fluent-vocablisted

# Vocabulary Drill Session ## Overview Flashcard-style vocabulary practice using spaced repetition. One word at a time, immediate feedback, DB update at the end. Interleaves three modes (recognition, production, cloze) to force active recall rather than passive re-reading. ## When to Use Skip this skill if no vocabulary items are due and no new words are queued — offer `/fluent-review` or `/fluent-learn` instead. ## Instructions ### 1. Load vocabulary data ```bash python3 "${CLAUDE_PLUGIN_ROOT:-${CLAUDE_PROJECT_DIR:-.}}/.claude/hooks/read-db.py" ``` If the helper is unavailable, resolve `<data_dir>` via `fluent_paths.data_dir()` then read: - `<data_dir>/spaced-repetition.json` - `<data_dir>/mistakes-db.json` - `<data_dir>/mastery-db.json` - `<data_dir>/learner-profile.json` (for target_language, name, level) If any are missing, direct the learner to `/fluent-setup` and stop. ### 2. Select words Priority order: 1. Items in `spaced-repetition.review_queue.today` with `item_type == "vocabulary"`. 2. Words from `mistakes-db.json` where `category == "vocabulary"` and `mastery_level <= 2`. 3. New high-frequency words matching `learner-profile.focus_areas`. Limit: `spaced-repetition.daily_limits.review_items_per_day` (default 20). ### 3. Present one word at a time ```markdown ## Word {N}/{total} {the prompt — see the three modes below} **Type your answer:** ``` Rotate the three modes so the session is not monotonous: - **Recognition** (target → native) — show the