Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add dair-ai/dair-academy-plugins --skill youtube-notetakergit clone --depth 1 https://github.com/dair-ai/dair-academy-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dair-ai/dair-academy-plugins/youtube-notetaker)<a href="https://agentmods.dev/skills/dair-ai/dair-academy-plugins/youtube-notetaker"><img src="https://agentmods.dev/badge/skills/dair-ai/dair-academy-plugins/youtube-notetaker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dair-ai/dair-academy-plugins/youtube-notetaker"><img src="https://agentmods.dev/badge/skills/dair-ai/dair-academy-plugins/youtube-notetaker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00195 | $0.02492 |
| Opus 5 | $0.00097 | $0.01246 |
| Sonnet 5 | $0.00039 | $0.00498 |
| Haiku 4.5 | $0.00019 | $0.00249 |
Grade A, and why
youtube-notetaker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YouTube Notetaker
Build a personal library of YouTube talks you study with. Each video becomes one plain markdown file: slide snapshots at their timestamps, a full timestamped transcript, and editable notes. A small bundled server renders the library as an interactive deep-dive in the browser. No database, no cloud service. Everything is files on disk you fully own.
Architecture (read this first)
The markdown library is the single source of truth. The artifact is a thin HTML shell that fetches from the server and writes notes back. Never hardcode video data into the HTML.
- Library: a plain folder, set by
VIDEO_LIBRARY_DIR(default~/video-deepdives/).- One markdown file per video, filename slug = YouTube id (e.g.
RtywqDFBYnQ.md). - Frontmatter holds video metadata + a
slidesarray. - Body holds the full transcript as
[HH:MM:SS] textlines. _media/holds slide images, namespaced per video as<youtube_id>-slide-NN.jpgto avoid collisions between videos.
- One markdown file per video, filename slug = YouTube id (e.g.
- Server:
scripts/serve.py, a single stdlib + PyYAML file. Start it with:
It serves the artifact atpython3 scripts/serve.py --dir ~/video-deepdives --port 8000/and a small API the artifact talks to:GET /api/video-deepdives(front page fetches this) lists every video.GET /api/video-deepdives/<id>returns one video{meta, body}.GET /api/video-deepdives/_media/<file>serves a slide image.PATCH /api/video-deepdives/<id>with{fields:{slides:[...]}}writes notes back.- It picks up new videos automatically the moment a markdown file exists. Adding a video means writing a markdown file + media; you almost never touch the HTML.
- The
/api/video-deepdivesURL namespace is local to the bundled server.
- Artifact:
reference/artifact.html, served byserve.pyat/. A clean reference copy; only rewrite it if the user wants a UI change. For new videos, leave it alone.
Requirements
yt-dlpandffmpegon PATH (download + frame/scene extraction).- Python 3 with
Pillow(contact sheet) andPyYAML(markdown file + server).pip install yt-dlp pillow pyyaml # ffmpeg via your package manager
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/artifact.html 19 KB
- scripts/contact_sheet.py 2.4 KB runs code
- scripts/detect_slides.sh 941 B runs code
- scripts/download.sh 1.0 KB runs code
- scripts/extract_slides.py 2.0 KB runs code
- scripts/serve.py 6.6 KB runs code
- scripts/setup.sh 1.2 KB runs code
- scripts/verify.sh 1.2 KB runs code
- scripts/vtt_to_transcript.py 2.1 KB runs code
- scripts/write_library_item.py 2.6 KB runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 189 lines · 195 tokens per session scan A f3e35e1aa6d3
youtube-notetaker is a skill published in the GitHub repository dair-ai/dair-academy-plugins (613 stars, last pushed 1mo ago), licensed MIT. It adds 195 tokens to every session and 2,492 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.