Progressive concept teaching through three depth levels (Core → Mechanics → Deep Dive). Creates diagrams, provides annotated code walkthroughs from the current codebase, and builds explanations from fundamentals to production internals. Triggers: "teach me about [pattern/concept]", "how does [architecture/pattern] work", "walk me through [this implementation]", "tutorial on [concept]", "deep dive into [system/pattern]", "help me understand [this design]" Use when: user requests multi-level learning about code patterns, architecture, or implementation mechanics with checkpoint-based progression. Not for: quick answers, single-sentence explanations, code fixes, or "what does this line do" questions—those are standard assistance.
98
Quality
100%
Does it follow best practices?
Impact
97%
1.44xAverage score across 5 eval scenarios
Created examples.md with complete Level 1-3 walkthrough of dependency injection:
Created separate reference files:
trigger-reference.md - Complete trigger word listexamples.md - Full teaching examplesvisualization-guide.md - Diagram decision tree (already existed)license: MITmetadata.version: 0.1.0The include field in tile.json doesn't prevent the orphaned files warning. This appears to be a linter quirk—the files are properly linked via references in SKILL.md.
Added version to metadata, but one warning remains (likely linter expecting different format).
learning-opportunity/
├── SKILL.md (84 lines, down from 85)
├── tile.json (updated with license)
├── examples.md (NEW - teaching examples)
├── trigger-reference.md (NEW - trigger patterns)
├── visualization-guide.md (existing)
└── IMPROVEMENTS.md (this file)If you want to further improve the score, consider:
Install with Tessl CLI
npx tessl i neomatrix369/learning-opportunity@0.1.0evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5