teach-back-evaluator
CommunityTest understanding by teaching a confused peer
Education & Research#metacognition#questioning#student assessment#teach-back#peer tutoring#learning by teaching#misconception detection
AuthorGarethManning
Version1.0.0
Installs0
System Documentation
What problem does it solve?
It helps learners verify they truly understand a concept by forcing them to explain it and then diagnosing gaps using authentic questions from a novice perspective.
Core Features & Use Cases
- Teach-back simulation: The learner teaches the target concept to an AI acting as a curious, slightly confused peer.
- Gap-finding via novice questions: The AI asks clarifying, mechanism, connection, and example-seeking questions to surface what the learner has missed or oversimplified.
- Structured scoring with pass criteria: The AI evaluates the teach-back on coherence, completeness, and misconception risk, and only advances when the explanation is sufficiently solid.
Quick Start
Use the teach-back evaluator to run an understanding check for the concept by having the learner explain it to Alex (a curious novice peer) using the provided context.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: teach-back-evaluator Download link: https://github.com/GarethManning/education-agent-skills/archive/main.zip#teach-back-evaluator Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.