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.
Evaluate educational chapters through dual lenses: the Student Experience (engagement, clarity, confidence) and the Teacher Perspective (pedagogy, objectives, assessment). Output structured analysis with ratings, gaps, and actionable improvements.
Read all lesson files in the chapter directory:
ls -la <chapter-path>/*.md | grep -v summary | grep -v README | grep -v quiz
For each lesson file, extract:
Evaluate as a beginner encountering this content for the first time.
| Score | Criteria |
|---|---|
| 9-10 | Compelling hook, real-world relevance clear, I want to keep reading |
| 7-8 | Interesting enough, some engaging moments, minor dry spots |
| 5-6 | Functional but forgettable, reads like documentation |
| 3-4 | Boring, walls of text, no compelling reason to continue |
| 1-2 | Would abandon after first section |
Check for:
| Verdict | Criteria |
|---|---|
| Too Short | Missing examples, concepts unexplained, abrupt endings, "I don't understand" |
| Just Right | Each concept has sufficient depth, examples clarify, natural flow |
| Too Long | Repetitive explanations, over-elaborated points, could cut 30%+ |
Word count benchmarks:
| Score | Criteria |
|---|---|
| 9-10 | Crystal clear, no re-reading needed, "aha" moments |
| 7-8 | Mostly clear, occasional re-read for complex parts |
| 5-6 | Understandable with effort, some confusing sections |
| 3-4 | Frequently confused, missing context, jargon unexplained |
| 1-2 | Cannot follow, assumes knowledge I don't have |
Check for:
| Score | Criteria |
|---|---|
| 9-10 | Clear steps, achievable, builds confidence, "I did it!" |
| 7-8 | Mostly clear, minor ambiguity, successful completion likely |
| 5-6 | Workable but confusing steps, may need to troubleshoot |
| 3-4 | Missing steps, unclear what to do, likely to get stuck |
| 1-2 | Cannot complete without external help |
Check for:
| Score | Criteria |
|---|---|
| 9-10 | Clear path from start to mastery, each lesson builds on previous |
| 7-8 | Generally progressive, minor jumps between lessons |
| 5-6 | Some logical progression, noticeable gaps |
| 3-4 | Disconnected lessons, unclear how they relate |
| 1-2 | Random ordering, no clear learning path |
Check for:
| Score | Criteria |
|---|---|
| 9-10 | "I can definitely do this now" - ready to apply independently |
| 7-8 | "I mostly understand and could figure out the rest" |
| 5-6 | "I kind of get it but would need help applying it" |
| 3-4 | "I'm confused about when/how to use this" |
| 1-2 | "I have no idea what I just read" |
Check for:
Evaluate as an instructional designer assessing pedagogical soundness.
| Score | Criteria |
|---|---|
| 9-10 | SMART objectives, measurable, aligned to content and assessment |
| 7-8 | Clear objectives, mostly measurable, good alignment |
| 5-6 | Objectives present but vague or partially aligned |
| 3-4 | Weak objectives, not measurable, poor alignment |
| 1-2 | Missing or meaningless objectives |
Check for:
| Score | Criteria |
|---|---|
| 9-10 | Appropriate concepts for level, well-scaffolded, no overload |
| 7-8 | Generally appropriate, minor overload moments |
| 5-6 | Some cognitive overload, too many concepts at once |
| 3-4 | Significant overload, concepts piled without consolidation |
| 1-2 | Overwhelming, no chance of retention |
Benchmarks by proficiency:
Check for:
| Score | Criteria |
|---|---|
| 9-10 | Perfect progression, each concept builds on previous, no gaps |
| 7-8 | Good scaffolding, minor jumps that students can bridge |
| 5-6 | Some scaffolding gaps, requires prior knowledge not taught |
| 3-4 | Significant gaps, assumes knowledge not in prerequisites |
| 1-2 | No scaffolding, concepts appear randomly |
Check for:
| Layer | Expected Characteristics |
|---|---|
| L1 (Foundation) | Manual-first, understand before automate, no AI shortcuts |
| L2 (Collaboration) | AI as Teacher/Student/Co-Worker, learning through interaction |
| L3 (Intelligence) | Pattern recognition, creating reusable intelligence (skills/subagents) |
| L4 (Orchestration) | Capstone, combining components, spec-driven development |
Check for:
| Score | Criteria |
|---|---|
| 9-10 | Prompts directly extend lesson, specific, build skills |
| 7-8 | Good prompts, mostly connected to content |
| 5-6 | Generic prompts, loosely connected |
| 3-4 | Copy-paste prompts, don't match lesson |
| 1-2 | Missing or irrelevant prompts |
Check for:
| Score | Criteria |
|---|---|
| 9-10 | Clear verification at each step, students know if they succeeded |
| 7-8 | Good verification for most exercises |
| 5-6 | Some verification, students may be unsure of success |
| 3-4 | Weak verification, students can't tell if they're on track |
| 1-2 | No verification, students have no idea if they succeeded |
Check for:
After scoring, identify specific missing elements:
For each gap, provide:
Generate analysis in this structure:
# Chapter Evaluation: [Chapter Name]
## Executive Summary
[1 paragraph: Overall quality assessment, key strengths, critical issues, recommendation]
## Student Analysis
### Scores
| Dimension | Score | Verdict |
|-----------|-------|---------|
| Engagement | X/10 | [One-line summary] |
| Length | [Short/Right/Long] | [One-line summary] |
| Clarity | X/10 | [One-line summary] |
| Hands-On | X/10 | [One-line summary] |
| Progression | X/10 | [One-line summary] |
| Confidence | X/10 | [One-line summary] |
**Overall Student Experience**: X/10
### Detailed Findings
[Specific observations per dimension with examples from content]
### Student Pain Points
1. [Specific issue from student perspective]
2. [Specific issue from student perspective]
...
## Teacher Analysis
### Scores
| Dimension | Score | Verdict |
|-----------|-------|---------|
| Learning Objectives | X/10 | [One-line summary] |
| Cognitive Load | X/10 | [One-line summary] |
| Scaffolding | X/10 | [One-line summary] |
| Layer Appropriateness | X/10 | [One-line summary] |
| Try With AI | X/10 | [One-line summary] |
| Assessment | X/10 | [One-line summary] |
**Overall Pedagogical Quality**: X/10
### Detailed Findings
[Specific observations per dimension with examples from content]
### Pedagogical Concerns
1. [Specific issue from teacher perspective]
2. [Specific issue from teacher perspective]
...
## Gap Analysis
### Content Gaps
| Gap | Lesson(s) | Impact |
|-----|-----------|--------|
| [Missing element] | L0X | High/Med/Low |
...
### Structural Gaps
| Gap | Lesson(s) | Impact |
|-----|-----------|--------|
| [Missing element] | L0X | High/Med/Low |
...
### Pedagogical Gaps
| Gap | Lesson(s) | Impact |
|-----|-----------|--------|
| [Missing element] | L0X | High/Med/Low |
...
## Improvement Recommendations
### Priority 1 (Critical)
| # | Problem | Fix | Effort | Lesson(s) |
|---|---------|-----|--------|-----------|
| 1 | [Issue] | [Action] | Low/Med/High | L0X |
...
### Priority 2 (Important)
| # | Problem | Fix | Effort | Lesson(s) |
|---|---------|-----|--------|-----------|
| 1 | [Issue] | [Action] | Low/Med/High | L0X |
...
### Priority 3 (Nice-to-Have)
| # | Problem | Fix | Effort | Lesson(s) |
|---|---------|-----|--------|-----------|
| 1 | [Issue] | [Action] | Low/Med/High | L0X |
...
## Summary Metrics
| Metric | Value |
|--------|-------|
| Total Lessons | X |
| Average Word Count | X |
| Student Score | X/10 |
| Teacher Score | X/10 |
| Overall Score | X/10 |
| Critical Issues | X |
| Estimated Fix Time | X hours |
Compare evaluated chapters against high-quality reference lessons. The skill should automatically identify and read a reference lesson from Part 1 or Part 6 for comparison when available.
Reference lesson patterns to look for:
01-agent-factory-paradigm/01-digital-fte-revolution.md33-introduction-to-ai-agents/01-what-is-an-ai-agent.mdSee references/ for detailed rubrics:
student-rubric.md - Detailed student perspective evaluation criteriateacher-rubric.md - Detailed teacher perspective evaluation criteriaword-count-benchmarks.md - Word count guidelines by lesson type