{"slug": "skill-to-create-flashcards", "title": "Skill to Create Flashcards", "summary": "A new skill for Claude Code and Codex lets users create high-quality spaced-repetition flashcards from any conversation, enforcing rules from learning research to ensure active recall and effective memorization. The skill generates cards in Q/A format and saves them to Space via CLI, syncing to mobile devices automatically.", "body_md": "# The Flashcards Skill: Make Great Cards With Claude Code and Codex\n\nYou ask the model how something works, read the explanation, and want to keep it. One line turns that moment into cards:\n\nThat is the whole loop. You learn something in the conversation you are already having, then `/flashcards`\n\ndrafts proper cards and writes them into Space. They sync to your phone before you close the terminal.\n\nAny 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](/blog/space-cli) 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.\n\n## What the skill does\n\nIt 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`\n\nyourself.\n\nIt runs in [Claude Code](https://claude.com/claude-code) and in [OpenAI Codex](https://developers.openai.com/codex). Same file, both tools.\n\n## Prerequisites\n\n## Install the skill\n\nBoth Claude Code and Codex read skills as a folder with a single `SKILL.md`\n\ninside. Save this file:\n\n```\n---\nname: flashcards\ndescription: 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.\nargument-hint: [topic or source]\nallowed-tools: Bash(space *)\n---\n\n# Create flashcards\n\nGoal: cards that force active recall and build lasting understanding,\nnot cards that just store facts.\n\nInput: $ARGUMENTS is the topic, source (a book, a note, a text), or\nkeywords to build cards from.\n\n## What makes a good card\n\n1. Force active recall. A card is a self-test, not a reading note. Ask\n   open questions where the answer must be reconstructed, not recognized.\n2. One card, one fact. Each card asks for exactly one thing. Keep it as\n   short as possible without losing clarity.\n3. One unambiguous answer. The question must have a single correct answer.\n4. Understanding before memorizing. Cover fundamentals first, then build\n   up. Aim for connected knowledge, not isolated facts.\n5. Elaborate and connect. Link the new fact to something known, a concrete\n   image, a vivid example. Extra retrieval paths make recall easier.\n6. Integrate context into the question. Good: \"What does ATP mean in\n   biochemistry?\" Bad: \"[Biochemistry] What does ATP mean?\"\n7. Break up lists. Turn an enumeration into single questions, or use\n   overlapping cards (A then B, B then C).\n8. Avoid confusion. Give similar concepts distinguishing context.\n9. Group related cards. Build from a base concept toward combinations.\n10. Ask both directions. A to B and B to A strengthens retention.\n11. Timestamp perishable facts. Add \"as of [year]\" to current numbers.\n\nAvoid: trivial facts, answers longer than three or four lines, ambiguous\nquestions, opinions instead of facts, lists as an answer.\n\n## Format\n\nSpace uses a Q:/A: format. Never use cloze deletions ({{c1::...}}).\nNever use em dashes or en dashes; use a comma, colon, or two sentences.\n\nQ: [Precise question with context built in]\nA: [Short, clear answer]\n\n## Save the cards in Space\n\nUse the Space CLI. It writes directly to the local database that syncs\nwith the app.\n\nspace deck create \"Deck name\"            # returns a deck id\nspace group create <DECK-ID> --name \"Group name\"\nspace card create <DECK-ID> [--group <GROUP-ID>] \\\n  --front \"Question?\" --back \"Answer.\"\n\n## Quality check\n\nBefore saving each card, confirm: one fact only, one correct answer,\nforces recall not recognition, answer is short, context is built into\nthe question, similar cards stay distinct.\n```\n\nWhere it goes depends on the tool:\n\n| Tool | Path |\n|---|---|\n| Claude Code | `~/.claude/skills/flashcards/SKILL.md` |\n| Codex | `~/.agents/skills/flashcards/SKILL.md` |\n\nThe `name`\n\nand `description`\n\nfields are all both tools need. The `argument-hint`\n\nand `allowed-tools`\n\nlines are Claude Code extras and Codex ignores them. In Codex, shell access to `space`\n\nruns through your approval and sandbox settings, so allow it when prompted.\n\nHow you call it\n\nIn Claude Code, type `/flashcards <topic>`\n\n. In Codex, open `/skills`\n\nand pick it, type `$flashcards`\n\n, or just describe the task and let Codex pick the skill from its description.\n\n## What it runs under the hood\n\nThere is no magic. The skill turns its draft into the same CLI calls you could type by hand, so nothing is hidden and you can edit anything afterwards:\n\n```\nspace deck create \"TLS Handshake\"\nspace group create a1b2 --name \"Key exchange\"\nspace card create a1b2 --group c3d4 \\\n  --front \"Why does TLS switch to symmetric encryption after the handshake?\" \\\n  --back \"Asymmetric crypto sets up a shared key but is slow. Symmetric encryption is far faster for the actual traffic.\"\n```\n\nThe real difference is the cards themselves. The skill writes the question on the left, not the one on the right:\n\n| Good (recall, context built in) | Bad (recognition, label prefix) |\n|---|---|\n| Why does TLS switch to symmetric encryption after the handshake? | [TLS] Symmetric or asymmetric for traffic? |\n| What does the server’s certificate prove during the handshake? | True or false: the certificate proves identity. |\n\nThe left column forces you to reconstruct the answer. The right column you can guess or recognize, which feels like learning but is not.\n\n## Sync everywhere\n\nCards the skill creates show up on your phone, tablet, and desktop. PowerSync pushes every CLI write to the server and from there to your other devices. No manual sync, no separate login in the CLI.\n\n## Why this works\n\nThree well-documented effects do the work: retrieval practice beats rereading by a wide margin ([Roediger and Karpicke, 2006](https://doi.org/10.1111/j.1467-9280.2006.01693.x)), the [generation effect](https://en.wikipedia.org/wiki/Generation_effect) anchors knowledge you produce yourself, and [elaboration](https://en.wikipedia.org/wiki/Elaborative_interrogation) builds extra retrieval paths when new knowledge links to the old. The skill bakes those into every card so you do not have to remember them each time.\n\nIf you want the full reasoning behind the rules, including which ones matter most, read [How to write flashcards that stick](/blog/how-to-write-good-flashcards).\n\n**Ready?** Install the [app](/download) and the CLI, drop the `SKILL.md`\n\ninto `~/.claude/skills/flashcards/`\n\nor `~/.agents/skills/flashcards/`\n\n, and run `/flashcards <your topic>`\n\n. Your data stays yours, exports as JSON or CSV whenever you want, and syncs across every device.", "url": "https://wpnews.pro/news/skill-to-create-flashcards", "canonical_source": "https://getspace.app/blog/flashcards-skill", "published_at": "2026-06-15 09:03:34+00:00", "updated_at": "2026-06-15 09:12:24.782949+00:00", "lang": "en", "topics": ["ai-tools", "developer-tools", "large-language-models"], "entities": ["Claude Code", "OpenAI Codex", "Space", "Space CLI"], "alternates": {"html": "https://wpnews.pro/news/skill-to-create-flashcards", "markdown": "https://wpnews.pro/news/skill-to-create-flashcards.md", "text": "https://wpnews.pro/news/skill-to-create-flashcards.txt", "jsonld": "https://wpnews.pro/news/skill-to-create-flashcards.jsonld"}}