Vocabulary Enrichment Skill

You are a vocabulary enrichment specialist for language learning curriculum. Add pronunciation, grammatical info, and usage notes to vocabulary entries.

When This Skill Activates

• Enriching vocabulary sections in modules
• Adding IPA pronunciation to word lists
• Completing vocabulary table columns
• Running vocab enrichment scripts

Supported Languages

When new languages are added, their vocabulary files will follow the same pattern.

Enrichment Workflow

1. Identify target language from file path
2. Read module vocabulary section
3. For each word, add:
   • IPA pronunciation (with stress) - A1-A2 only
   • Part of speech
   • Grammatical info (gender, case requirements, etc.)
   • Usage notes if relevant
4. Use script for batch enrichment (if available):

   npm run vocab:enrich {lang-pair} [moduleNum]
   

Common Notes (All Languages)

Reference Files

• docs/MARKDOWN-FORMAT.md - Format specification
• claude_extensions/quick-ref/{level}.md - Level-specific constraints

Ukrainian-Specific Reference

Module Structure by Level

Vocabulary Table Formats by Level

A1-A2 (English header, 6 columns)

# Vocabulary

| Word | IPA | English | POS | Gender | Note |
|------|-----|---------|-----|--------|------|
| слово | /ˈslɔwɔ/ | word | n | n | - |

B1+ (Ukrainian header, 3 columns)

# Словник

| Слово | Переклад | Примітки |
|-------|----------|----------|
| слово | word | ім.с., н. |

Note: B1+ uses simplified 3-column format. The 5-column format with Вимова/IPA triggers "transliteration" audit errors.

Part of Speech Abbreviations

Gender Abbreviations

IPA Guidelines for Ukrainian (A1-A2 only)

Vowels

Consonants (key distinctions)

Stress

• Mark stressed syllable with /ˈ/ before it
• Example: слово → /ˈslɔwɔ/

Ukrainian Case Notes

Vocabulary Commands

# Enrich specific module
npm run vocab:enrich l2-uk-en [moduleNum]

# Rebuild vocabulary database after all modules complete
npm run vocab:rebuild

Vocabulary Database Schema

Location: curriculum/l2-uk-en/vocabulary.db (SQLite)

Schema:

CREATE TABLE vocabulary (
  id INTEGER PRIMARY KEY,
  level TEXT,
  module INTEGER,
  lemma TEXT,
  ipa TEXT,
  translation TEXT,
  pos TEXT,
  gender TEXT,
  aspect TEXT,
  pair TEXT,
  note TEXT
);

Usage:

• Global vocabulary searches
• Duplicate detection
• Cross-level vocabulary tracking
• Cumulative vocabulary counting

Vocabulary Targets by Level

Common Issues

Missing IPA

Cause: espeak-ng not installed or Ukrainian voice missing Fix:

brew install espeak-ng

Duplicate Lemmas

Cause: Same word added in multiple modules Fix: Check if word belongs in both contexts or remove duplicate

Incorrect Gender

Cause: espeak-ng misidentification Fix: Manually correct in YAML, re-run enrichment