assessment-architect
Assessment Architect - Concept-First Certification Exams
Generate rigorous certification exams by extracting concepts FIRST, then building scenario-based questions from the concept map.
Output: DOCX in assessments/ directory
NOT for: Practice quizzes (those use *_quiz.md in chapter directories)
Operating Contract (Non-Negotiable)
These rules are structural and cannot be overridden:
- No memorization questions. Every question requires a novel scenario paragraph before the stem. Questions testing recall of lesson-specific facts are rejected.
- Grounding notes before concepts. Read lessons → write notes file → extract concepts FROM notes. Never extract concepts from memory. The notes file is evidence of engagement.
- Concepts before questions. The concept map (built from notes) is the contract for Phase 2. Never generate questions by walking through lessons sequentially.
- Filesystem discovery only. No hardcoded book structure. Use
ls -dto find paths. The filesystem is the source of truth. - Structural validation. Anti-memorization (grep patterns) and anti-gaming (distribution bias) are FAIL conditions. Readability is a principle, not a word-count gate.
- Importance-weighted question count. Core lessons get 3-5 questions, supporting get 1-2, intro get 0-1. No flat "2 per lesson" — weight by importance.
More from panaversity/agentfactory
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
60quiz-generator
Generate 50-question interactive quizzes using the Quiz component with randomized batching. Use when creating end-of-chapter assessments. Displays 15-20 questions per session with immediate feedback. NOT for static markdown quizzes.
58ai-collaborate-teaching
Design co-learning experiences using the Three Roles Framework (AI as Teacher/Student/Co-Worker). Use when teaching AI-driven development workflows, spec-first collaboration, or balancing AI assistance with foundational learning. NOT for curriculum without AI integration.
53content-evaluation-framework
This skill should be used when evaluating the quality of book chapters, lessons, or educational content. It provides a systematic 6-category rubric with weighted scoring (Technical Accuracy 30%, Pedagogical Effectiveness 25%, Writing Quality 20%, Structure & Organization 15%, AI-First Teaching 10%, Constitution Compliance Pass/Fail) and multi-tier assessment (Excellent/Good/Needs Work/Insufficient). Use this during iterative drafting, after content completion, on-demand review requests, or before validation phases.
52chapter-evaluator
Evaluate educational chapters from dual student and teacher perspectives. This skill should be used when analyzing chapter quality, identifying content gaps, or planning chapter improvements. Reads all lessons in a chapter directory and provides structured analysis with ratings, gap identification, and prioritized recommendations.
51summary-generator
This skill should be used when generating lesson summaries for educational content. It extracts key concepts, mental models, patterns, and common mistakes from lesson markdown files using a Socratic extraction process. Use this skill when a lesson file needs a `.summary.md` companion file, or when reviewing/refreshing existing summaries.
49