agentleFS
tubeagentkittubeagentkit/youtube-transcript-cursor-plugin/skills/search-youtube/SKILL.md

search-youtube

Skill0 starsChanged 21 days agoMITView on GitHub

Use when the user wants to search YouTube - for videos on a topic, or for a channel by name/handle. Calls the search_youtube tool from the bundled getyoutubetranscript.com MCP server (falls back to GET /search on the REST API) - requires an API key or an OAuth-connected MCP session (100 credits on sign-up).

  • 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, call:

    line 16
  2. Very specific:

    Never construct or decode a continuation token yourself - pass it back exactly as returned.

    line 26
  3. Very specific:

    If the user's next ask is about a specific result (its transcript, or more videos from that channel), hand off to the fetch-transcript or …

    line 47

≈ “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

Search YouTube

Searches YouTube for videos or channels, without a Google API key or quota to manage.

Trigger

User wants to find videos about a topic ("find videos about X", "top videos on Y"), or find a channel by name ("search YouTube for MKBHD's channel").

Preferred path: the bundled MCP tool

If the youtube-transcript MCP server is connected, call:

search_youtube({
  query: "<search terms>",       // required unless continuing pagination
  search_type: "video",           // "video" (default) or "channel" - restricts to one kind, never mixes both
  continuation: "<token>"         // optional - opaque token from a previous response, fetches the next page
})

Never construct or decode a continuation token yourself - pass it back exactly as returned.

Fallback: the REST API

curl -s "https://getyoutubetranscript.com/api/v1/search?q=<query>&type=video&country=us&language=en&limit=20" \
  -H "Authorization: Bearer $YOUTUBE_TRANSCRIPT_API_KEY"
  • q - the search query (required for a first page).
  • type - video (default) or channel. Video results land in data.video_results, channel results in data.channel_results - one call returns exactly one kind.
  • page_token - from a previous response's data.pagination.next_page_token, to fetch the next page (works for both types).
  • country / language - optional region/language hints.
  • limit - optional max results for the page.

See the fetch-transcript skill for how to obtain YOUTUBE_TRANSCRIPT_API_KEY if it isn't already set.

Cost: 1 credit per page. Errors follow the same {success, code, message} shape as every other endpoint - see fetch-transcript's error table for the common codes (401/402/429/503).

After searching

If the user's next ask is about a specific result (its transcript, or more videos from that channel), hand off to the fetch-transcript or channel-playlist-research skill rather than re-searching from scratch.

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.