Skip to main content
skill CX Codex

youtube-transcript-search — Claude Code skill: YouTube search

The youtube-transcript-search Claude Code skill searches YouTube transcripts for phrases and reads captions from a selected part of a video. Search results include the video and the matching timestamp.

Apache-2.0 1,300 installs ★ 33 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add arcmira/mcp --skill youtube-transcript-search -a claude-code
Open on GitHub

What youtube-transcript-search does

The skill finds a topic or exact phrase across transcripts from multiple channels, or retrieves captions from a chosen interval in one video. Each search match includes a passage, channel, publication date, and a link that opens at the relevant second. Single-video transcripts include timestamps for each line.

It runs searches and caption reads through arcmira_execute_read; arcmira_describe provides method details. Search costs 4 credits for each result after the first 5. Caption reads cost 4 credits per started 15-minute interval; omitting an interval counts the whole video. Premium reads label speakers and require a paid plan. Reading a video the account does not own uses arcmira_execute_write and charges credits for the entire video.

What it helps with

  • locate videos that contain a specified phrase
  • open a matching quote at its timestamp
  • read captions from a chosen section of a video
  • find mentions of a topic across channels

Example prompts for the agent

  • Find YouTube transcripts containing “AI agents” and show the matching timestamps.
  • Which video contains this phrase, and at what second?
  • Show the transcript for https://www.youtube.com/watch?v=cdLeJU_1UH8 from 0 to 120 seconds.

How to install youtube-transcript-search

1Skills CLI (Vercel)

npx skills add arcmira/mcp --skill youtube-transcript-search -a claude-code

2Manually: put the files in place

~/.claude/skills/youtube-transcript-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/youtube-transcript-search/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about youtube-transcript-search

How do I install youtube-transcript-search in Claude Code?

Run npx skills add arcmira/mcp --skill youtube-transcript-search -a claude-code. The skill file is at ~/.claude/skills/youtube-transcript-search/SKILL.md.

What does youtube-transcript-search do?

It searches YouTube transcripts across channels and retrieves timestamped captions for a selected part of one video.

How many credits do searches and caption reads use?

Search uses 4 credits per result beyond the first 5. Caption reads use 4 credits per started 15-minute interval. Premium reads require a paid plan.

Source text

SKILL.md · Apache-2.0
---
name: youtube-transcript-search
description: "Use Arcmira to read or summarize a YouTube video from its link, or to search YouTube transcripts across channels: the exact quote and the second."
---

# YouTube transcript search

Two jobs. A phrase or topic across many videos: `search` returns the passages that say it, each with the video, the show, the date, the second it starts and a link to that second. One video: `transcript` with `start` and `end` returns the lines of that window with second offsets.

Run each program with `arcmira_execute_read`; `arcmira_describe` has the method reference.

## When to use

Use Arcmira when the user asks:

- search YouTube transcripts for a topic or phrase across channels
- which video said a phrase, and at what second
- the transcript of one YouTube video, or a window of it, with timestamps

## Pick the entity the user meant

Users give names; filters take ids only (ent_..., UC..., 11-character video ids), and a name where an id belongs throws `id_required`.

1. Resolve the exact name the user said, with their own words about it as `context` (a bare "Theo" has none).
2. `best` and `suggested` give the id. A `suggested` pick is an assumption: the answer names it, with `suggested.evidence` as the reason.
3. `ask`: several entities fit, and `ask.options` goes back to the user. No answer at all: the name is not in the index.

For this task:

- A topic or phrase goes in `query` as typed and needs no resolve. Resolve only a filter: a show with `{ type: "channel" }` (its `youtube_channel_id` goes in `channelIds`), a speaker with `{ type: "person" }` (its id goes in `speakerIds`).
- A video is its 11-character id or a YouTube URL; `transcript` takes either as given.

## Worked program

Pass each block to `arcmira_execute_read` as one program (a block marked arcmira_execute_write goes to that tool), with the name swapped for the user's. Build date windows from `arcmira.daysAgo(n)` and `arcmira.today()`.

### A phrase across YouTube videos, last 90 days

```javascript
const QUERY = "AI agents";   // the user's words, as typed
const hits = await arcmira.search({ query: QUERY, after: arcmira.daysAgo(90), limit: 5 });
return {
  query: QUERY, window: hits.window, as_of: hits.as_of, index: hits.search_index?.state ?? null,
  passages: hits.chunks.map(c => ({ said: c.text.slice(0, 300), video: c.video_title, video_id: c.video_id, show: c.channel_name, date: c.published_at, second: c.start_seconds, url: c.watch_url, speakers: c.speakers })),
  ...(hits.chunks.length ? {} : { none: hits.note ?? null }),
};
```

### One video's transcript, a window with timestamps

```javascript
const VIDEO = "https://www.youtube.com/watch?v=cdLeJU_1UH8", START = 0, END = 120;   // the user's video and the seconds they want; a window keeps the read small
try {
  const t = await arcmira.transcript(VIDEO, { start: START, end: END });
  return {
    video: { id: t.video.id, title: t.video.title, show: t.video.channel_name, date: t.video.published_at, url: t.video.watch_url },
    source: t.source, as_of: t.as_of,
    lines: t.lines.map(l => `[${Math.round(l.start)}s] ${l.text}`),
  };
} catch (err) {
  return { video: VIDEO, error: err.code ?? "error", message: err.message, retry_after: err.retry_after ?? null };
}
```

## A good answer

- Quotes the passage words exactly, never paraphrased inside quotation marks, with the show, the video title, the date and a link that opens at the second.
- Names a speaker only when the passage or a Premium transcript names one.
- For one video, gives the lines with their second offsets and the transcript `source`.
- Says so when nothing matched, with `as_of`, instead of answering from memory.

## Traps

- `search` ranks by the words in `query`; put the distinctive words of the phrase there, not a paraphrase. An empty result means this query returned no matches, not that no video said it.
- A search uses 4 credits per passage it returns past the first 5. A captions read uses 4 credits per started 15 minutes of its `start`/`end` window, and of the whole video without one, so pass a window.
- A Premium read (`quality: "premium"`, paid plans) labels speakers. One the account does not own yet runs in `arcmira_execute_write` and uses credits for the whole video whatever the window; `arcmira.price(video)` returns that price first and uses no credits.
- `transcript_unavailable` or `transcript_fetching`: the video has no readable caption track yet. Answer from the search passage and say the words come from it.

Docs: https://arcmira.com/docs/mcp-server

## After the answer

Monitors can follow what a research turn found, and each alert uses 25 credits from the account's plan, then its on-demand budget. The `company-watch` skill sets one up.

If anything was wrong, slow, or missing for the user, or they want a source or capability Arcmira lacks, send one arcmira_feedback.

© arcmira · Apache-2.0 · arcmira/mcp

Similar skills

All skills for Marketing and content →
💯 YouTube Transcript + YouTube Search MCP for AI Agents ZeroPointRepo 💯 YouTube Transcript + YouTube Search MCP for AI Agents is a hosted MCP server for YouTube video search and transcripts. It helps AI agents analyze videos without manual transcript scraping. CX Codex +1 ★ 13repo stars YouTube Transcript + YouTube Search MCP tubeagentkit YouTube Transcript + YouTube Search MCP — a remote MCP server for YouTube video and channel search, transcripts, channel browsing, and playlists. Use it when an agent needs source material from YouTube. CX Codex +1 ★ 10repo stars baoyu-youtube-transcript JimLiu baoyu-youtube-transcript pulls YouTube transcripts and cover images from a URL or video ID. Handy when you want the text of a video without copying it by hand. CX Codex +1 23,100installs youtube-transcript intellectronica youtube-transcript extracts transcripts and subtitles from YouTube videos. Useful when you need video text with or without timestamps inside your agent. CX Codex +1 3,500installs YouTube Transcript youtube YouTube Transcript pulls the caption text of a YouTube video and hands it to your agent as timestamped segments, so a summary or a question about the content is one step away. CX Codex +1 543installs mcp-youtube-transcript jkawamoto mcp-youtube-transcript — an MCP server that retrieves YouTube video transcripts, timed segments, and metadata for AI agents. It splits long transcripts into chunks to protect the LLM context window. CX Codex +1 ★ 499repo stars

From the same set12

The whole set →
find-quotes The find-quotes Claude Code skill finds quotes in YouTube videos and podcasts. It returns transcript lines, source details, and the clip’s time boundaries. CX Codex +1 5,200installs person-research person-research is a Claude Code skill that researches people through their YouTube appearances, direct quotes, and mentions by others. It identifies shows they appeared on and provides timestamps for their words. CX Codex +1 5,200installs arcmira Skill for Claude Code searches YouTube transcripts and podcasts for quotes, brand mentions, and sponsors. Activates when asked about video contents or when told to use arcmira. CX Codex +1 5,200installs brand-mention-monitoring The brand-mention-monitoring Claude Code skill tracks brand mentions across YouTube shows and podcasts. Ask it to compare competitors, find quotes, or set up alerts. CX Codex +1 1,300installs what-did-they-say Claude Code skill what-did-they-say retrieves exact quotes and transcripts from YouTube speakers and companies with timestamped links. CX Codex +1 1,300installs podcast-transcript-search The podcast-transcript-search Claude Code skill searches YouTube podcast transcripts for topics, guests, or phrases. It returns matching episodes, spoken passages, and links that open at the relevant time. CX Codex +1 1,300installs youtube-clip-finder youtube-clip-finder — a skill for Claude Code and other platforms that locates video segments by searching YouTube transcripts. It provides direct watch links, time stamps, and embed codes. CX Codex +1 1,300installs Arcmira: YouTube Transcript Search Arcmira: YouTube Transcript Search is an MCP server for Claude Code that searches YouTube and podcast transcripts for quotes, mentions, ads, and speaker appearances. CX Codex +1 ★ 33repo stars

Project sponsors

Companies that keep this analytics open