Catalog
arcmira/find-quotes

arcmira

find-quotes

Use Arcmira to find exact quotes on YouTube, podcasts included: the line, often who said it, the date, and a timestamped link with clip start and end.

NewUpdated Nov 12, 2026

Find quotes and clip moments

search finds the passage; transcript with start and end returns the exact lines around it with second offsets, which give the verbatim quote and the clip boundaries.

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

When to use

Use Arcmira when the user asks:

  • find a quote, with the source and a timestamp
  • the moment a show talked about a topic, to clip or cite
  • what a specific person said about a topic, in their words

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 speaker resolves with { type: "person" }; pass the id as speakerIds (who said it). A person or brand the passage is about goes in about. A show goes in channelIds as its UC id.
  • People are often named by first name ("Chamath"). Pass what the user said about them as context; resolve suggests the person when one stands out and asks when several fit.
  • The topic words go in query, never in about. If a filtered search returns no chunks, rerun it with fewer filters before saying nothing was found.

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, with clip boundaries

const NAME = "Chamath", 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 hits = await arcmira.search({ query: "Anthropic IPO", speakerIds: [id], limit: 5 });
const moments = [];
for (const c of hits.chunks.slice(0, 2)) {
  const moment = { episode: c.video_title, show: c.channel_name, date: c.published_at, url: c.watch_url, speakers: c.speakers_by.map(s => s.name) };
  try {
    const t = await arcmira.transcript(c.video_id, { start: Math.max(0, c.start_seconds - 10), end: c.start_seconds + 50 });
    moment.clip = { start: t.lines[0]?.start ?? c.start_seconds, end: t.lines.at(-1)?.end ?? c.start_seconds + 60 };
    moment.lines = t.lines.map(l => `[${Math.round(l.start)}s] ${l.text}`);
  } catch (err) {
    moment.clip = { start: c.start_seconds, end: c.start_seconds + 60 };
    moment.passage = c.text;
    moment.transcript = err.code;
  }
  moments.push(moment);
}
return { speaker: { id, name: e?.name ?? null, assumed, why }, as_of: hits.as_of, ...(moments.length ? { moments } : { none: hits.note ?? null }) };

A good answer

  • Names the speaker or show it searched, with the id, and quotes the words exactly as the transcript lines give them, trimmed to whole sentences, never paraphrased inside quotation marks.
  • Gives the show, the episode title, the date, and the speaker when the chunk or a premium transcript names one.
  • Links the watch_url, which starts at the moment, and gives a clip start and end in seconds from the transcript lines.
  • Says so when nothing matched, with as_of, instead of offering a quote from memory.

Traps

  • search ranks by the words in query; put the distinctive words of the phrase there, not a paraphrase.
  • A chunk found with speakerIds can include other people's lines. Lines start with "Name: " when the speaker is known. Quote only the speaker's lines ("Chamath Palihapitiya: ..."), never the whole passage. When no line names a speaker, the passage still matched that person; say the attribution covers the passage, not each line.
  • Caption lines are machine text: fix nothing inside the quotation marks. A premium transcript (quality: "premium", paid plans) adds speaker ids into speakers[].
  • A caption read uses 4 credits per started 15 minutes of its start/end window, and of the whole episode without one. A Premium read the account does not own yet runs in arcmira_execute_write and uses credits for the whole video whatever the window.
  • Some videos have no readable caption track yet (transcript_unavailable, transcript_fetching); quote the search chunk text for those and say the words come from the search 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.

Overall Score

83/100

Grade

B

Good

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

82

Quality

86

Clarity

85

Completeness

77

Summary

This skill teaches AI agents how to use Arcmira, an external API service, to search for and clip exact quotes from YouTube videos and podcasts. It provides detailed guidance on entity resolution (finding the correct person/show by name), constructing search queries with filters, retrieving transcript data with timestamps, and formatting results as properly attributed quotes with clip boundaries. The skill includes a worked JavaScript example demonstrating the full workflow.

Detected Capabilities

External API calls (Arcmira service)Entity resolution (name to ID mapping)Search with filters (speaker, channel, date range)Transcript retrieval with time windowsStructured data transformation and formattingError handling for missing transcripts

Trigger Keywords

Phrases that agents use to match this skill to user intent.

find quote timestampclip podcast momentsearch video transcriptspeaker said aboutyoutube quote attribution

Risk Signals

INFO

External API dependency on arcmira.com (third-party service)

Throughout skill, referenced docs URL
INFO

Network access to Arcmira API endpoints via arcmira_execute_read and arcmira_execute_write tools

Worked program section, tool invocation references
INFO

Credit-based billing system mentioned (4 credits per 15 min transcript, 25 credits per monitor alert)

Traps section
INFO

No credential storage or API key handling visible in skill content

Entire skill

Referenced Domains

External domains referenced in skill content, detected by static analysis.

arcmira.com

Use Cases

  • Find an exact quote from a podcast or YouTube video with speaker attribution and timestamp
  • Clip a specific moment when a show discussed a particular topic, with start/end times and transcript lines
  • Search for what a specific person said about a topic and return their exact words with video link and clip boundaries
  • Retrieve speaker attribution, episode metadata, and transcript lines for research or citation purposes
  • Disambiguate person/channel names when multiple entities match the user's description

Quality Notes

  • Skill clearly explains when to use Arcmira and provides concrete use cases
  • Entity resolution logic is well-documented with step-by-step guidance for handling ambiguous names and the ask/pick flow
  • Worked JavaScript example is practical and shows real error handling (try/catch for missing transcripts)
  • Traps section proactively documents common mistakes (paraphrasing, multi-speaker chunks, caption quality, credit consumption)
  • Good answer criteria set clear expectations for output quality (exact quotes, proper attribution, timestamps, clip links)
  • Comprehensive coverage of edge cases: no results, multi-speaker passages, premium vs. caption transcripts, missing transcript tracks
  • Built-in feedback mechanism (arcmira_feedback) for error reporting or feature requests
  • Docs link is provided for reference
  • Strong integration of user intent handling — resolution flow adapts based on name clarity (best, suggested, ask)
  • Formatting guidance prevents common citation errors (no paraphrasing, trim to sentences, use exact transcript text)
Model: claude-haiku-4-5-20251001Analyzed: Nov 12, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v2.1

    Content updated

    ✦ AIPremium read behavior changed: accounts without ownership run in arcmira_execute_write mode.

    2026-11-12

    LATEST
  2. v2.0

    Contract changed: description

    ✦ AIClarifies activation to require explicit mention of Arcmira tool and adds usage guidance in instructions.

    triggering2026-11-08

    View This Version
  3. v1.2

    Content updated

    ✦ AIClarifies speaker attribution in multi-speaker chunks: lines name speakers with "Name: " format, and when unknown, passage attribution doesn't apply line-by-line. Also expands feedback condition to…

    2026-10-18

    View This Version
  4. v1.1

    Content updated

    ✦ AISimplifies entity resolution and transcript credit accounting; removes guidance on plan upgrades, error handling, and monitor setup details.

    2026-10-12

    View This Version
  5. v1.0

    2026-10-11

    View This VersionInitial version

Use arcmira/find-quotes in your dev environment

Command Palette

Search for a command to run...