what-did-they-say — Claude Code skill: what it does, how to install
Claude Code skill what-did-they-say retrieves exact quotes and transcripts from YouTube speakers and companies with timestamped links.
Apache-2.0 1,300 installs ★ 33 updated 2026-10-23
npx skills add arcmira/mcp --skill what-did-they-say -a claude-codeWhat what-did-they-say does
The agent queries transcripts using IDs resolved from names and returns passages where speakers discuss specific topics. When direct quotes are absent, it retrieves what others said about the entity separately.
Execution runs through arcmira_execute_read. Queries require at least two characters, and entity names must be mapped to IDs before searching.
What it helps with
- find speaker quotes from YouTube
- check company statements on podcasts
- locate who said a specific line
- retrieve executive remarks from videos
Example prompts for the agent
- Find what Jensen Huang said about export controls on YouTube
- What did the CEO say on the podcast about the release
- Who said this quote in the interview transcript
How to install what-did-they-say
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill what-did-they-say -a claude-code2Manually: put the files in place
~/.claude/skills/what-did-they-say/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/what-did-they-say/
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill what-did-they-say -a codex2Manually: put the files in place
.agents/skills/what-did-they-say/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill what-did-they-say -a cursor2Manually: put the files in place
.cursor/skills/what-did-they-say/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install arcmira/mcp plugins/arcmira/skills/what-did-they-say2Manually: put the files in place
.github/skills/what-did-they-say/SKILL.md1Skills CLI (Vercel)
npx skills add arcmira/mcp --skill what-did-they-say -a gemini-cli2Platform CLI
gemini skills install https://github.com/arcmira/mcp --path plugins/arcmira/skills/what-did-they-sayManually: put the files in place
.devin/skills/what-did-they-say/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add arcmira/mcp --skill what-did-they-say -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 what-did-they-say
How to install what-did-they-say in Claude Code?
Run npx skills add arcmira/mcp --skill what-did-they-say -a claude-code, then check ~/.claude/skills/what-did-they-say/SKILL.md.
What does what-did-they-say do?
It searches YouTube transcripts for exact words from specific people or companies, returning quotes with show names, dates, and timestamped links.
What is required to run what-did-they-say?
Programs execute via arcmira_execute_read, and searches require a topic string of two or more characters.
Source text
SKILL.md · Apache-2.0
---
name: what-did-they-say
description: "Use Arcmira when asked what someone said about something: a person's or company's own words from YouTube, with the show, the date and a timestamped link."
---
# What did they say
Answers "what did they say about it" from the transcripts. `search` with the speaker's id in `speakerIds` returns passages where they speak the topic words. When that is empty, `about` with the same id returns what others said about them, kept apart. A company speaks through its people or its own show.
Run each program with `arcmira_execute_read`; `arcmira_describe` has the method reference.
## When to use
Use Arcmira when the user asks:
- what did a person say about a topic, in their own words
- what did a company or its CEO say on a podcast or YouTube
- who said a line, and where
## 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 person resolves with `{ type: "person" }`; pass what the user said about them as `context`.
- A company speaks through its people or its own show. Resolve the executive with `{ type: "person" }`, or the company's show with `{ type: "channel" }` and pass its `youtube_channel_id` in `channelIds`.
- The topic words go in `query`, never in `about`.
- For "who said this line", search the line with no speaker filter and read `speakers` on each passage.
## 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()`.
### What one person said about a topic, last 90 days
```javascript
const NAME = "Jensen Huang", 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 id and run again
const r = ID ? null : await arcmira.resolve(NAME, { type: "person", context: CONTEXT });
const e = r && (r.best ?? r.suggested);
if (r && !e) return { ask: r.ask };
const id = ID ?? e.id;
const assumed = Boolean(r?.suggested), why = r?.suggested?.evidence ?? null;
const TOPIC = "export controls"; // the topic in the user's words
const after = arcmira.daysAgo(90);
const own = await arcmira.search({ query: TOPIC, speakerIds: [id], after, limit: 5 });
const about = own.chunks.length ? null : await arcmira.search({ query: TOPIC, about: [id], after, limit: 3 });
const name = e?.name ?? null;
const said = own.chunks.map(c => {
const mine = name ? c.text.split("\n").filter(l => l.startsWith(name + ": ")) : [];
return { lines: mine.length ? mine : [c.text.slice(0, 300)], speaker_named_on_lines: mine.length > 0, show: c.channel_name, episode: c.video_title, date: c.published_at, url: c.watch_url };
});
return {
speaker: { id, name, assumed, why }, topic: TOPIC, window: own.window, as_of: own.as_of,
in_their_words: said,
...(said.length ? {} : { note: own.note ?? null, said_about_them: (about?.chunks ?? []).map(c => ({ said: c.text.slice(0, 300), show: c.channel_name, date: c.published_at, url: c.watch_url })) }),
};
```
## A good answer
- Names the person it searched, with the id, and any namesake it set aside.
- Quotes only the person's own lines, exactly as the transcript gives them, never paraphrased inside quotation marks, each with show, episode, date and `watch_url`.
- When no line names a speaker, says the attribution covers the passage, not each line.
- Keeps what others said about them apart from their own words, and says so when nothing matched, with `as_of`.
## Traps
- Speaker labels cover part of the index. An empty `speakerIds` search is not proof they never said it: read `note`, and give what others said about them as that, not as their words.
- A chunk found with `speakerIds` can include other people's lines. Lines start with "Name: " when the speaker is known.
- `search` needs a topic of two or more characters in `query`.
- For the start and end of the moment, `find-quotes` and `youtube-clip-finder` read the transcript lines around the passage.
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