Generate Doc Template
jeremylongshore/tons-of-skills-marketplace
Generates on-brand document and deck templates — letterhead, slide, and one-pager — as SVG from the active brand profile, with editable title, subtitle, and body zones.
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…
Install Lecture To Notes
$ npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install drpwchen/lecture-to-notes lecture-to-notes --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
Claude Code skills documentation · loads skills from .claude/skills/
Install the "lecture-to-notes" agent skill from https://github.com/drpwchen/lecture-to-notes/tree/main into .claude/skills/lecture-to-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lecture-to-notes", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install drpwchen/lecture-to-notes lecture-to-notes --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lecture-to-notes" agent skill from https://github.com/drpwchen/lecture-to-notes/tree/main into .agents/skills/lecture-to-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lecture-to-notes", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install drpwchen/lecture-to-notes lecture-to-notes --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "lecture-to-notes" agent skill from https://github.com/drpwchen/lecture-to-notes/tree/main into .cursor/skills/lecture-to-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lecture-to-notes", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install drpwchen/lecture-to-notes lecture-to-notes --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "lecture-to-notes" agent skill from https://github.com/drpwchen/lecture-to-notes/tree/main into .gemini/skills/lecture-to-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lecture-to-notes", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install drpwchen/lecture-to-notes lecture-to-notesInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "lecture-to-notes" agent skill from https://github.com/drpwchen/lecture-to-notes/tree/main into .github/skills/lecture-to-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lecture-to-notes", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install drpwchen/lecture-to-notes lecture-to-notes --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "lecture-to-notes" agent skill from https://github.com/drpwchen/lecture-to-notes/tree/main into .opencode/skills/lecture-to-notes/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lecture-to-notes", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
lecture-to-notes- GitHub stars
- 108
- Token cost
- ~4.9k tokens
- SKILL.md length
- 1,913 words
- Files
- 87 (incl. scripts)
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
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…
- Works in 12 steps: Ask the language (mandatory, no command) → Set up the lecture directory → GPU pre-flight → …
- Tasks that involve Transcription
- SKILL.md covers HARD RULES, Input types and routing, Pipeline and Edge cases, plus 3 more sections
- Calls python, ollama and pip
What it does
Lecture To Notes is an agent skill from drpwchen/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.
Its SKILL.md is about 4.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 91 other files, including scripts (for example `.github/workflows/secret-scan.yml`, `CHANGELOG.md` and `README.md`).
It sits in Media & Creative, covering Transcription and Slides and decks. The repository describes itself as: Lecture recordings → structured grounded notes + a synced HTML viewer: video, timestamped transcript and curated summary on one page. Local GPU pipeline (Whisper ASR · slide… The licence is MIT.
When your agent uses it
- Tasks that involve Transcription
- Tasks that involve Slides and decks
Example prompts
- “/lecture-to-notes”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read, Write, Edit, Bash, Glob, Grep, Agent
Workflow steps
12 steps, taken from the step headings in SKILL.md.
- Ask the language (mandatory, no command)
- Set up the lecture directory
- GPU pre-flight
- Transcribe
- Stage A: frame extraction (Path A only)
- Stage B: quick OCR + entropy (Path A only)
- alt — Path B / B-images bridge
- Stage C: semantic dedup (Path A only)
- Stage B2: high-quality OCR (Surya)
- Stage D: VLM signals
- Stage E: transcript grounding
- Flag suspect ASR tokens
What it can do on your machine
Read from SKILL.md and the folder at commit 79053a3. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditBashGlobGrepAgent
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/, which the agent can run.
Shell commands in SKILL.md call:
pythonollamapip
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Lecture To Notes loads about 4.9k tokens when it runs. Until then it costs about 64 tokens; SKILL.md has 1,913 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Write, Edit, Bash, Glob, Grep, Agent
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from drpwchen/lecture-to-notes at commit 79053a3, republished under its MIT licence (© drpwchen). 1,913 words, ~4,914 tokens.
Download SKILL.mdSave it as
.claude/skills/lecture-to-notes/SKILL.md (or your agent's skills folder). This skill also uses 86 other files; get the full folder from GitHub.- 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.
| File | What is in it |
|---|---|
reference/pipeline.md | Per-stage flags, thresholds, JSON schemas, timeouts, observability |
reference/note-spec.md | Note quality spec, tier scoring, width table, synthesis prompt requirements |
reference/segmented-mode.md | Multi-talk workshop folders → per-segment L2/L3 + Hub + web viewer |
reference/multi-camera.md | One long recording + many phone clips/photos → one timeline |
reference/decisions.md | Post-mortems, benchmarks, wrong turns, VRAM measurements |
HARD RULES
- ==ASK the user what language the speaker(s) used== (English / Mandarin /
bilingual code-switching) before transcribing. There is no default and
transcribe_video.pyexits without--lang. A wrong guess makes Whisper hallucinate Chinese from accented English and the transcript is unusable. - ==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.
- ==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. - ==Do not bypass the collapse auto-retry.==
transcribe_video.pyauto-runsretranscribe_segment.py --autoon detected token-collapse. If collapses survive that, escalate (wider beam +--no-repeat-ngram-size+ a glossary), never skip. - ==The VLM does not do OCR.== Stage D asks only for semantic signals. Text
comes from Stage B
quick_text, Stage B2clean_text, orpdf_text.json.ocr.vlm_textis an always-empty compatibility field. - ==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.
- ==On an 8 GB card, never exceed
--batch-size 4with--beam-size 10==, and never combine--beam-size 15with sequential mode — that crashes (0xC0000005). The measured sweet spot is--batch-size 3 --beam-size 10. - ==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.jsonexists. A single subagent bounces during the long GPU waits and burns 30+ min of wall time per lecture. - ==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's240526_1119.mp3sorts into the middle of the video files, and on-site-1-/-2-labels get stuck on the wrong file. Runscripts/batch/course_timeline.pyBEFORE segmenting any multi-source course;manifest.jsonclip order andL1_coarse.mdsection 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. - ==🚫 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 folder | Slide source | Route |
|---|---|---|
| Video, no deck | frames from the video | Path A — Steps 5–7 |
| Audio/video + PDF deck (==preferred==) | PDF text + page renders | Path B — build_slides_from_pdf.py |
| Audio/video + loose slide images (≥3) | the images themselves | Path B-images — build_slides_from_images.py |
| Audio only, no deck | none | Path C — transcript-only note |
| N-up handout PDF | cropped tiles | Path B-multi — crop_multiup_pdf.py first |
| Multi-talk workshop folder | per segment | reference/segmented-mode.md |
| One long recording + many phone clips/photos | per source | reference/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 1 — Ask the language (mandatory, no command)
English / Mandarin / bilingual? Accented speakers? Code-switching mid-sentence? Use AskUserQuestion if the user has not said. HARD RULE 1.
Step 2 — Set up the lecture directory
One directory per lecture holds every intermediate; name it
{date}_{speaker}_{topic}, the shape finalize_to_vault.py parses.
Step 3 — GPU pre-flight
python <skill-dir>/scripts/gpu_check.py --out-dir "$OUT_DIR" --min-free-mb 6000Gate before transcription and again before Stage D. Exit 0 proceed, 1 warn
and proceed, 2 blocked — surface it, ==do not retry in a loop==. A card whose
total VRAM is under the threshold (2–4 GB laptops) is GPU_TOO_SMALL, exit
0: not contention, nothing will free up — proceed with the CPU path
(transcribe_video.py --device cpu --model small, or --engine groq).
→ reference/pipeline.md#gpu-check
Step 4 — Transcribe
python <skill-dir>/scripts/transcribe_video.py "<media>" \
--output-dir "$OUT_DIR" --lang <zh|en|bilingual|auto> \
--batch-size 3 --beam-size 10Local faster-whisper by default; --engine groq is an optional offload (HARD
RULE 9). Default model alias is breeze25 (needs a local model dir); on a
machine without one, pass --model large-v3, which faster-whisper downloads.
Recordings over ~30 min go through the chunked runner instead.
→ reference/pipeline.md#transcription
Step 5 — Stage A: frame extraction (Path A only)
python <skill-dir>/scripts/extract_slides.py "<video>" --output-dir "$OUT_DIR" --interval 15Writes slides/frame_NNNN.jpg + slides/timestamps.json, phash-deduping adjacent
near-identical frames. Path B/B-images skip this. → reference/pipeline.md#stage-a
Step 6 — Stage B: quick OCR + entropy (Path A only)
python <skill-dir>/scripts/quick_ocr.py "$OUT_DIR"RapidOCR on every frame → slides_raw.json. ==Required==: without it every slide
looks decorative to the Stage D gate. → reference/pipeline.md#stage-b
Step 6-alt — Path B / B-images bridge
python <skill-dir>/scripts/build_slides_from_pdf.py "$OUT_DIR" [--audio-duration-sec N]
python <skill-dir>/scripts/build_slides_from_images.py "<img_dir>" -o "$OUT_DIR" [--audio-duration-sec N]Either bridge emits slides_raw.json + slides_dedup.json directly, replacing
Steps 5–7. → reference/pipeline.md#path-b
Step 7 — Stage C: semantic dedup (Path A only)
python <skill-dir>/scripts/dedup_semantic.py "$OUT_DIR"Merges adjacent frames by text-subset or layout similarity, marks
dedup.is_canonical. Output slides_dedup.json.
→ reference/pipeline.md#stage-c
Step 8 — Stage B2: high-quality OCR (Surya)
python <skill-dir>/scripts/ocr_surya.py "$OUT_DIR" [--resume]Surya in its own venv on canonical text-bearing slides, RapidOCR as the shallow
fallback. Adds ocr.clean_text / ocr_engine / ocr_confidence. ==Updates
slides_dedup.json in place== (one-time backup slides_dedup.pre_b2.json) and
writes slides_ocr.json. Path B skips it — pdf_text is already clean. Without
a Surya venv it warns and routes everything to RapidOCR rather than failing.
→ reference/pipeline.md#stage-b2
Step 9 — Stage D: VLM signals
python <skill-dir>/scripts/vlm_signals.py "$OUT_DIR" --model minicpm-v:8b --num-ctx 4096Semantic signals per canonical slide, behind a 4-condition pre-skip gate for
decorative frames. Re-check the GPU first (Step 3). Output slides_vlm.json.
scripts/ocr_slides.py is a deprecated shim forwarding here, same argv and
outputs. → reference/pipeline.md#stage-d
Step 10 — Stage E: transcript grounding
python <skill-dir>/scripts/ground_slides.py "$OUT_DIR"Pure Python, 0 LLM calls. Ties each canonical slide to the words spoken over it.
Output slides_grounded.json — the input to synthesis.
→ reference/pipeline.md#stage-e
Step 11 — Flag suspect ASR tokens
python <skill-dir>/scripts/flag_asr_suspects.py --dir "$OUT_DIR"Runs HERE, after Stage E: the slide glossary it needs comes from
slides_grounded.json. Writes asr_suspects.txt; ==the transcript is left
byte-identical==. Treat each line as a question, never a substitution.
→ reference/pipeline.md#asr-suspects
Show full SKILL.md (766 more words)Show less
Step 12 — Chunked pre-summarization (long lectures only)
Over ~30 min / 25 k tokens of transcript, offload chunk summaries to a Sonnet
subagent instead of reading the whole transcript into main context. Coverage
guards ([CHUNK_END], [CONTINUE_NEEDED], expected-chunk count) are mandatory.
→ reference/pipeline.md#chunked-summarization
Step 13 — Stage F: synthesis (Claude)
Two passes for batches and long lectures — ==Tier-pass then Write-pass==:
- Tier-pass subagent reads
slides_grounded.json+transcript.txt+pdf_text.json, applies the tier scoring rules, writes onlyslides_final.json(integertier,attachment_name,embed_width,section_suggestion). This file is the frozen tier authority. - Write-pass subagent reads the frozen
slides_final.json+ transcript + slide text, writesnote_draft.mdwith[[EMBED sN]]placeholders only — no paths, widths or callouts.
One pass is fine for one short lecture; splitting them stops the writer from
simplifying structure to make its own embed audit pass. → reference/note-spec.md
(mandatory: quality spec, tier rules, prompt requirements)
Step 14 — Render, finalize, audit
python <skill-dir>/scripts/render_embeds.py "$OUT_DIR" --note note_draft.md --in-place
python <skill-dir>/scripts/finalize_to_vault.py "$OUT_DIR" [--vault-root PATH]
python <skill-dir>/scripts/audit_note.py "<note path>" --mode lecture --grounding "$OUT_DIR"render_embeds.py expands placeholders to col-0 callouts with path + width and
audits Tier-1/2 coverage; finalize_to_vault.py copies cited slides + the note
into the vault; the auditor is the gate. ==Always pass --grounding== — without
it the caption↔frame check only warns. → reference/note-spec.md
Draft review exemption: this output is machine-transcribed and synthesized —
write to the inbox without showing a draft; the user reviews in Obsidian.
Step 15 — Web viewer export (default whenever there is video)
python <skill-dir>/scripts/build_single_talk_web.py "$OUT_DIR" --plan seg_plan.json
# … Stage F writes the L3/ files … then:
python <skill-dir>/scripts/build_single_talk_web.py "$OUT_DIR" --plan seg_plan.json --exportA single talk gets the synced HTML viewer by default, not just workshops.
==Stage F authors the segment plan itself== (JSON list:
seg/start/end/slug/title_zh, derived from the transcript + slide topics — no
human segmentation needed); ==content sections = more segments, not more
headings==, the viewer builds exactly two chapters per segment. The script assembles manifest + segments.json + L2 slices + HUB
skeleton from transcript.json, and ==auto-appends an L3-only 全場總整理
overview segment== (sorted first — many segments still need one place listing
everything; the HUB never renders in the viewer). Stage F then writes one
L3_segNN_<slug>.md per segment (==image embeds by basename only, timecodes
`(V1 MM:SS)`==) plus the overview note — content shape picked by ==one
question: is this a single body of knowledge?== (single talk → pearls +
per-segment one-liners; same-lecturer arc → thematic reorganization with
sources; multi-speaker workshop → ==catalog only, never forced synthesis== —
spec in reference/pipeline.md#web-export); --export refuses while any L3
is missing.
Compression default is ==H.265 CRF 24== (self-use; --codec h264 when sharing
to machines you can't verify). Multi-talk workshops keep their own flow →
reference/segmented-mode.md. → reference/pipeline.md#web-export
Edge cases
- Audio only, no deck → transcript-only note using
# 逐段筆記instead of# 逐投影片筆記. - N-up handout PDF → render one mid page and ==look at it== before deciding
the grid; heuristics are unreliable on slide-heavy PDFs. Then
crop_multiup_pdf.py <pdf> <out_dir> --expected-rows R --expected-cols C. Pages that are genuinely 1-up (title pages) are handled per page, not forced into the consensus grid. - Very long lecture (>90 min) → chunked runner for transcription, Step 12 for reading it. Batch of recordings → transcribe strictly sequentially; ~4.5 GB RAM per faster-whisper instance.
- One talk split across several files → one note, not several.
- Slides English, speaker Mandarin → keep both; the deck gives terms, the transcript gives the explanation.
- Speaker asked not to be recorded → exclude that content.
- Dense text handout, not a slide deck → primary source, but drop the slide-by-slide structure.
- CJK path failures (exit 127 / 3221226505) → extract audio with ffmpeg
separately first; the script reuses a validated
audio.wav.
Optional infrastructure
Everything below is ==this machine's setup, not a requirement== — nothing in the pipeline depends on any of it, and the generic alternative is inline.
| Used for | Generic alternative |
|---|---|
job_runner.py wrapping long GPU jobs (tree-kills children on timeout) | plain timeout <n> <cmd>, or run in the foreground |
gpu_lease.py / a pause-flag file between concurrent batches | run GPU stages one at a time; leave paths.pause_flag empty in config |
vault-search / OpenEvidence / Zotero lookups during synthesis | skip; cite only what the lecture itself provided |
ntfy completion pings | skip |
external batch control plane (run_queue, rerun_batch, clip_order, dashboard) | course-specific, not shipped — see reference/segmented-mode.md |
Vault paths (99Attachment/lecture_{slug}, the inbox folder) are ==a private vault
convention== and configurable: render_embeds.py --attach-root / --attach-dir,
finalize_to_vault.py --vault-root.
Dependencies
ollama pull minicpm-v:8b # ~5.5 GB Q4_K_M, Stage D
pip install rapidfuzz rapidocr-onnxruntime scikit-image pyyaml json_repair pillow numpyffmpeg + ffprobe on PATH. Surya (Stage B2) lives in its own venv; point
ocr_engine.surya_python at it in config.yaml, or leave it blank to fall back
to RapidOCR. Copy config.example.yaml → config.yaml on a new machine; every
machine-specific value there is blank by default and env-overridable.
==Optional dependencies degrade loudly, not silently== — a missing scikit-image or
RapidOCR is reported and gated, because a silent degrade produced wrong output
rather than less output (reference/decisions.md#optional-dependency-degradation).
File locations
<skill-dir>/
├── SKILL.md, config.yaml, config.example.yaml
├── reference/ pipeline.md · note-spec.md · segmented-mode.md · multi-camera.md · decisions.md
├── data/ real_words.txt, real_acronyms.txt (regenerated, not committed)
├── ocr_bench/ engine benchmark harness (bring your own fixtures)
└── scripts/
├── route_inputs.py front door — classifies material, prints the plan
├── transcribe_video.py retranscribe_segment.py gpu_check.py groq_asr.py
├── extract_slides.py quick_ocr.py dedup_semantic.py ocr_surya.py
├── vlm_signals.py (ocr_slides.py = deprecated shim → here)
├── build_slides_from_pdf.py build_slides_from_images.py crop_multiup_pdf.py
├── ground_slides.py flag_asr_suspects.py make_glossary.py build_real_words.py
├── render_embeds.py finalize_to_vault.py audit_note.py export_web.py
├── media_capture_index.py xcorr_media_offsets.py query_near_field.py
├── _mdpm.py AVCHD .MTS recording clock (no container tag)
├── adapters/ surya_adapter.py (production OCR adapters)
├── batch/ course_timeline (real-time ordering authority) ·
│ audit_segmentation (is the proposal still valid?) ·
│ build_L1 · split_segments · split_L1_by_segment · add_dhash ·
│ vlm_cache · detect_language · detect_language_audio ·
│ phi_mask · process_slide_deck (generic batch layer)
├── layout2/ viewer.css, viewer.js (web viewer assets, edited verbatim)
└── _common.py _log.py _paths.pyPer-lecture output directory:
{lecture}/
├── metadata.json run_id + media fingerprint + per-stage status
├── transcript.json/.txt timestamped segments; .txt is [MM:SS] text, H:MM:SS past an hour
├── asr_suspects.txt flagged tokens — flags only, never a rewrite
├── alignment.json multi-source capture-start hypotheses (when applicable)
├── slides/ frame_NNNN.jpg | page_NN.jpg | original photo names
├── slides_raw.json Stage B quick text + density + entropy
├── slides_dedup.json Stage C canonical markers (Stage B2 updates in place)
├── slides_dedup.pre_b2.json one-time pre-Stage-B2 snapshot
├── slides_ocr.json Stage B2 Surya result, for inspection
├── slides_vlm.json Stage D VLM signals + vlm_skip + skip_metrics
├── slides_grounded.json Stage E transcript grounding + retrieval fields
├── slides_final.json Stage F tier + score + attachment_name + width
└── logs/progress_*.jsonl per-stage event streams (not every stage emits one)Each stage output is a superset of the previous, so you can re-run one stage
without redoing transcription or frame extraction. runs.jsonl one level up
carries one summary line per stage run, joined by run_id. Keep the intermediates
— they are how tier decisions get debugged.
© drpwchen, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 86 other files (scripts) in the repository root of drpwchen/lecture-to-notes.
- SKILL.md
- .gitattributes
- .github/workflows/secret-scan.yml
- .gitignore
- CHANGELOG.md
- LICENSE
- README.md
- README.zh-TW.md
- SYNC-LEDGER.md
- config.example.yaml
- data/.gitignore
- data/real_acronyms.txt
- data/real_words.txt
- docs/AUDIT_SUMMARY.md
- docs/assets/hero.png
- docs/assets/hero.zh.png
- … and 71 more
Open the folder on GitHubat commit 79053a3
Compare with similar skills
Lecture To Notes next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Lecture To Notes this skilldrpwchen/lecture-to-notes | 108 | — | ~4.9k | Automated safety check: Notes | MIT | |
| Generate Doc Templatejeremylongshore/tons-of-skills-marketplace | 2.8k | — | ~1.3k | Automated safety check: Pass | MIT | |
| Youtube Notetakersickn33/agentic-awesome-skills | 47k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Multimodal Extractionswyxio/skills | 175 | — | ~922 | Automated safety check: Pass | MIT | |
| Explain Videolimin112/min-skill | 412 | — | ~2.4k | Automated safety check: Pass | None | |
| Orange Line Illustrationorange2ai/orange-line-illustration | 440 | — | ~2.5k | Automated safety check: Pass | Proprietary |
Similar skills
Youtube Notetaker
sickn33/agentic-awesome-skills
Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.
Multimodal Extraction
swyxio/skills
Given a local video or video URL, downloads the media if needed, extracts slide frames and key moments, transcribes the audio, and writes a Markdown timeline that interleaves screenshots with the…
Explain Video
limin112/min-skill
Build a narrated explainer video from a concept — discussion → structure → HTML slide deck → narration script → TTS voice → subtitles → background music → Playwright screen recording → ffmpeg…
Orange Line Illustration
orange2ai/orange-line-illustration
Generate New Yorker-style minimalist editorial illustrations — thin black ink lines on white, vast negative space, a single orange accent (F97316) — for articles, principles, covers, concept…
Strategy Consulting Visualization
kgraph57/mckinsey-style-visualization-skill
A skill your agent uses when turning any content into clear, professional visualizations - board slides, reports, proposals, research summaries, training materials, technical diagrams, infographics…
Related
Categories
Questions about Lecture To Notes
What does Lecture To Notes do?
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…. Lecture To Notes is an agent skill from drpwchen/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.
When should I use Lecture To Notes?
Lecture To Notes fits situations like: tasks that involve Transcription; tasks that involve Slides and decks.
How do I install Lecture To Notes in Claude Code?
Run `npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a claude-code`. Or copy the skill folder (the drpwchen/lecture-to-notes repository) into .claude/skills/lecture-to-notes in your project. Claude Code loads it when a task matches its description.
How do I install Lecture To Notes in Codex?
Run `npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a codex`. Or copy the skill folder (the drpwchen/lecture-to-notes repository) into .agents/skills/lecture-to-notes in your project. Codex loads it when a task matches its description.
Can I use Lecture To Notes in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add drpwchen/lecture-to-notes --skill lecture-to-notes -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lecture-to-notes, .gemini/skills/lecture-to-notes, .github/skills/lecture-to-notes and .opencode/skills/lecture-to-notes in your project.
What does Lecture To Notes need to run?
Going by SKILL.md and its folder, Lecture To Notes needs the command-line tools its instructions call (python, ollama and pip). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Write, Edit, Bash, Glob, Grep, Agent.
Does Lecture To Notes access the network?
SKILL.md contains no URLs. Its commands use pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Lecture To Notes safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Lecture To Notes use?
Lecture To Notes is published under the MIT licence (from the LICENSE file in the skill folder). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Lecture To Notes use?
About 4.9k tokens (SKILL.md is roughly 20k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Lecture To Notes?
Skills that share tags, products or a category with Lecture To Notes: Generate Doc Template (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Youtube Notetaker (sickn33/agentic-awesome-skills, 47k stars), Multimodal Extraction (swyxio/skills, 175 stars) and Explain Video (limin112/min-skill, 412 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Lecture To Notes?
drpwchen (a GitHub user) maintains it in drpwchen/lecture-to-notes, which has 108 GitHub stars. The repository was last updated on September 1, 2026.
Source: drpwchen/lecture-to-notes on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.