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
npx skills add arcmira/mcp --skill youtube-transcript-search -a claude-codeWhat 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_1UH8from 0 to 120 seconds.
How to install youtube-transcript-search
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill youtube-transcript-search -a claude-code2Manually: put the files in place
~/.claude/skills/youtube-transcript-search/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/youtube-transcript-search/
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill youtube-transcript-search -a codex2Manually: put the files in place
.agents/skills/youtube-transcript-search/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill youtube-transcript-search -a cursor2Manually: put the files in place
.cursor/skills/youtube-transcript-search/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install arcmira/mcp plugins/arcmira/skills/youtube-transcript-search2Manually: put the files in place
.github/skills/youtube-transcript-search/SKILL.md1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill youtube-transcript-search -a gemini-cli2Platform CLI
gemini skills install https://github.com/arcmira/mcp --path plugins/arcmira/skills/youtube-transcript-searchManually: put the files in place
.devin/skills/youtube-transcript-search/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add arcmira/mcp --skill youtube-transcript-search -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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