drpwchen
UserLecture recordings → structured grounded notes + a synced HTML viewer: video, timestamped transcript and curated summary on one page. Local GPU pipeline (Whisper ASR · slide extraction · OCR · VLM signals · capture-time alignment). Claude Code skill + plain CLI.
Categories
Indexed Skills (4)
lecture-to-notes
Turn a lecture/conference recording (video or audio: MOV/MP4/M4A/MP3/WAV) into structured vault notes via local GPU transcription + slide extraction — 演講影片, 演講音檔, 上課錄影, '整理演講', '影片轉筆記', '音檔轉筆記', or a dropped media file. Handles batch runs.
textbook-to-md
Convert PDF/EPUB textbooks to searchable markdown files for an AI agent's own reference. Use this skill whenever: (1) the user asks to convert a textbook/PDF chapter to markdown, (2) you need to search textbook content and no markdown version exists yet, (3) batch-converting a set of reference books into a knowledge base. This is a 0-token local conversion — no vision model needed.
paper-digest
Produce a content/knowledge digest of ONE paper for fast absorption of its full content — not a quality critique. Use when the user wants to "整理內容", "快速吸收", "知識整理", "內容平讀", or when /paper-sync dispatches a 📚內容 pick. The digest reorganizes the paper's full text into a teaching-style structured note (structure routed by paper type) plus self-test review cards pushed to the 複習頁 (configured `review_site.url`). REQUIRES full text: no full text → STOP and report 缺全文, never produce an abstract-only digest. NOT a critical appraisal (that is /paper-review) and NOT a multi-paper synthesis.
paper-review
Deep single-paper academic analysis — journal credibility, author profiling, reference verification, citation impact, and critical appraisal. Like a teaching hospital journal club report. Use this skill whenever the user wants to deeply review, evaluate, or dissect a single academic paper, prepare a journal club presentation, verify a paper's references, check an author's track record, or do any thorough paper-level analysis. Also trigger when the user says "review this paper", "深度評讀", "journal club", "論文評讀", "幫我看這篇", or provides a DOI/PMID asking for analysis. NOT for multi-paper systematic reviews or standalone evidence grading.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.