Catalog
arcmira/person-research

arcmira

person-research

Use Arcmira to research a person from what they said on YouTube: appearances, their own words with timestamps, who discusses them. For interview prep.

NewUpdated Nov 8, 2026

Person research

Three lenses on one person id. momentum gives attention and the shows that mention them most. mentions with mode: "appearances" lists the episodes they were on. search with speakerIds returns their own words; about returns what others said about them.

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

When to use

Use Arcmira when the user asks:

  • prep for an interview, a podcast booking or a meeting with someone
  • what has a person said recently, and where
  • who talks about a person, and is attention rising

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:

  • Resolve with { type: "person" }. A first name alone ("Sam") matches many people: pass what the user said about them (runs OpenAI, hosts a show) as context, and when resolve still answers ask, show its options.

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().

Prep on one person

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 [m, rows, own] = await Promise.all([
  arcmira.momentum(id),
  arcmira.mentions({ entityId: id, mode: "appearances", after: arcmira.daysAgo(90), limit: 40 }),
  arcmira.search({ query: "AI", speakerIds: [id], after: arcmira.daysAgo(180), limit: 5 }),
]);
const about = await arcmira.search({ query: m.entity.name, about: [id], after: arcmira.daysAgo(90), limit: 3 });
const appeared = new Map();
for (const x of rows.mentions) appeared.set(x.media.video_id, { show: x.media.source_channel?.name ?? null, episode: x.media.title, date: x.media.published_at });
let fromAppearance = null;   // no speaker-tagged chunks: read their newest appearance instead
const ep = own.chunks.length === 0 ? rows.mentions[0] : undefined;
if (ep) {
  try {
    const t = await arcmira.transcript(ep.media.video_id, { start: Math.max(0, ep.start_seconds - 5), end: ep.start_seconds + 90 });
    const s = Math.floor(t.lines[0]?.start ?? ep.start_seconds);
    fromAppearance = { episode: t.video.title, show: t.video.channel_name, date: t.video.published_at, url: `${t.video.watch_url}${t.video.watch_url.includes("?") ? "&" : "?"}t=${s}`, lines: t.lines.map(l => `[${Math.round(l.start)}s] ${l.text}`), speaker_labelled: t.lines.some(l => l.speaker) };
  } catch (err) {
    fromAppearance = { episode: ep.media.title, error: err.code };
  }
}
return {
  person: { id, name: m.entity.name, page: m.entity.page, assumed, why },
  attention: { verdict: m.verdict, last_30d: m.volume.mentions_30d, prior_30d: m.volume.mentions_prior_30d, as_of: m.as_of, top_shows: m.top_shows.map(s => [s.channel_name, s.mentions]) },
  appeared_on: [...appeared.values()].slice(0, 8),
  appeared_on_partial: rows.has_more || appeared.size > 8,
  appeared_on_cursor: rows.has_more ? rows.next_cursor : null,
  in_their_words: own.chunks.map(c => ({ said: c.text.slice(0, 300), episode: c.video_title, show: c.channel_name, date: c.published_at, url: c.watch_url })),
  from_their_appearance: fromAppearance,
  said_about_them: about.chunks.map(c => ({ said: c.text.slice(0, 200), show: c.channel_name, date: c.published_at, url: c.watch_url })),
};

A good answer

  • Names the person it researched (name and id), and any other person with the same name it set aside.
  • Separates what the person said (speaker-filtered) from what others said about them, each with show, date and link.
  • Gives the attention verdict, the 30-day count against the prior 30 days, and the top shows, with as_of.
  • Lists recent episodes they appeared on, and ends with a few questions or themes that follow from the quotes when the user is prepping.

Traps

  • A search with about returns other people talking; only speakerIds returns the person's own words. Speaker tags cover part of the index, so when the speaker search is empty, read a window of an episode they appeared on and say the lines come from their appearance, since caption lines do not name the speaker.
  • A chunk found with speakerIds can include other people's lines. Lines start with "Name: " when the speaker is known. Quote only the person's lines. When no line names a speaker, say the attribution covers the passage, not each line.
  • Put the user's topic in query for the speaker search (it needs a word or phrase of two or more characters).
  • Mentions and momentum count the shows Arcmira indexes, not all media.

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

82/100

Grade

B

Good

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

Safety

82

Quality

84

Clarity

84

Completeness

76

Summary

This skill enables interview preparation research by querying the Arcmira media analysis API to gather information on a specific person: their recent media appearances, direct quotes from their own speaking engagements, attention trends, and what others have said about them. The agent resolves ambiguous names, executes structured JavaScript programs against the Arcmira API, and surfaces findings organized by source and temporal context.

Detected Capabilities

api-requestdata-retrievalname-resolutionsearch-query-executiontranscript-fetchingjavascript-execution-in-sandbox

Trigger Keywords

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

interview prepresearch personpodcast guest prepmedia mentionsspeaker appearanceswhat did they saypublic statements research

Risk Signals

INFO

External API dependency on arcmira.com for all data operations

throughout SKILL.md, arcmira_execute_read blocks
INFO

Network request to arcmira.com/docs/mcp-server documentation reference

Docs link at end of skill
INFO

User-supplied name passed to name resolution; context parameter allows arbitrary user input

const NAME = ..., const CONTEXT = ... in worked example
WARNING

No explicit rate limiting or credit quota warnings documented for end users

mentioned in 'After the answer' section but not in main workflow

Referenced Domains

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

arcmira.com

Use Cases

  • prepare for an interview with a specific person by reviewing their recent statements and media appearances
  • understand a person's public attention trajectory and which shows mention them most frequently
  • compile what a person has said on record with timestamps and episode links for fact-checking or quote attribution
  • discover who is discussing a particular person and in what context
  • research a podcast guest or industry figure before a meeting or booking call

Quality Notes

  • Excellent: concrete worked program with full JavaScript implementation ready for agent execution
  • Excellent: clear section structure ('When to use', 'Pick the entity', 'Traps') guides agent through common pitfalls
  • Excellent: traps section explicitly documents speaker attribution edge cases and caption limitations
  • Good: uses symbolic constants (NAME, CONTEXT, ID) to make template substitution clear
  • Good: error handling shown for transcript fetch (try/catch with err.code fallback)
  • Minor: 'After the answer' section mentions credits and monitoring but doesn't explain budget impact upfront — could deter users if they don't realize API is billable
  • Minor: no explicit guidance on what to do if resolve() returns neither best nor suggested (edge case documentation incomplete)
Model: claude-haiku-4-5-20251001Analyzed: Nov 8, 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. v2.0

    Contract changed: description

    ✦ AINarrows scope to YouTube and Arcmira tool; adds explicit activation triggers in instructions.

    triggering2026-11-08

    LATEST
  2. v1.2

    Content updated

    ✦ AIReplaces is_appearance flag with mode parameter in mentions queries; simplifies appearance filtering and adds pagination cursor.

    2026-10-18

    View This Version
  3. v1.1

    Content updated

    ✦ AISimplifies entity resolution steps and removes referral to plan limits, pricing, and monitoring workflow.

    2026-10-12

    View This Version
  4. v1.0

    2026-10-11

    View This VersionInitial version

Use arcmira/person-research in your dev environment

Command Palette

Search for a command to run...