File: workshop/side-quest-01-02-environment-reference.md
Overall Score: 4.93 / 10.0 (corpus mean: 6.14)
Flagged Dimensions:
| Dimension |
Score |
Benchmark |
Delta |
| cognitive_load |
6.3 |
≤ 800 words / ≤ 15 concepts |
word_count=1433 (−7.2 vs ideal), new_concepts=17 |
| active_learning |
2.1 |
density ≥ 3 |
activity_density=0.63 (2 code blocks + 7 checklist items / 14.3×100 words) |
| checkpoint_quality |
0.0 |
present + ≥4 items |
false negative — page has a valid ## :white_check_mark: Checkpoint section with 7 items, but the rubric's CHECKPOINT_RE only matches the literal ✅ glyph, not the :white_check_mark: shortcode used throughout the corpus |
Root Cause (≤ 2 sentences):
This reference page packs a 10-entry glossary table plus 8 "conceptual screenshot" subsections into 1433 words with only 2 code blocks, producing low interactivity relative to length. Note the checkpoint_quality: 0.0 score is a tooling artifact (regex mismatch), not a real content gap — the page already has a compliant checkpoint.
Evidence (quoted from the file):
Knowing which name maps to which role helps you follow workshop instructions without stopping to wonder what "the terminal" or "Codespaces" means in context.
| Term | What it means in this workshop | When you use it | Official documentation |
Learning Science Rationale:
Mayer's redundancy and coherence principles predict that long, uninterrupted expository blocks (a 10-row table plus 8 near-identical "you use X when..." image captions) impose extraneous cognitive load without corresponding retrieval practice; each additional passive segment increases word count without increasing the activity_density that active learning requires for durable encoding.
Improvement Prompt (for an agent):
Edit workshop/side-quest-01-02-environment-reference.md to reduce passive reading load and increase active learning density:
1. Collapse the 8 "conceptual screenshot" subsections (GitHub Codespaces, VS Code, Terminal, gh CLI, gh-aw CLI, Copilot CLI, Copilot app, Claude, OpenAI Codex) into 2-3 grouped <details> blocks (e.g. "Development environments" and "AI tools") to cut prose volume by roughly 400-500 words while keeping all images.
2. Add one short "quick match" active-recall exercise right after the glossary table, e.g. a 4-item mini-quiz: "Which tool would you use to install the gh-aw CLI extension? (a) VS Code (b) Terminal (c) Copilot app" with a collapsed answer, to raise activity_density above 3.
3. Keep the existing checkpoint section unchanged — it is already compliant with the workshop's checkpoint convention.
Do not remove any existing links, image references, or the enterprise callout.
Expected Score After Fix: 6.0 / 10.0
Generated by 🔬 Curriculum Quality Evaluator · copilot · auto · 77.1 AIC · ⌖ 14.6 AIC · ⊞ 9K · ◷
File:
workshop/side-quest-01-02-environment-reference.mdOverall Score:
4.93 / 10.0(corpus mean:6.14)Flagged Dimensions:
## :white_check_mark: Checkpointsection with 7 items, but the rubric'sCHECKPOINT_REonly matches the literal✅glyph, not the:white_check_mark:shortcode used throughout the corpusRoot Cause (≤ 2 sentences):
This reference page packs a 10-entry glossary table plus 8 "conceptual screenshot" subsections into 1433 words with only 2 code blocks, producing low interactivity relative to length. Note the
checkpoint_quality: 0.0score is a tooling artifact (regex mismatch), not a real content gap — the page already has a compliant checkpoint.Evidence (quoted from the file):
Learning Science Rationale:
Mayer's redundancy and coherence principles predict that long, uninterrupted expository blocks (a 10-row table plus 8 near-identical "you use X when..." image captions) impose extraneous cognitive load without corresponding retrieval practice; each additional passive segment increases word count without increasing the activity_density that active learning requires for durable encoding.
Improvement Prompt (for an agent):
Expected Score After Fix:
6.0 / 10.0