Skip to main content
skill CX Codex

podcast-transcript-search — Claude Code skill for podcast 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.

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 podcast-transcript-search -a claude-code
Open on GitHub

What podcast-transcript-search does

The skill searches YouTube podcast transcripts for a topic, guest, or phrase. For a specific show, it resolves the channel and returns matching episodes with dates, transcript excerpts, and timestamped links. It also reports how far transcript indexing has reached and lists recent episodes.

Search runs through arcmira_execute_read; arcmira_describe provides method details. Show and guest names are matched to IDs first. If several entities fit, the skill asks which one to use. An empty result means this query found no matches, not that the show never covered the topic: a recent episode may still be outside the transcript index.

What it helps with

  • find podcast episodes that discuss a topic
  • locate episodes featuring a particular guest
  • get a transcript passage with a link to its timestamp

Example prompts for the agent

  • Find All In episodes that discuss tariffs.
  • Which episodes of this show feature guest Theo?
  • Find the moment when the host says this phrase and return a timestamped link.

How to install podcast-transcript-search

1Skills CLI (Vercel)

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

2Manually: put the files in place

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

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

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

Questions about podcast-transcript-search

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

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

What does podcast-transcript-search do?

It searches YouTube podcast transcripts for topics, guests, and phrases, then returns matching episodes, transcript passages, and timestamped links.

Why might searching a guest's name miss episodes they appeared in?

A name used as a text query matches only passages where that name is spoken. The skill resolves the guest to a person ID to find episodes they appear in.

Source text

SKILL.md · Apache-2.0
---
name: podcast-transcript-search
description: "Use Arcmira to search podcast transcripts on YouTube for a topic, guest or phrase: which episodes covered it, what was said, and a timestamped link."
---

# Podcast transcript search

`search` with a show in `channelIds` finds the episodes that covered a topic, guest or phrase, with the words and a link to the second. `status({ channelId })` says how far the show's transcript search runs, and `episodes` lists its latest episodes, so an empty result can be told apart from a missing episode.

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

## When to use

Use Arcmira when the user asks:

- search podcast transcripts for a topic or phrase
- which episodes of a podcast covered a topic or had a guest
- find the moment in a podcast episode, with a timestamped link

## 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 show resolves with `{ type: "channel" }`; its id is `youtube_channel_id` (a UC id). Users shorten show names ("All In"); say when the show was assumed.
- A guest resolves with `{ type: "person" }`. Their id in `entityIds` limits results to episodes they appear in; in `speakerIds` it returns their own lines.
- Across every podcast: drop the pick, `channelIds`, and the `status` and `episodes` calls.

## 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. It opens with the pick: set `CONTEXT` to the user's own words about the name. When several entities fit it returns `ask` and runs nothing else. Show those options to the user, then run it again with `ID` set to the pick. Build date windows from `arcmira.daysAgo(n)` and `arcmira.today()`.

### A topic on one podcast, last 90 days

```javascript
const NAME = "All-In Podcast", CONTEXT = undefined, ID = null;   // CONTEXT: the user's own words about the name, never a guess. After an ask, set ID to the picked option's channel_id and run again
const r = ID ? null : await arcmira.resolve(NAME, { type: "channel", context: CONTEXT });
const e = r && (r.best ?? r.suggested);
if (r && !e) return { ask: r.ask && { question: r.ask.question, options: r.ask.options.map(o => ({ ...o, channel_id: r.candidates.find(c => c.id === o.id)?.youtube_channel_id ?? null })) } };
const id = ID ?? e.youtube_channel_id;
const assumed = Boolean(r?.suggested), why = r?.suggested?.evidence ?? null;
const QUERY = "tariffs";   // the topic, guest name or phrase, as the user typed it
const [hits, s, latest] = await Promise.all([
  arcmira.search({ query: QUERY, channelIds: [id], after: arcmira.daysAgo(90), limit: 5 }),
  arcmira.status({ channelId: id }),
  arcmira.episodes(id, { limit: 3 }),
]);
const episodes = new Map();
for (const c of hits.chunks) {
  const ep = episodes.get(c.video_id) ?? { episode: c.video_title, date: c.published_at, moments: [] };
  ep.moments.push({ second: c.start_seconds, said: c.text.slice(0, 300), url: c.watch_url });
  episodes.set(c.video_id, ep);
}
return {
  show: { name: e?.name ?? null, channel_id: id, assumed, why },
  window: hits.window, as_of: hits.as_of, search_indexed_through: s.channel.search_indexed_through,
  latest_episodes: latest.episodes.map(x => ({ title: x.title, date: x.published_at })),
  episodes: [...episodes.values()],
  ...(hits.chunks.length ? {} : { none: hits.note ?? null }),
};
```

## A good answer

- Names the show with its channel id, and says when it was assumed.
- Lists the episodes that covered it, each with the date, the words said and a link that opens at the second.
- Gives `search_indexed_through` for the show and the window it searched.
- Says so when nothing matched, and that an empty result is not proof the show never said it.

## Traps

- An empty result means this query returned no matches. Check `search_indexed_through` and the latest episodes before saying the show never covered it; the newest episode may not be in transcript search yet.
- A guest name in `query` matches only where the name is spoken. Resolve the guest and pass the id for the episodes they appear in.
- Never count passages to say how many episodes covered a name; `occurrences` with the show and the entity id counts episodes.
- A passage is not a clip: `start_seconds` is where it starts. `find-quotes` and `youtube-clip-finder` read the transcript lines for a start and an end.

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

SKILL.md skills catalog →
phase-10i-transcript-search-research ghostwright phase-10i-transcript-search-research guides an architectural study for historical chat transcript search in Phantom after Murph compaction. Useful when planning agent context retrieval. GP ChatGPT ★ 1,497repo stars 💯 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 tech-podcast-interview-prep Samuel Berthe tech-podcast-interview-prep prepares a guest for someone else's technical podcast, YouTube interview or panel: show reconnaissance, a message spine, sound bites and a post-release promotion plan. CX Codex +1 13,500installs 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

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 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 youtube-transcript-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. 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