The Flashcards Skill: Make Great Cards With Claude Code and Codex | Space Blog

You ask the model how something works, read the explanation, and want to keep it. One line turns that moment into cards:

claude codecodex

> How does the TLS handshake work?<br>The handshake sets up an encrypted channel before any data flows.<br>The client and server agree on a cipher, the server proves its<br>identity with a certificate, and they derive a shared symmetric<br>key using asymmetric crypto. Traffic after that uses the faster<br>symmetric key.<br>> Make me flashcards for this. /flashcards<br>Creating deck "TLS Handshake" -> a1b2<br>Writing 5 cards...<br>Q: What does the TLS handshake establish before data is sent?<br>Q: Why does TLS switch to symmetric encryption after setup?<br>Q: What does the server's certificate prove in the handshake?<br>Done. 5 cards, synced to your devices.

That is the whole loop. You learn something in the conversation you are already having, then /flashcards drafts proper cards and writes them into Space. They sync to your phone before you close the terminal.

Any AI can spit out a hundred flashcards in a few seconds. The problem is that most of them are bad: they test recognition instead of recall, cram three facts onto one card, or answer with a list you will never reproduce from memory. Generation was never the hard part. Quality is. Our Space CLI post made the case for “bring your own AI”. This skill adds the part the raw pipe was missing: it already knows what a good card looks like.

What the skill does

It is two things in one file. First, a compact set of rules for what makes a card worth reviewing, drawn from the spaced-repetition research (Make It Stick, Fluent Forever, How We Learn). Second, the handful of Space CLI commands it is allowed to run, so it can create the deck, group the cards, and write them without you touching space card create yourself.

It runs in Claude Code and in OpenAI Codex. Same file, both tools.

Prerequisites

✨ You need the app and the CLI<br>Install the Space app and open it once so the local database exists. Then install the CLI: brew install space-org/tap/space-cli. Full install notes, including Windows and manual paths, live on the CLI page.

Install the skill

Both Claude Code and Codex read skills as a folder with a single SKILL.md inside. Save this file:

name: flashcards<br>description: Create high-quality spaced-repetition flashcards and save them to Space via the CLI. Triggers on requests to make flashcards or a deck about a topic or source.<br>argument-hint: [topic or source]<br>allowed-tools: Bash(space *)

# Create flashcards

Goal: cards that force active recall and build lasting understanding,<br>not cards that just store facts.

Input: $ARGUMENTS is the topic, source (a book, a note, a text), or<br>keywords to build cards from.

## What makes a good card

1. Force active recall. A card is a self-test, not a reading note. Ask<br>open questions where the answer must be reconstructed, not recognized.<br>2. One card, one fact. Each card asks for exactly one thing. Keep it as<br>short as possible without losing clarity.<br>3. One unambiguous answer. The question must have a single correct answer.<br>4. Understanding before memorizing. Cover fundamentals first, then build<br>up. Aim for connected knowledge, not isolated facts.<br>5. Elaborate and connect. Link the new fact to something known, a concrete<br>image, a vivid example. Extra retrieval paths make recall easier.<br>6. Integrate context into the question. Good: "What does ATP mean in<br>biochemistry?" Bad: "[Biochemistry] What does ATP mean?"<br>7. Break up lists. Turn an enumeration into single questions, or use<br>overlapping cards (A then B, B then C).<br>8. Avoid confusion. Give similar concepts distinguishing context.<br>9. Group related cards. Build from a base concept toward combinations.<br>10. Ask both directions. A to B and B to A strengthens retention.<br>11. Timestamp perishable facts. Add "as of [year]" to current numbers.

Avoid: trivial facts, answers longer than three or four lines, ambiguous<br>questions, opinions instead of facts, lists as an answer.

## Format

Space uses a Q:/A: format. Never use cloze deletions ({{c1::...}}).<br>Never use em dashes or en dashes; use a comma, colon, or two sentences.

Q: [Precise question with context built in]<br>A: [Short, clear answer]

## Save the cards in Space

Use the Space CLI. It writes directly to the local database that syncs<br>with the app.

space deck create "Deck name" # returns a deck id<br>space group create --name "Group name"<br>space card create [--group ] \<br>--front "Question?" --back "Answer."

## Quality check

Before saving each card, confirm: one fact only, one correct answer,<br>forces recall not recognition, answer is short, context is built into<br>the question, similar cards stay distinct.<br>Where it goes depends on the tool:

ToolPathClaude Code~/.claude/skills/flashcards/SKILL.mdCodex~/.agents/skills/flashcards/SKILL.md<br>The name and description fields are all both tools need. The argument-hint and allowed-tools lines are Claude...