agentleFS
tubeagentkittubeagentkit/youtube-transcript-cursor-plugin/skills/channel-playlist-research/SKILL.md

channel-playlist-research

Skill0 starsChanged 21 days agoMITView on GitHub

Use when the user wants to resolve a channel handle, browse a channel's recent or full upload history (including Shorts, live streams or its most popular videos), see its playlists, community posts or banner, search inside one channel's videos, list every video in a playlist, find videos related to one, or read a video's estimated dislikes. Calls get_channel_latest_videos, search_channel_videos, list_channel_videos, list_channel_playlists, list_channel_posts, get_channel_banner, list_playlist_videos, get_related_videos and get_video_dislikes from the bundled getyoutubetranscript.com MCP server (REST API fallback available) - every call costs 1 credit per successful call (per page when paginated); only `get_credits` is free.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If the youtube-transcript MCP server is connected, use whichever tool matches the ask:

    line 20
  2. Very specific:

    Only care about one topic within a channel?

    line 59
  3. Very specific:

    Before paginating a large channel or playlist, consider checking remaining balance first (get_credits tool, or GET /credits, both free) so …

    line 60

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Channel & playlist research

Covers everything about a YouTube channel or playlist short of fetching an individual video's transcript (see the fetch-transcript skill for that).

Trigger

  • "What has @channel posted recently?" -> latest videos (1 credit)
  • "List every video @channel has ever uploaded" -> full upload history (paginated)
  • "Search @channel's videos for X" -> in-channel search (paginated)
  • "List all videos in this playlist" -> playlist contents (paginated)
  • "What's this channel's ID / is this the right channel?" -> resolve a handle/URL to a canonical channel ID (1 credit)

Preferred path: the bundled MCP tools

If the youtube-transcript MCP server is connected, use whichever tool matches the ask:

ToolUse forCost
get_channel_latest_videos({ channel })Channel metadata + its home tab's recent uploads1 credit
list_channel_videos({ channel | continuation, tab, sort })The channel's uploads, paginated. tab: videos (default), shorts, streams (Live). sort: latest (default), popular, oldest. Both first page only1 credit/page
list_channel_playlists({ channel | continuation })The channel's playlists (pass an id to list_playlist_videos)1 credit/page
list_channel_posts({ channel | continuation })The channel's community posts1 credit/page
get_channel_banner({ channel })Banner (original and every crop size) and avatar1 credit
get_related_videos({ video_url })The videos YouTube suggests next to a video1 credit
get_video_dislikes({ video_url })Estimated likes and dislikes (YouTube no longer publishes dislikes)1 credit
search_channel_videos({ channel, query | continuation })Search within one channel's videos1 credit/page
list_playlist_videos({ playlist | continuation })Every video in a playlist1 credit/page

channel accepts an @handle, a channel URL, or a UC... ID. playlist accepts a playlist URL or ID. For any of the paginated tools, pass the previous response's opaque continuation token back verbatim to continuation for the next page - never construct or decode it. A null/absent token means there are no more pages.

Fallback: the REST API

Same base URL and auth as fetch-transcript (https://getyoutubetranscript.com/api/v1, Authorization: Bearer $YOUTUBE_TRANSCRIPT_API_KEY):

EndpointParamsCost
GET /resolve?handle=@mkbhdhandle (ID, URL, or @handle)1 credit
GET /channel/latest?channel=@mkbhdchannel1 credit
GET /channel/videos?channel=@mkbhd (or &continuation=)channel or continuation; optional tab, sort on a first page1 credit/page
GET /channel/playlists?channel=@mkbhd (or &continuation=)channel or continuation1 credit/page
GET /channel/posts?channel=@mkbhd (or &continuation=)channel or continuation1 credit/page
GET /channel/banner?channel=@mkbhdchannel1 credit
GET /video/related?v=<id or URL>v1 credit
GET /video/dislikes?v=<id or URL>v1 credit
GET /channel/search?channel=@mkbhd&q=iphone (or &continuation=)channel+q, or continuation1 credit/page
GET /playlist?list=<id or URL> (or &continuation=)list or continuation1 credit/page

See the fetch-transcript skill for how to obtain YOUTUBE_TRANSCRIPT_API_KEY, and for the shared error-code table (401/402/404/429/503).

Which one to reach for

  • Just want to know what's new? get_channel_latest_videos / channel/latest - it's one credit for the whole latest shelf, use it before reaching for the paginated full-history tool.
  • Need the complete history (for an archive, a database, or "has this channel ever covered X")? list_channel_videos / channel/videos. Add sort=popular for the most-viewed first, or tab=shorts / tab=streams for Shorts or live streams.
  • Only care about one topic within a channel? search_channel_videos / channel/search - cheaper than paginating the full history and filtering yourself.
  • Before paginating a large channel or playlist, consider checking remaining balance first (get_credits tool, or GET /credits, both free) so a long pagination loop doesn't die partway through on a 402.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.