Flashcards

SkillDocs & knowledge

Turn vault notes, lessons, or a topic into spaced-repetition flashcards and quiz the user on due cards. Use when the user wants to study, review, memorize, retain notes, or asks to be quizzed. Stores cards as a simple JSON deck the agent can schedule reviews against.

Use Flashcards in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Flashcards and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Flashcards skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Add Ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

FlashcardsStart free

What this skill tells your AI

The instructions your AI receives, as published by thesmokedev/taskchad-os in optional-skills/productivity/flashcards/SKILL.md and read by Ahel’s review.

Generate spaced-repetition flashcards from notes and run review sessions.

Deck format

One JSON file per deck under vault/flashcards/<deck>.json:

[
  {
    "id": "uuid",
    "front": "What does the recall pipeline do?",
    "back": "Surfaces durable memory relevant to the current message.",
    "ease": 2.5,
    "interval_days": 0,
    "due": "2026-06-25",
    "reps": 0
  }
]

Generating cards

From a note or topic, extract atomic question/answer pairs — one fact per card, front phrased as a question, back as a short answer. Avoid compound cards. Aim for 5–15 cards per note; quality over volume.

Review session

  1. Load the deck, filter to cards where due <= today.
  2. Show front, wait for the user's answer, then reveal back.
  3. Ask the user to grade 0–5 (0 = blank, 5 = perfect).
  4. Update schedule with the SM-2 algorithm in scripts/sm2.py and persist.
uv run python optional-skills/productivity/flashcards/scripts/sm2.py --grade 4 \
  --ease 2.5 --interval 1 --reps 2

End the session with a one-line tally (reviewed / again / mastered).

Signals

GitHub stars
26
Forks
5
Last commit
Sep 2026

Ahel review

  • K6low
    bundled executables the agent is told to run

Automated review, not a security audit. Ruleset v1+k2.

Advanced
Item type
skill
Key
flashcards-thesmokedev
Source
github.com/thesmokedev/taskchad-os