anki

Create and browse Anki flashcards during coding sessions. Use when the user invokes /anki, asks to create a flashcard, or when you notice the user learning something new and worth remembering (a concept, trick, gotcha, or mental model).

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "anki" with this command: npx skills add doasfrancisco/anki-skill/doasfrancisco-anki-skill-anki

Anki Card Creator

Create flashcards from Claude Code. Scripts are bundled in ./scripts/.

Available operations

Create a card

python ./scripts/create_card.py \
  --deck "7. computer science" \
  --front "What does __slots__ do in Python?" \
  --back "Restricts instance attributes to a fixed set, saving memory by skipping the per-instance __dict__." \
  --tags "python,memory"

List cards (check for duplicates before creating)

python ./scripts/list_cards.py --query "tag:python added:7"
python ./scripts/list_cards.py --deck "7. computer science" --added 30

List decks (discover deck names)

python -c "import sys; sys.path.insert(0, './scripts'); from anki_connect import list_decks; print(list_decks())"

Card quality rules

The user has 226 leeches. Quality over quantity.

  1. Atomic — one fact per card. If the answer has "and", split it.
  2. Short, specific front — few words, one unambiguous answer. Not open-ended.
  3. Minimal back — no unnecessary text. If a structure speaks for itself, don't add explanation below it.
  4. Visual over prose — prefer file trees, code blocks, or diagrams over sentences when the answer is structural.
  5. No trivia — only things worth remembering long-term (concepts, gotchas, mental models).
  6. Tag consistently — use lowercase, comma-separated (e.g. python,decorators).

Good card

  • Front: "What's the file structure of a Claude Code skill?"
  • Back:
<skill>/
├── SKILL.md
└── scripts/
    ├── main.py
    └── helpers.py

Bad card

  • Front: "Explain Python's memory model, GIL, and garbage collection"
  • Back: (three paragraphs) — too many facts, split into separate cards.

Workflow

  1. Propose the card: show front, back, deck, and tags in a formatted block.
  2. Wait for user approval. Never create without explicit confirmation.
  3. Check duplicates with list_cards.py --query "<relevant keywords>" before creating.
  4. Create the card only after approval.
  5. Confirm with the note ID from the output.

Troubleshooting

If the connection fails, Anki desktop must be running with the AnkiConnect addon installed (addon code: 2055492159).

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

anki

No summary provided by upstream source.

Repository SourceNeeds Review
Automation

anki

No summary provided by upstream source.

Repository SourceNeeds Review
General

image-gen

Generate AI images from text prompts. Triggers on: "生成图片", "画一张", "AI图", "generate image", "配图", "create picture", "draw", "visualize", "generate an image".

Archived SourceRecently Updated
General

explainer

Create explainer videos with narration and AI-generated visuals. Triggers on: "解说视频", "explainer video", "explain this as a video", "tutorial video", "introduce X (video)", "解释一下XX(视频形式)".

Archived SourceRecently Updated