agentleFS
mtibebumtibebu/technical-learning-lab/.claude/skills/quiz-flashcards/SKILL.md

quiz-flashcards

Skill0 starsChanged 3 months agoMITView on GitHub

Generate or export quiz questions and flashcards for a topic as an Anki-importable CSV. Use when a training or mock-interview session produces quiz questions, or the user explicitly asks for flashcards/quizzes for a topic.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask one at a time where practical, or a small batch if the user prefers.

    line 16
  2. Very specific:

    Use quiz performance to inform (not unilaterally decide) the TRAINING.md status update — see train-topic.

    line 18
  3. Distinctive:

    Keep fronts short (a question or term), backs concise (a definition or answer) — these are spaced-repetition cards, not notes.

    line 31

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Quiz & Flashcards

Produces two things depending on what's asked: an interactive quiz (run in the conversation) and/or a flashcard CSV export (saved to disk for Anki import). They can come from the same question set.

Interactive quiz

  • 5-10 questions per topic session, mixed format: multiple choice, short answer, "explain X to me", small code-reading/output-prediction questions.
  • Ask one at a time where practical, or a small batch if the user prefers; give feedback on each answer rather than only a final score.
  • Use quiz performance to inform (not unilaterally decide) the TRAINING.md status update — see train-topic.

Flashcard CSV export

  • File path: flashcards/<slug>.csv, where <slug> matches the topic's slug in TRAINING.md / topics/. Append to an existing file rather than overwriting if the topic already has cards, unless the user asks to regenerate.
  • Format: plain CSV, no header row (Anki's basic CSV import expects none by default), two columns: front,back. Keep each field on one line — no literal newlines inside a field; use <br> if a card needs a line break, since Anki's importer renders basic HTML.
  • Quote any field containing a comma or double-quote per standard CSV rules (wrap in "...", escape internal " as "").
  • Keep fronts short (a question or term), backs concise (a definition or answer) — these are spaced-repetition cards, not notes. Don't just copy full paragraphs from the topic notes.

Example:

"What does RAG stand for?","Retrieval-Augmented Generation"
"Why use a vector DB instead of full-text search for embeddings?","Enables approximate nearest-neighbor search over dense vectors by semantic similarity, not keyword overlap"

Scope vs spaced-review

This CSV export is the input to Anki, which becomes the system of record for atomic fact/ definition/term recall (Anki owns its own scheduling from here — this project doesn't track it). Open-ended "explain this to me"/teach-it-back questions don't belong in the CSV — those go through the spaced-review skill's in-conversation review instead, since Anki's flip-card format can't grade them.

After exporting

Tell the user the file path and how many cards were added, and that Anki import is: Anki → File → Import → select the CSV → map columns to Front/Back → set "Fields separated by" to Comma.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.