跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
效率与协作

Lecture To Notes

A Claude Code skill and CLI that converts lecture recordings into structured, traceable notes with a synced HTML viewer.

drpwchen · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add drpwchen/lecture-to-notes

技能说明


name: lecture-to-notes description: "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." allowed-tools: Read Write Edit Bash Glob Grep Agent

Lecture-to-Notes

Turn a lecture recording (video or audio-only) into structured notes. Every heavy stage runs locally at 0 Claude tokens; Claude only does the final synthesis. This page is the map; detail lives in reference/, one topic per file.

FileWhat is in it
reference/pipeline.mdPer-stage flags, thresholds, JSON schemas, timeouts, observability
reference/note-spec.mdNote quality spec, tier scoring, width table, synthesis prompt requirements
reference/segmented-mode.mdMulti-talk workshop folders → per-segment L2/L3 + Hub + web viewer
reference/multi-camera.mdOne long recording + many phone clips/photos → one timeline
reference/decisions.mdPost-mortems, benchmarks, wrong turns, VRAM measurements

HARD RULES

  1. ==ASK the user what language the speaker(s) used== (English / Mandarin / bilingual code-switching) before transcribing. There is no default and transcribe_video.py exits without --lang. A wrong guess makes Whisper hallucinate Chinese from accented English and the transcript is unusable.
  2. ==Never skip Stage D (VLM) or Stage E (grounding)== for speed or for a deadline. ==The user has not set a deadline; do not invent one.== If a stage really is too slow (>2 h ETA), report the ETA and ask.
  3. ==Never auto-correct the transcript.== Flag suspects, let synthesis resolve them. Both auto-correction passes ever built were measured and retired — see reference/decisions.md#asr-auto-correction. Do not add an auto-apply mode.
  4. ==Do not bypass the collapse auto-retry.== transcribe_video.py auto-runs retranscribe_segment.py --auto on detected token-collapse. If collapses survive that, escalate (wider beam + --no-repeat-ngram-size + a glossary), never skip.
  5. ==The VLM does not do OCR.== Stage D asks only for semantic signals. Text comes from Stage B quick_text, Stage B2 clean_text, or pdf_text.json. ocr.vlm_text is an always-empty compatibility field.
  6. ==Serialize all GPU work.== Whisper and the VLM may not run concurrently on an 8 GB card, and frame extraction must not run alongside transcription.
  7. ==On an 8 GB card, never exceed --batch-size 4 with --beam-size 10==, and never combine --beam-size 15 with sequential mode — that crashes (0xC0000005). The measured sweet spot is --batch-size 3 --beam-size 10.
  8. ==Director batch dispatch==: for a multi-lecture batch, dispatch Steps 1–9 as one subagent and Step 10 synthesis as a separate fresh subagent, spawned only after slides_grounded.json exists. A single subagent bounces during the long GPU waits and burns 30+ min of wall time per lecture.
  9. ==Order material by REAL CAPTURE TIME — never by filename, never by the printed agenda.== Filenames are labels, not clocks: a camcorder counter restarts across days (a two-day shoot has two 00000), a recorder's 240526_1119.mp3 sorts into the middle of the video files, and on-site -1-/-2- labels get stuck on the wrong file. Run scripts/batch/course_timeline.py BEFORE segmenting any multi-source course; manifest.json clip order and L1_coarse.md section order must both be built from it. An agenda is not a clock either — the 2024-05 Conference-Y conference ran ~25 min early on day 1 and ~35 min late on day 2, while its break gaps matched to the minute.
  10. ==🚫 PHI red line==: if the recording contains patient-identifiable content (case discussion, ward rounds, named patients), transcribe LOCAL ONLY — drop --engine groq. When unsure, ask; default to local.

Input types and routing

==Start here. route_inputs.py is the front door== — it classifies a folder and prints the ordered commands plus the questions a human must answer. It is plan-only: it never runs anything and never writes a file.

python <skill-dir>/scripts/route_inputs.py <material_dir> [--recursive] [--out-dir DIR] [--json]
What is in the folderSlide sourceRoute
Video, no deckframes from the videoPath A — Steps 5–7
Audio/video + PDF deck (==preferred==)PDF text + page rendersPath B — build_slides_from_pdf.py
Audio/video + loose slide images (≥3)the images themselvesPath B-images — build_slides_from_images.py
Audio only, no decknonePath C — transcript-only note
N-up handout PDFcropped tilesPath B-multi — crop_multiup_pdf.py first
Multi-talk workshop folderper segmentreference/segmented-mode.md
One long recording + many phone clips/photosper sourcereference/multi-camera.md
.pptx / .docx / .key—convert to PDF yourself first; there is no conversion step here

==Multi-source contract==: when two or more independent sources are present, establish the timeline BEFORE anything else — course_timeline.py <course_dir> for a course folder with a manifest (it writes _seg/real_timeline.json, maps photos onto the recordings, and with --reorder-manifest fixes clip order at the root), or media_capture_index.py --emit-alignment alignment.json for a loose material folder. ==Capture timestamps are HYPOTHESES; transcript cross-correlation (xcorr_media_offsets.py) is EVIDENCE.== A source whose reliable flag is false got its start from mtime or has none — it must not be aligned on. Nothing is ever auto-corrected: a claimed-vs-measured disagreement >5 s is flagged "conflict": true for a human to judge. Details in reference/multi-camera.md.

Pipeline

One command plus its purpose per step; flags, thresholds and outputs are in reference/pipeline.md.

Step

阅读完整来源 ↗