Address first round of feedback

- Flashcards: whole card flips on click (both sides), 3D turn, swipe-away on grading,
  streak chip and flame bursts, bigger cards on desktop, arrow keys for everything
- Review and browse keep the sidebar on desktop
- Quizzes: live practice score, partial-credit explanation, time limit for shared exams
- Class page: items grouped by type inside each folder
- Import: copyable, editable instructions for outside chatbots
- Assistant: reads notes and links to library items

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
Elijah 2026-11-11 18:30:07 -07:00
parent c59591ccb9
commit aed14cd04f
13 changed files with 769 additions and 216 deletions

View file

@ -559,3 +559,73 @@ export function draftsFromValue(value: unknown): { items: ContentDraft[]; notice
collect(value, items, notices);
return { items, notices };
}
/* ------------------------------------------------------------------ */
/* Instructions for writing importable content with an outside chatbot */
/* ------------------------------------------------------------------ */
export const LLM_INSTRUCTIONS: Record<'quiz' | 'deck', string> = {
quiz: `You are writing practice questions that will be imported into a study app.
Reply with ONE JSON object and nothing else: no commentary and no Markdown code fence.
Use exactly this shape:
{
"kind": "quiz",
"title": "Short title",
"description": "One sentence about what this covers",
"questions": [
{
"type": "single",
"stem": "The question",
"options": [
{ "text": "Answer choice", "correct": true, "why": "Why this choice is right or wrong" }
],
"rationale": "Teaching explanation of the correct answer",
"topic": "Short topic label",
"difficulty": "medium"
}
]
}
Rules:
- "type" is "single" (multiple choice) or "multi" (select all that apply).
- "single" questions have exactly 4 options and exactly one with "correct": true.
- "multi" questions have 5 or 6 options, 2 to 5 of them correct, and the stem ends with "Select all that apply."
- Write NCLEX-style questions that test clinical judgment: a short client scenario, one clear question, priority wording where it fits (first, best, most important), and distractors that are plausible but wrong for a specific reason. Never use "all of the above" or "none of the above".
- Every option needs a one-sentence "why". The "rationale" explains the principle behind the correct answer.
- "topic" is a short label. Reuse the same label for related questions and keep the number of different topics small.
- "difficulty" is "easy", "medium" or "hard".
- Markdown is allowed inside strings (bold, lists, tables). Write line breaks inside strings as \\n.
- The output must be valid JSON: double quotes around every key and string, no trailing commas.
- Base everything on the material below. Do not add facts that are not in it.
Write 20 questions.
Material:
[paste your notes or lecture content here]`,
deck: `You are writing flashcards that will be imported into a study app.
Reply with ONE JSON object and nothing else: no commentary and no Markdown code fence.
Use exactly this shape:
{
"kind": "deck",
"title": "Short title",
"description": "One sentence about what this covers",
"cards": [
{ "front": "Term or question", "back": "Answer", "hint": "Optional memory aid", "tags": ["topic"] }
]
}
Rules:
- One fact or idea per card. Fronts are specific questions or terms; backs are short.
- For medications, put the generic name on the front and use a short Markdown list on the back: class, action, key adverse effects, nursing considerations.
- "hint" is optional. Leave it out or use "" when there is no good memory aid.
- Markdown is allowed inside strings (bold, lists, tables). Write line breaks inside strings as \\n.
- The output must be valid JSON: double quotes around every key and string, no trailing commas.
- Base everything on the material below. Do not add facts that are not in it.
Write 30 cards covering the most testable facts.
Material:
[paste your notes or lecture content here]`,
};