alt-import

alt-import

Exam Radar is OPTIMETA's Alt plugin. From lecture-recording transcripts it extracts the topics a professor verbally emphasized, ranks them by exam probability, and lets the user triage each into one of three zones. Its 복사 button emits a fixed markdown form. This skill ingests that form.

PAIDEIA already has one exam-probability signal — HW density (course-index/coverage.md). Exam Radar adds a second, independent one — lecture emphasis. The two corroborate where they agree and expose blind spots where they diverge.

Premise (do not break). HW density remains the primary Exam tier. Lecture emphasis is layered on as annotation and a second opinion — it is surfaced, never substituted. As with a user-declared weak zone, a single lecture signal does not auto-upgrade an HW-based tier (mirror course-builder's rule). What it does is flag divergences for the user to judge.

---

1. The export format (exam-radar:v1)

# Exam Radar 작전 — <course>
<!-- exam-radar:v1 source=alt -->

- 코스: <course>
- 시험까지: <D-N>
- 토픽: 총 <N>개 (골드존 <G> · 버려도 안전 <D>)
- 버려도 안전 비중: 전체의 <P>%

## 지금 할 것 — 골드존 (시험확률 높음 · 아직 약함)
1. <topic> · 시험확률 <p>%[ · 🎙]
...

## 이미 다진 것 (잘 알거나 시험에 덜 나옴)
- <topic> · 시험확률 <p>%
...

## 버려도 안전 (안 해도 되는 것)
- <topic> · 시험확률 <p>%
...

Parse rules:

• Detect by the <!-- exam-radar:v1 marker. Parse the vN integer; if > 1, warn and parse the v1 fields best-effort (ignore unknown ones).
• Meta: read - 코스:, - 시험까지: (D-N), and the count line.
• Zones: three ## headings →
  • 지금 할 것 — 골드존 → zone gold (high exam-prob, low self-confidence).
  • 이미 다진 것 → zone strong (already known or low exam-prob).
  • 버려도 안전 → zone skip (safe to drop).
• Each topic line: <name> · 시험확률 <p>%, optionally · 🎙 (the professor verbally stressed it). The leading 1. / - is just list markup. Parse name, integer p (0–100), and the 🎙 flag.
• Be lenient on whitespace and the leading marker. A zone with (없음) / (아직 없음 …) is empty.