Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Japanese SRS Scheduler (SM-2)

    1

    Exact spaced-repetition scheduling for Japanese decks: rate cards, see what's due, pick new JLPT words, forecast reviews.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Japanese SRS Scheduler (SM-2)

    Japanese SRS Scheduler (SM-2)

    Example session with this skill installed

    Today I reviewed 図書館 (Good), 駅 (Again) and 勉強する (Easy). Update vocab.json, then tell me what's coming up this week. I'm targeting N4, Lesson 26.

    • Read your context and instructions
    • Compiled the japanese srs scheduler

    Summary

    Updated 3 cards in vocab.json. Tomorrow: 2 reviews and 2 new N4 words. One card is a leech.

    Today's reviews

    CardRatingIntervalEaseNext reviewStage
    図書館Good6 → 15 days2.5 → 2.58 Novreview
    駅Again15 → 1 day2.5 → 2.325 Octrelearning
    勉強するEasy1 → 8 days2.5 → 2.651 Novlearning

    Tomorrow (25 Oct)

    • Due: 駅 (relearning), 忘れる
    • New: 覚える, 調べる (N4 + Lesson 26, priority 250 each)

    Next 7 days

    25262728293031
    2010000

    Deck health

    8 cards: 3 new, 2 learning, 2 review, 1 relearning. Average ease 2.22.
    Leech: 忘れる (ease stuck at the 1.3 floor). Drilling it again won't help much; rewrite the card with a new mnemonic or a context sentence.

    python3 scripts/srs.py review vocab.json --card 図書館 --rating good --write
    python3 scripts/srs.py due vocab.json --new 2 --jlpt n4 --focus-lesson "Lesson 26"
    

    Next steps

    • Want me to rewrite the 忘れる card?
    • Your week is light. You could raise new cards to 5 a day.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Rate a card Again, Hard, Good or Easy and get the exact next review date, computed by a tested SM-2-style script instead of the model doing arithmetic in its head. Works on a plain CSV or JSON deck.

    Features

    • review: rate a card and save the new interval, ease and date to your deck
    • due: today's reviews (oldest first) plus new words, weighted toward your JLPT level, lesson or a priority word list
    • forecast: how many reviews land on each of the next N days
    • stats: new / learning / review / mature counts, average ease and leech cards
    • level: XP and level from your total correct answers
    • Adds SRS fields to any deck automatically

    Also useful for developers

    The skill includes the full algorithm as a spec, so your agent can review SRS code in your own app. It specifically checks the common bug where Hard schedules further out than Good.

    Pairs with the Japanese Vocab Quiz Master: quiz results become ratings you can apply in one step.

    Requires Python 3.8+. Deck must be in CSV or JSON format with specific scheduling fields. Does not support audio or image assets.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 24 days ago

    Requires

    Python 3.8+
    Python

    Permissions

    Terminal / Shell
    Read Files
    Write Files

    File Scopes

    *.csv
    *.json

    Runs a bundled Python script (standard library only) to calculate review dates. With --write it updates the scheduling fields in the deck file you name, nothing else. No network, no environment variables.

    Listed24 days ago

    What's inside

    Frequently Asked Questions

    This skill automates the math behind the SuperMemo-2 (SM-2) algorithm, providing mathematically precise review dates, identifying difficult 'leech' cards, and prioritizing new vocabulary based on JLPT levels.

    The skill requires a Python 3.8+ environment and is compatible with any AI agent or platform that can execute local Python scripts and read/write CSV or JSON files.

    You will receive the 'scripts/srs.py' standalone Python script, documentation on the required data schema for your CSV/JSON decks, and a guide on integrating the scheduler with your AI agent.

    No, this skill is designed purely for scheduling and metadata management; it calculates when you should see a card, but it does not modify the actual Japanese text or definitions.

    The scheduler provides a 'load forecasting' feature that analyzes your current intervals to predict future review spikes, helping you decide whether to add new cards today without overwhelming your future schedule.

    It schedules flashcard reviews with an SM-2-style spaced repetition algorithm. Rate a card and it writes the next interval and date into your deck; ask what's due and it builds today's queue and picks new words weighted toward your JLPT level.

    Any agent that follows the open SKILL.md standard, including Claude Code, Cursor, VS Code Copilot, Codex CLI and Gemini CLI. The agent picks the skill up from its description, so you just ask in plain English.

    Point your agent at a CSV or JSON deck and say things like "rate 食べる Good", "what's due today?", "forecast the next 2 weeks" or "which cards are leeches?".

    It is SM-2-style with four buttons, like Anki's classic scheduler: Hard ×1.2, Good × ease, Easy × ease × 1.5, with ease between 1.3 and 3.0. The full spec is inside the skill.

    New in Education & Learning