[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6Q0EAB96PX83W5PTE8A0R8D":3,"skill-same:01M6Q0EAB96PX83W5PTE8A0R8D":129},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":34,"commitSha":62,"skillDirectory":63,"forksCount":13,"repositoryHtmlUrl":64,"repositoryHomepageUrl":6,"ownerHtmlUrl":65,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":66,"install":67,"resources":80},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker",null,"Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"notetaker","youtube notetaker","youtube","annotations","viewer","dair-academy","local","study","main","README","cli","slides","markdown","Video","license","code","notes","official","workflow","safe","2026-11-10 10:12:30",false,"---\nname: youtube-notetaker\ndescription: \"Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.\"\ncategory: \"video\"\nrisk: \"safe\"\nsource: \"official\"\nsource_repo: \"dair-ai\u002Fdair-academy-plugins\"\nsource_type: \"official\"\ndate_added: \"2026-06-19\"\nauthor: \"DAIR.AI\"\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins\u002Fblob\u002Fmain\u002FREADME.md#license\"\ntags:\n  - dair-academy\n  - ai\n  - workflow\ntools:\n  - claude-code\n  - codex-cli\n  - cursor\n---\n\n# YouTube Notetaker\n\n## When to Use\n\nUse when this workflow matches the user request: >\n\n\n_Source: [dair-ai\u002Fdair-academy-plugins](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins) (MIT)._\n\nBuild a personal library of YouTube talks you study with. Each video becomes one **plain\nmarkdown file**: slide snapshots at their timestamps, a full timestamped transcript, and\neditable notes. A small bundled server renders the library as an interactive deep-dive in the\nbrowser. No database, no cloud service. Everything is files on disk you fully own.\n\n## Architecture (read this first)\n\nThe **markdown library is the single source of truth**. The artifact is a thin HTML shell that\nfetches from the server and writes notes back. Never hardcode video data into the HTML.\n\n- **Library:** a plain folder, set by `VIDEO_LIBRARY_DIR` (default `~\u002Fvideo-deepdives\u002F`).\n  - One markdown file per video, **filename slug = YouTube id** (e.g. `RtywqDFBYnQ.md`).\n  - Frontmatter holds video metadata + a `slides` array.\n  - Body holds the full transcript as `[HH:MM:SS] text` lines.\n  - `_media\u002F` holds slide images, **namespaced per video** as `\u003Cyoutube_id>-slide-NN.jpg`\n    to avoid collisions between videos.\n- **Server:** `scripts\u002Fserve.py`, a single stdlib + PyYAML file. Start it with:\n  ```\n  python3 scripts\u002Fserve.py --dir ~\u002Fvideo-deepdives --port 8000\n  ```\n  It serves the artifact at `\u002F` and a small API the artifact talks to:\n  - `GET \u002Fapi\u002Fvideo-deepdives` (front page fetches this) lists every video.\n  - `GET \u002Fapi\u002Fvideo-deepdives\u002F\u003Cid>` returns one video `{meta, body}`.\n  - `GET \u002Fapi\u002Fvideo-deepdives\u002F_media\u002F\u003Cfile>` serves a slide image.\n  - `PATCH \u002Fapi\u002Fvideo-deepdives\u002F\u003Cid>` with `{fields:{slides:[...]}}` writes notes back.\n  - **It picks up new videos automatically** the moment a markdown file exists. Adding a video\n    means writing a markdown file + media; you almost never touch the HTML.\n  - The `\u002Fapi\u002Fvideo-deepdives` URL namespace is local to the bundled server.\n- **Artifact:** `reference\u002Fartifact.html`, served by `serve.py` at `\u002F`. A clean reference copy;\n  only rewrite it if the user wants a UI change. For new videos, leave it alone.\n\n## Requirements\n\n- `yt-dlp` and `ffmpeg` on PATH (download + frame\u002Fscene extraction).\n- Python 3 with `Pillow` (contact sheet) and `PyYAML` (markdown file + server).\n  ```\n  pip install yt-dlp pillow pyyaml      # ffmpeg via your package manager\n  ```\n\n## Adding a video — the pipeline\n\nAll helper scripts are in `scripts\u002F`. `setup.sh` creates a private, unpredictable scratch\ndirectory; copy the printed `SCRATCH` path into a shell variable, then copy final assets into the\nlibrary. Set `VIDEO_LIBRARY_DIR` once per shell if you don't want the\ndefault. **Do not use em dashes (—) or arrows (→) in notes\u002Ftitles.**\n\n### 1. Resolve the id and check embeddability\n```\nbash scripts\u002Fsetup.sh \"\u003Cyoutube_url_or_id>\"\n```\nPrints the 11-char `YTID`, the scratch dir, the target library path, and whether YouTube\n**embedding is allowed** (oembed 200) or **blocked** (oembed 401, e.g. some university talks).\nIf blocked, inline playback won't work but the artifact degrades gracefully to an \"open at this\nmoment on YouTube\" link, so proceed normally.\n\nCopy the exact unpredictable path printed by the command before continuing:\n```\nSCRATCH=\"\u002Fpath\u002Fprinted\u002Fby\u002Fsetup.sh\"\n```\n\n### 2. Download video + subtitles\n```\nbash scripts\u002Fdownload.sh \"\u003CYTID>\" \"$SCRATCH\"\n```\nUses `yt-dlp` to grab the video (≤720p is plenty for slide frames) and the best available\nsubtitles (manual if present, else auto-captions) as `.vtt`. Also fetches title\u002Fuploader.\n\n### 3. Detect candidate slide timestamps\n```\nbash scripts\u002Fdetect_slides.sh \"$SCRATCH\u002Fvideo.mp4\" \"$SCRATCH\"\n```\nRuns ffmpeg scene detection (`select='gt(scene,0.3)'`) and writes `scene_times.txt` (seconds).\n0.3 is a good default; lower it (0.2) for subtle slide decks, raise it (0.4) for busy video.\n\n### 4. Build a contact sheet and CURATE\n```\npython3 scripts\u002Fcontact_sheet.py \"$SCRATCH\u002Fvideo.mp4\" \"$SCRATCH\u002Fscene_times.txt\" \"$SCRATCH\u002Fcontact.jpg\"\n```\nRead `contact.jpg` (labeled with index + timestamp). **This is the human-judgment step:** keep\nframes that are real content slides; **drop talking-head shots, transitions, duplicates, and\nblurry mid-animation frames.** Save the kept timestamps (seconds) to `$SCRATCH\u002Fkeep.txt`,\none per line. Typical talk yields 15-25 slides.\n\n### 5. Extract the curated slides at full quality and install to _media\n```\npython3 scripts\u002Fextract_slides.py \u003CYTID> \"$SCRATCH\u002Fvideo.mp4\" \"$SCRATCH\u002Fkeep.txt\" > \"$SCRATCH\u002Fslides.json\"\n```\nExtracts each kept timestamp at 1280px wide, JPEG, and copies them into\n`$VIDEO_LIBRARY_DIR\u002F_media\u002F` as `\u003CYTID>-slide-01.jpg`, `-02.jpg`, … (numbered in time order).\nProgress goes to stderr; a clean `slides.json` scaffold prints to **stdout**, so redirect it to a\nfile as shown, then fill in `title` and `note`.\n\nTip: talks are often a slide + speaker-cam composite, and speakers flip back and forth, so the\nsame slide appears at several timestamps. Keep the cleanest instance of each, and re-anchor each\nslide's `t` to where it is actually discussed in the transcript (better \"play from here\" UX).\n\n### 6. Build the transcript\n```\npython3 scripts\u002Fvtt_to_transcript.py \"$SCRATCH\"\u002F*.vtt \"$SCRATCH\u002Ftranscript.txt\"\n```\nParses the VTT into clean, de-duplicated `[HH:MM:SS] text` lines (YouTube auto-captions repeat\nrolling text; the script collapses it). This becomes the markdown body.\n\n### 7. Write notes and assemble the markdown file\nFor each kept slide, write a 1-3 sentence `note` grounded in the transcript around that timestamp\n(don't invent claims). Then assemble:\n```\npython3 scripts\u002Fwrite_library_item.py \\\n  --id \u003CYTID> \\\n  --title \"Talk title\" \\\n  --speaker \"Name, Role, Org\" \\\n  --tags tag1,tag2,tag3 \\\n  --slides \"$SCRATCH\u002Fslides.json\" \\\n  --transcript \"$SCRATCH\u002Ftranscript.txt\"\n```\nWrites `$VIDEO_LIBRARY_DIR\u002F\u003CYTID>.md` with correct frontmatter + body.\n\n### 8. Serve and verify (always do this)\n```\npython3 scripts\u002Fserve.py --dir \"$VIDEO_LIBRARY_DIR\" --port 8000 &\nscripts\u002Fverify.sh \u003CYTID>                 # defaults to http:\u002F\u002F127.0.0.1:8000\n```\n`verify.sh` curls the collection list, the item, the first slide image, and the artifact,\nasserting HTTP 200 and that the new id appears in the index. Then open\n`http:\u002F\u002F127.0.0.1:8000\u002F#\u002F\u003CYTID>` in a browser to confirm slides + transcript + notes render.\n\n## Markdown file shape (reference)\n\n```markdown\n---\nid: RtywqDFBYnQ\ntitle: Memory and dreaming for self-learning agents\nyoutube_id: RtywqDFBYnQ\nspeaker: Mahesh, Product Manager, Platform team at Anthropic\nsource_url: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RtywqDFBYnQ\nslide_count: 19\ncreated: '2026-05-25'\ntags: [anthropic, memory, agents]\nslides:\n- idx: 1\n  t: 55.7                 # seconds (float ok), used for seeking\n  mmss: 00:55             # display label\n  title: Agent primitives have evolved\n  note: One to three sentences grounded in the transcript at this timestamp.\n  img: \u002Fapi\u002Fvideo-deepdives\u002F_media\u002FRtywqDFBYnQ-slide-01.jpg\n# ... more slides\n---\n## Transcript\n[00:00:08] Hello, everyone...\n[00:00:11] ...\n```\n\nNotes:\n- `idx` can be sparse\u002Fnon-contiguous; the artifact sorts slides by `t`, so ordering is by\n  timestamp, not idx.\n- `img` is always a `\u002Fapi\u002Fvideo-deepdives\u002F_media\u002F\u003Cfile>` URL (served by serve.py),\n  never base64.\n- Slide `note` is what the user edits in the UI; PATCH writes the whole `slides` array back.\n\n## Gotchas\n- **Embedding disabled** (oembed 401): inline player is blocked by the video owner. Not a bug;\n  the artifact shows an \"open at this moment on YouTube\" link instead. Mention it to the user.\n- **Image collisions:** always namespace media `\u003CYTID>-slide-NN.jpg`. Never reuse bare\n  `slide-NN.jpg` for a new video.\n- **Auto-caption noise:** rolling YouTube captions duplicate text across cues; use the provided\n  VTT parser, don't dump raw VTT into the body.\n- **Don't touch existing videos** when adding a new one. Each video is an independent file.\n- **Server not picking up a video:** confirm the `.md` file is directly inside `--dir` (not a\n  subfolder) and the filename is `\u003CYTID>.md`.\n\n## What makes this portable\n- **No orchestrator \u002F no database.** Storage is a plain folder of markdown + images.\n- **One env var** (`VIDEO_LIBRARY_DIR`) controls where the library lives.\n- **One small server file** (`serve.py`, stdlib + PyYAML) renders everything and handles\n  note write-back. Drop it anywhere Python runs.\n- The markdown files are portable: readable in Obsidian or any editor, and the frontmatter is\n  standard YAML.\n\n\n## Limitations\n\n- Requires the upstream tool, account, API key, or local setup when the workflow names one.\n- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.\n- Validate generated artifacts or recommendations against the user's real sources before treating them as final.\n","# YouTube Notetaker\n\n## When to Use\n\nUse when this workflow matches the user request: >\n\n\n_Source: [dair-ai\u002Fdair-academy-plugins](https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins) (MIT)._\n\nBuild a personal library of YouTube talks you study with. Each video becomes one **plain\nmarkdown file**: slide snapshots at their timestamps, a full timestamped transcript, and\neditable notes. A small bundled server renders the library as an interactive deep-dive in the\nbrowser. No database, no cloud service. Everything is files on disk you fully own.\n\n## Architecture (read this first)\n\nThe **markdown library is the single source of truth**. The artifact is a thin HTML shell that\nfetches from the server and writes notes back. Never hardcode video data into the HTML.\n\n- **Library:** a plain folder, set by `VIDEO_LIBRARY_DIR` (default `~\u002Fvideo-deepdives\u002F`).\n  - One markdown file per video, **filename slug = YouTube id** (e.g. `RtywqDFBYnQ.md`).\n  - Frontmatter holds video metadata + a `slides` array.\n  - Body holds the full transcript as `[HH:MM:SS] text` lines.\n  - `_media\u002F` holds slide images, **namespaced per video** as `\u003Cyoutube_id>-slide-NN.jpg`\n    to avoid collisions between videos.\n- **Server:** `scripts\u002Fserve.py`, a single stdlib + PyYAML file. Start it with:\n  ```\n  python3 scripts\u002Fserve.py --dir ~\u002Fvideo-deepdives --port 8000\n  ```\n  It serves the artifact at `\u002F` and a small API the artifact talks to:\n  - `GET \u002Fapi\u002Fvideo-deepdives` (front page fetches this) lists every video.\n  - `GET \u002Fapi\u002Fvideo-deepdives\u002F\u003Cid>` returns one video `{meta, body}`.\n  - `GET \u002Fapi\u002Fvideo-deepdives\u002F_media\u002F\u003Cfile>` serves a slide image.\n  - `PATCH \u002Fapi\u002Fvideo-deepdives\u002F\u003Cid>` with `{fields:{slides:[...]}}` writes notes back.\n  - **It picks up new videos automatically** the moment a markdown file exists. Adding a video\n    means writing a markdown file + media; you almost never touch the HTML.\n  - The `\u002Fapi\u002Fvideo-deepdives` URL namespace is local to the bundled server.\n- **Artifact:** `reference\u002Fartifact.html`, served by `serve.py` at `\u002F`. A clean reference copy;\n  only rewrite it if the user wants a UI change. For new videos, leave it alone.\n\n## Requirements\n\n- `yt-dlp` and `ffmpeg` on PATH (download + frame\u002Fscene extraction).\n- Python 3 with `Pillow` (contact sheet) and `PyYAML` (markdown file + server).\n  ```\n  pip install yt-dlp pillow pyyaml      # ffmpeg via your package manager\n  ```\n\n## Adding a video — the pipeline\n\nAll helper scripts are in `scripts\u002F`. `setup.sh` creates a private, unpredictable scratch\ndirectory; copy the printed `SCRATCH` path into a shell variable, then copy final assets into the\nlibrary. Set `VIDEO_LIBRARY_DIR` once per shell if you don't want the\ndefault. **Do not use em dashes (—) or arrows (→) in notes\u002Ftitles.**\n\n### 1. Resolve the id and check embeddability\n```\nbash scripts\u002Fsetup.sh \"\u003Cyoutube_url_or_id>\"\n```\nPrints the 11-char `YTID`, the scratch dir, the target library path, and whether YouTube\n**embedding is allowed** (oembed 200) or **blocked** (oembed 401, e.g. some university talks).\nIf blocked, inline playback won't work but the artifact degrades gracefully to an \"open at this\nmoment on YouTube\" link, so proceed normally.\n\nCopy the exact unpredictable path printed by the command before continuing:\n```\nSCRATCH=\"\u002Fpath\u002Fprinted\u002Fby\u002Fsetup.sh\"\n```\n\n### 2. Download video + subtitles\n```\nbash scripts\u002Fdownload.sh \"\u003CYTID>\" \"$SCRATCH\"\n```\nUses `yt-dlp` to grab the video (≤720p is plenty for slide frames) and the best available\nsubtitles (manual if present, else auto-captions) as `.vtt`. Also fetches title\u002Fuploader.\n\n### 3. Detect candidate slide timestamps\n```\nbash scripts\u002Fdetect_slides.sh \"$SCRATCH\u002Fvideo.mp4\" \"$SCRATCH\"\n```\nRuns ffmpeg scene detection (`select='gt(scene,0.3)'`) and writes `scene_times.txt` (seconds).\n0.3 is a good default; lower it (0.2) for subtle slide decks, raise it (0.4) for busy video.\n\n### 4. Build a contact sheet and CURATE\n```\npython3 scripts\u002Fcontact_sheet.py \"$SCRATCH\u002Fvideo.mp4\" \"$SCRATCH\u002Fscene_times.txt\" \"$SCRATCH\u002Fcontact.jpg\"\n```\nRead `contact.jpg` (labeled with index + timestamp). **This is the human-judgment step:** keep\nframes that are real content slides; **drop talking-head shots, transitions, duplicates, and\nblurry mid-animation frames.** Save the kept timestamps (seconds) to `$SCRATCH\u002Fkeep.txt`,\none per line. Typical talk yields 15-25 slides.\n\n### 5. Extract the curated slides at full quality and install to _media\n```\npython3 scripts\u002Fextract_slides.py \u003CYTID> \"$SCRATCH\u002Fvideo.mp4\" \"$SCRATCH\u002Fkeep.txt\" > \"$SCRATCH\u002Fslides.json\"\n```\nExtracts each kept timestamp at 1280px wide, JPEG, and copies them into\n`$VIDEO_LIBRARY_DIR\u002F_media\u002F` as `\u003CYTID>-slide-01.jpg`, `-02.jpg`, … (numbered in time order).\nProgress goes to stderr; a clean `slides.json` scaffold prints to **stdout**, so redirect it to a\nfile as shown, then fill in `title` and `note`.\n\nTip: talks are often a slide + speaker-cam composite, and speakers flip back and forth, so the\nsame slide appears at several timestamps. Keep the cleanest instance of each, and re-anchor each\nslide's `t` to where it is actually discussed in the transcript (better \"play from here\" UX).\n\n### 6. Build the transcript\n```\npython3 scripts\u002Fvtt_to_transcript.py \"$SCRATCH\"\u002F*.vtt \"$SCRATCH\u002Ftranscript.txt\"\n```\nParses the VTT into clean, de-duplicated `[HH:MM:SS] text` lines (YouTube auto-captions repeat\nrolling text; the script collapses it). This becomes the markdown body.\n\n### 7. Write notes and assemble the markdown file\nFor each kept slide, write a 1-3 sentence `note` grounded in the transcript around that timestamp\n(don't invent claims). Then assemble:\n```\npython3 scripts\u002Fwrite_library_item.py \\\n  --id \u003CYTID> \\\n  --title \"Talk title\" \\\n  --speaker \"Name, Role, Org\" \\\n  --tags tag1,tag2,tag3 \\\n  --slides \"$SCRATCH\u002Fslides.json\" \\\n  --transcript \"$SCRATCH\u002Ftranscript.txt\"\n```\nWrites `$VIDEO_LIBRARY_DIR\u002F\u003CYTID>.md` with correct frontmatter + body.\n\n### 8. Serve and verify (always do this)\n```\npython3 scripts\u002Fserve.py --dir \"$VIDEO_LIBRARY_DIR\" --port 8000 &\nscripts\u002Fverify.sh \u003CYTID>                 # defaults to http:\u002F\u002F127.0.0.1:8000\n```\n`verify.sh` curls the collection list, the item, the first slide image, and the artifact,\nasserting HTTP 200 and that the new id appears in the index. Then open\n`http:\u002F\u002F127.0.0.1:8000\u002F#\u002F\u003CYTID>` in a browser to confirm slides + transcript + notes render.\n\n## Markdown file shape (reference)\n\n```markdown\n---\nid: RtywqDFBYnQ\ntitle: Memory and dreaming for self-learning agents\nyoutube_id: RtywqDFBYnQ\nspeaker: Mahesh, Product Manager, Platform team at Anthropic\nsource_url: https:\u002F\u002Fwww.youtube.com\u002Fwatch?v=RtywqDFBYnQ\nslide_count: 19\ncreated: '2026-05-25'\ntags: [anthropic, memory, agents]\nslides:\n- idx: 1\n  t: 55.7                 # seconds (float ok), used for seeking\n  mmss: 00:55             # display label\n  title: Agent primitives have evolved\n  note: One to three sentences grounded in the transcript at this timestamp.\n  img: \u002Fapi\u002Fvideo-deepdives\u002F_media\u002FRtywqDFBYnQ-slide-01.jpg\n# ... more slides\n---\n## Transcript\n[00:00:08] Hello, everyone...\n[00:00:11] ...\n```\n\nNotes:\n- `idx` can be sparse\u002Fnon-contiguous; the artifact sorts slides by `t`, so ordering is by\n  timestamp, not idx.\n- `img` is always a `\u002Fapi\u002Fvideo-deepdives\u002F_media\u002F\u003Cfile>` URL (served by serve.py),\n  never base64.\n- Slide `note` is what the user edits in the UI; PATCH writes the whole `slides` array back.\n\n## Gotchas\n- **Embedding disabled** (oembed 401): inline player is blocked by the video owner. Not a bug;\n  the artifact shows an \"open at this moment on YouTube\" link instead. Mention it to the user.\n- **Image collisions:** always namespace media `\u003CYTID>-slide-NN.jpg`. Never reuse bare\n  `slide-NN.jpg` for a new video.\n- **Auto-caption noise:** rolling YouTube captions duplicate text across cues; use the provided\n  VTT parser, don't dump raw VTT into the body.\n- **Don't touch existing videos** when adding a new one. Each video is an independent file.\n- **Server not picking up a video:** confirm the `.md` file is directly inside `--dir` (not a\n  subfolder) and the filename is `\u003CYTID>.md`.\n\n## What makes this portable\n- **No orchestrator \u002F no database.** Storage is a plain folder of markdown + images.\n- **One env var** (`VIDEO_LIBRARY_DIR`) controls where the library lives.\n- **One small server file** (`serve.py`, stdlib + PyYAML) renders everything and handles\n  note write-back. Drop it anywhere Python runs.\n- The markdown files are portable: readable in Obsidian or any editor, and the frontmatter is\n  standard YAML.\n\n\n## Limitations\n\n- Requires the upstream tool, account, API key, or local setup when the workflow names one.\n- Does not authorize destructive, production, paid, or external-message actions without explicit user approval.\n- Validate generated artifacts or recommendations against the user's real sources before treating them as final.\n",{"name":5,"risk":45,"tags":51,"tools":53,"author":57,"source":43,"license":14,"category":58,"date_added":59,"description":7,"source_repo":60,"source_type":43,"license_source":61},[31,52,44],"ai",[54,55,56],"claude-code","codex-cli","cursor","DAIR.AI","video","2026-06-19","dair-ai\u002Fdair-academy-plugins","https:\u002F\u002Fgithub.com\u002Fdair-ai\u002Fdair-academy-plugins\u002Fblob\u002Fmain\u002FREADME.md#license","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Fyoutube-notetaker","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":68,"prompt":78,"zipAvailable":79},[69,72,75],{"tool":70,"command":71},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill youtube-notetaker",{"tool":73,"command":74},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill youtube-notetaker",{"tool":76,"command":77},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill youtube-notetaker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",true,[81,87,93,97,101,105,109,113,117,121,125],{"path":82,"resourceType":83,"resourceTypeDesc":84,"sizeBytes":85,"sourceHtmlUrl":86},"reference\u002Fartifact.html","REFERENCE","参考文档",20253,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Freference\u002Fartifact.html",{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"scripts\u002Fcontact_sheet.py","SCRIPT","脚本",2416,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fcontact_sheet.py",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"scripts\u002Fdetect_slides.sh",1059,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fdetect_slides.sh",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"scripts\u002Fdownload.sh",1237,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fdownload.sh",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"scripts\u002Fextract_slides.py",2722,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fextract_slides.py",{"path":106,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":107,"sourceHtmlUrl":108},"scripts\u002Fscratch_safety.sh",1927,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fscratch_safety.sh",{"path":110,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":111,"sourceHtmlUrl":112},"scripts\u002Fserve.py",11377,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fserve.py",{"path":114,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":115,"sourceHtmlUrl":116},"scripts\u002Fsetup.sh",1598,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fsetup.sh",{"path":118,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":119,"sourceHtmlUrl":120},"scripts\u002Fverify.sh",1219,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fverify.sh",{"path":122,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":123,"sourceHtmlUrl":124},"scripts\u002Fvtt_to_transcript.py",2979,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fvtt_to_transcript.py",{"path":126,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":127,"sourceHtmlUrl":128},"scripts\u002Fwrite_library_item.py",3651,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002Fscripts\u002Fwrite_library_item.py",[130,158,181,202,227,242],{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":139,"publishedAt":46},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[136],{"categoryNo":137,"categoryName":138,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[140,141,142,143,144,145,132,146,147,148,149,150,151,34,152,153,154,155,156,157],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","community","active","critical","scope","scripts","relevant","implementing",{"skillNo":159,"name":160,"nameZh":6,"description":161,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":162,"categories":163,"keywords":164,"publishedAt":46},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[165,166,167,168,36,169,170,171,172,173,174,175,176,150,177,151,178,179,153,180],"delegate","zcode","zcode delegate","review","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":187,"publishedAt":46},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[188,189,28,45,190,191,192,40,193,194,195,196,197,151,34,32,198,199,200,201],"transcript","youtube transcript","github","codex","research","https","text","fetch","tooling","clean","output","deepapi","youtube transcripts","blob",{"skillNo":203,"name":204,"nameZh":6,"description":205,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":206,"categories":207,"keywords":217,"publishedAt":46},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[208,211,212],{"categoryNo":209,"categoryName":210,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":213,"categoryName":214,"taxonomyType":215,"taxonomyTypeDesc":216},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[188,189,28,218,45,219,190,191,40,220,221,39,222,195,223,151,34,224,225,226],"youtube transcript skills","gemini","search","api","browse","api-integration","free","card","channels",{"skillNo":228,"name":229,"nameZh":6,"description":230,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":231,"categories":232,"keywords":234,"publishedAt":46},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[233],{"categoryNo":209,"categoryName":210,"taxonomyType":20,"taxonomyTypeDesc":21},[235,28,236,237,45,219,220,238,239,221,39,222,195,240,223,151,34,224,241,200],"youtube full","full","google","server","dlp","credits","automatic",{"skillNo":243,"name":244,"nameZh":6,"description":245,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":246,"categories":247,"keywords":251,"publishedAt":46},"01M6Q0DKK9BWZZMRXG7F3Q0G3J","yao-meta-skill","Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes. Use for skill creation, reusable workflow packaging, skill improvement, evals, and team-ready distribution.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyao-meta-skill\u002FSKILL.md",[248],{"categoryNo":249,"categoryName":250,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[252,253,254,255,36,45,44,256,42,257,41,258,259,260,261,151,34,262,263,264],"Meta","meta skill","yao meta skill","yao","workflows","create","Evaluation","team","packaging","ready","meta-skill","creation","distribution"]