# Guest Researcher

> Research potential podcast guests — background, expertise, recent work, and prepare interview briefs

- Skill: `uitbreidenos/guest-researcher` (Agent Skill)
- Install (CLI): `npx skillmds@latest add uitbreidenos/guest-researcher`
- Raw SKILL.md: https://api.skillmd.com/api/skills/uitbreidenos/guest-researcher/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Research & Search
- Author: UitbreidenOS (https://skillmd.com/u/uitbreidenos)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/uitbreidenos/guest-researcher

---


## When to activate

- Researching potential guests for upcoming episodes
- Preparing interview briefs with background and talking points
- Finding guests that align with episode themes
- Creating outreach templates for guest invitations
- Building a guest pipeline with priority rankings

## When NOT to use

- For episode content planning (use episode-outliner)
- For post-interview fact-checking
- For audience research or listener analytics

## Instructions

1. **Define guest criteria.** What expertise, experience level, and perspective does this episode need?
2. **Research background.** LinkedIn, Twitter/X, personal website, recent talks/papers/articles, company role.
3. **Find unique angles.** What has this guest said recently that's contrarian, insightful, or newsworthy?
4. **Prepare 10 questions.** 3 warm-up, 5 deep-dive, 2 rapid-fire. Avoid questions they've answered 100 times.
5. **Create interview brief.** One-page: bio, expertise areas, recent work, key questions, topics to avoid.
6. **Draft outreach email.** Personalized, specific about why THEM, clear time commitment, and value proposition.
7. **Build guest pipeline.** Spreadsheet: name, status (researched/invited/confirmed), episode theme, date.

## Example

```
Guest Brief: Dr. Sarah Chen
Role: VP Engineering, ScaleAI
Expertise: Distributed systems, ML infrastructure, team scaling
Recent: Talk at KubeCon 2026 on "ML at Scale Without the Pain"
Twitter: @sarahchen (42K followers)

Key Questions:
1. "You mentioned ML infra is 80% plumbing — what did you mean?"
2. "What's the biggest mistake teams make when scaling ML pipelines?"
3. "How do you balance speed of experimentation with production reliability?"

Topics to avoid: Company financials, competitor comparisons
```