Menu
Generate an ordered list of daily study tasks tailored to the learner's current week focus, recent performance, and available time.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Generate a personalized 24-week Japanese study plan structure based on the learner's goal, level, daily time budget, and topic preferences.
Synthesize the past week's task history, self-ratings, and mistake patterns into a compressed weekly summary with weak areas, strong areas, and a recommended focus for the next week.
Produce a structured listening comprehension drill from data/listening.json, including transcript segments, key vocabulary callouts, comprehension questions, and a summary task.
Create a shadowing drill from listening or speaking content, with sentence-by-sentence guidance, rhythm cues, and repetition instructions.
Deliver a structured speaking task from data/speaking.json, with hint scaffolding, target patterns, and a timer target — revealing the sample answer only after the learner attempts.
Analyze a learner's Japanese answer and return a corrected version, a natural native version, a list of mistakes with Chinese explanations, and brief coaching advice.
| name | generate-daily-tasks |
| description | Generate an ordered list of daily study tasks tailored to the learner's current week focus, recent performance, and available time. |
Invoke this skill each time a learner runs /jp-today. It reads the learner's profile and current week plan to produce a concrete, time-bounded task list for today.
| Parameter | Type | Required | Description |
|---|---|---|---|
user_profile | object | yes | Full user record from storage/users.json |
current_week | object | yes | Current week object from the study plan (output of build-study-plan) |
recent_progress | object | yes | User's progress record from storage/progress.json |
available_minutes | integer | yes | Time the learner has today (defaults to user_profile.daily_minutes) |
An ordered array of task objects:
| Field | Type | Description |
|---|---|---|
task_id | string | Unique ID for today's session: {type}_{content_ref}_{YYYYMMDD} |
type | string | Task type: "vocab", "grammar", "listening", "shadowing", "speaking" |
content_ref | string | ID of the item in data/*.json to use |
estimated_minutes | integer | Time allocation for this task |
priority | string | "core" (must do) or "bonus" (if time allows) |
Time is distributed proportionally to the week's focus_area:
Round to nearest 5-minute block. Any remainder becomes bonus time.
Tasks are ordered to optimize learning flow:
If yesterday's daily_state.carry_forward_recommendation exists, prepend a short review task targeting those weak points before the warm-up.
select-vocab-items with recent_mistakes from progressselect-grammar-items with current week focusgenerate-listening-drill matching topic and levelgenerate-shadowing-drill from the same listening itemgenerate-speaking-prompt matching topicInput:
{
"user_profile": { "level": "N5", "daily_minutes": 30, "focus_topics": ["travel"] },
"current_week": { "week_index": 3, "focus_area": "vocab+listening", "target_vocab_count": 7 },
"recent_progress": { "recurring_mistakes": [{"pattern": "は vs が"}] },
"available_minutes": 30
}
Output:
[
{ "task_id": "vocab_003_20260413", "type": "vocab", "content_ref": "vocab_003", "estimated_minutes": 10, "priority": "core" },
{ "task_id": "listen_001_20260413", "type": "listening", "content_ref": "listen_001", "estimated_minutes": 15, "priority": "core" },
{ "task_id": "speak_001_20260413", "type": "speaking", "content_ref": "speak_001", "estimated_minutes": 5, "priority": "bonus" }
]