requirements, design principles, prototype changes, participant contribution maps, and design decision logs.
Design specifications for dissertation figures such as conceptual frameworks, concept-card/interview process diagrams, AI-agent workflow diagrams, adoption-condition models, and findings maps.
Maintain a lightweight dissertation research wiki with project memory, literature notes, methodology decisions, supervisor feedback, design rationale, and open questions.
Audit an AI agent prototype or design concept for usability, pedagogical fit, teacher feedback, active learning support, evidence quality, and next design iterations.
| name | teaching-knowledge-base-plan |
| description | Plan a teaching knowledge base for AI-agent support, including source types, metadata, RAG architecture, privacy boundaries, content governance, evaluation, and teacher-facing use cases. |
Use when the user asks to build a teaching knowledge base, RAG system, course knowledge base, AI tutor memory, or repository of active learning resources.
This skill plans the knowledge base. It does not install dependencies or implement a full system unless the user explicitly asks.
Use dissertation-knowledge-ops instead when the task is syncing, deduplicating, indexing, or deciding the source of record across research-wiki, knowledge-base, and Obsidian.
Consider:
Create or update:
knowledge-base/KB_PLAN.mdknowledge-base/SOURCE_REGISTER.mdknowledge-base/METADATA_SCHEMA.mdknowledge-base/RAG_EVALUATION_PLAN.mdFor a research-agent starter project, prefer:
Do not mix raw participant data with general teaching resources. Do not recommend uploading sensitive data to external services without explicit confirmation.