Master the art of podcast interviewing using NPR training methodology and Tim Ferriss's preparation techniques to extract compelling stories and insights from any guest. Use when: Preparing for a podcast interview with a guest; Designing questions that elicit stories, not soundbites; Struggling to get guests to open up authentically; Planning a new interview-format podcast; Improving your interviewing technique
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill podcast-interview
> Master the art of podcast interviewing using NPR training methodology and Tim Ferriss's preparation techniques to extract compelling stories and insights from any guest.
Source: NPR Training + Tim Ferriss (The Tim Ferriss Show, 700+ episodes)
Core Principle: Great interviews are 80% preparation and 20% presence. "The best interviews feel like conversations, but they're actually carefully orchestrated to extract specific moments of insight, emotion, and story." The interviewer's job is to be genuinely curious while guiding toward revelatory moments.
Why This Matters: Most podcast interviews are forgettable because hosts ask the same questions and accept surface-level answers. NPR-trained interviewers and Tim Ferriss have developed techniques that consistently produce the "good tape" that makes episodes shareable and memorable.
| Claude Does | You Decide |
|-------------|------------|
| Structures production workflow | Final creative direction |
| Suggests technical approaches | Equipment and tool choices |
| Creates templates and checklists | Quality standards |
| Identifies best practices | Brand/voice decisions |
| Generates script outlines | Final script approval |
Help me prepare for a podcast interview with [guest name].
They are known for: [brief background]
Episode angle/theme: [what you want to explore]
Length: [target runtime]
I'm interviewing [guest type] about [topic]. Help me design questions that get stories, not just information.
Review these interview questions and suggest improvements:
[paste questions]
When preparing and conducting interviews, follow this methodology:
Before writing a single question, immerse yourself in your guest.
## Research Checklist
**Primary Sources** (1-2 hours minimum):
□ Read/watch their most substantial long-form content
□ Their book, keynote, or signature work
□ Previous podcast appearances (note what's been asked before)
□ Recent social media activity (what are they thinking about NOW?)
**Secondary Sources** (30-60 min):
□ Wikipedia/bio for career arc and timeline
□ Company/project announcements
□ Industry news involving them
□ Interviews with people who've worked with them
**Look For**:
- Contradictions between what they say and do
- Topics they're NEVER asked about
- Recent changes in their thinking
- Personal moments that shaped their professional life
- The question you're dying to ask
Tim Ferriss's Rule: "I try to find the question they've never been asked that they'd love to answer."
The difference between a mediocre and great interview is the type of questions asked.
## Question Types Hierarchy
**AVOID - Information Questions** ❌
- "What do you do?"
- "How did you get started?"
- "What advice would you give?"
→ Gets: Rehearsed talking points
**BETTER - Scenario Questions** ✓
- "Take me to the moment when..."
- "Walk me through the day..."
- "What was going through your mind when..."
→ Gets: Specific memories, sensory details
**BEST - Emotional Truth Questions** ✓✓
- "What scared you most about that decision?"
- "What did you learn that surprised you?"
- "What's the thing about [topic] that most people get wrong?"
→ Gets: Authentic reflection, vulnerability
Don't just list questions—design a journey.
## Interview Arc Template
**Opening (5-10 min)**
Purpose: Establish rapport, get them talking
- Start with something CURRENT (not their origin story)
- Show you've done your homework
- Ask about something specific and recent
- Example: "I saw your tweet last week about [X]. What prompted that?"
**Middle - Act 1 (10-20 min)**
Purpose: Understand the journey
- Key inflection points
- Decisions that shaped their path
- "What most people don't know about that period..."
- Follow unexpected threads
**Middle - Act 2 (15-25 min)**
Purpose: Go deep on the main topic
- The questions you MUST ask
- Challenges to their public positions
- "How do you reconcile X with Y?"
- The uncomfortable but important questions
**Closing (5-10 min)**
Purpose: Synthesis and takeaways
- What they're working on now
- What they'd do differently
- One piece of advice (but make it specific)
- The question you're afraid to ask
The best material comes from following up, not from prepared questions.
## Follow-Up Techniques
**The Silence**: Say nothing after they finish. Count to 5. They'll fill it with gold.
**The Echo**: Repeat their last few words as a question.
Guest: "...and that's when I knew it was over."
You: "You knew it was over?"
**The Dig**: "Tell me more about that."
**The Redirect**: "Let's go back to something you said earlier..."
**The Challenge**: "Some people would say [counter-argument]. How do you respond?"
**The Feeling**: "How did that make you feel?" (Use sparingly but powerfully)
**The Unexpected**: "That's not what I expected you to say. Why...?"
NPR Rule: Prepare 2x more questions than you'll need, but be ready to throw them all out if the conversation goes somewhere better.
Vulnerability requires safety. Build it intentionally.
## Before Recording
- Share YOUR vulnerabilities about the topic
- Be explicit about your goals: "I want this to be a real conversation"
- Remind them they can say "off the record" anytime
- Start with low-stakes questions to warm up
- Match their energy and pace
## During Recording
- React authentically (laugh, express surprise)
- Share related personal experiences briefly
- Make eye contact (even on video calls)
- Nod, use "mm-hmm" to show engagement
- Never look at your phone or notes while they're sharing something vulnerable
## After Difficult Moments
- Acknowledge what they shared: "Thank you for being so honest about that."
- Give them an easy question to recover
- Return to vulnerable topics gently if needed
## When They Give a Non-Answer
**Technique**: Acknowledge, then redirect
"That's interesting. But I'm curious specifically about..."
"I hear you. Let me ask it differently..."
## When They're Being Promotional
**Technique**: Accept, then pivot to story
"The product sounds great. Take me to the moment you decided to build it."
"Before we get to that—what was the biggest failure on the way there?"
## When They're Uncomfortable
**Technique**: Name it, give an out
"I can tell this is a sensitive topic. We can skip it if you prefer, or..."
"I'm asking because [explain why it matters to listeners]..."
## When You Disagree
**Technique**: Steel-man, then question
"The strongest version of that argument is [X]. But what about [Y]?"
## When They Say Something Wrong
**Technique**: Curious, not confrontational
"That's different from what I've read. Help me understand..."
"Some people would push back on that. What would you say to them?"
Context: Interviewing a CEO who recently sold their company for $500M.
Input:
> Help me prepare for a podcast interview with Sarah Chen, CEO of DataFlow (just acquired by Microsoft for $500M). Episode theme: the journey from side project to acquisition.
Output:
Opening (current, not origin)
The Journey (inflection points)
The Deal (specifics, not platitudes)
The Real Stuff
10. "What's the conversation with your 2019 self—the one with the side project—look like?"
11. "What did the acquisition cost you that money can't buy back?"
Closing
12. "A year from now, what do you hope to have figured out?"
13. "What question do you wish interviewers would stop asking?"
Context: Improving standard interview questions for an author interview.
Input:
> Review these interview questions and suggest improvements:
> 1. What's your book about?
> 2. Why did you write it?
> 3. What's your writing process?
> 4. What advice would you give to aspiring writers?
Output:
1. "What's your book about?" ❌
*Problem: Gets the dust jacket summary*
Better:
2. "Why did you write it?" ❌
*Problem: Gets the rehearsed answer*
Better:
3. "What's your writing process?" ❌
*Problem: Gets generic productivity tips*
Better:
4. "What advice would you give to aspiring writers?" ❌
*Problem: Gets platitudes*
Better:
Every improved question:
## 48 Hours Before
Research:
- [ ] Read/watched their most significant recent work
- [ ] Listened to 2-3 previous podcast appearances
- [ ] Noted what they're NEVER asked
- [ ] Found one thing that surprised me
Questions:
- [ ] 15-20 questions drafted
- [ ] Questions progress from easy → hard
- [ ] At least 3 questions I'm nervous to ask
- [ ] Follow-up prompts ready for each section
Logistics:
- [ ] Confirmed time (with timezone!)
- [ ] Tested recording setup
- [ ] Backup recording method ready
- [ ] Questions sent to guest (optional, some hosts don't)
## 30 Minutes Before
- [ ] Tech check complete
- [ ] Recording test confirmed
- [ ] Water bottle ready
- [ ] Questions printed/visible
- [ ] Phone silenced
## During Recording
- [ ] Started with rapport-building
- [ ] Asked permission to go deeper when needed
- [ ] Followed unexpected threads
- [ ] Used silence effectively
- [ ] Listened more than talked
## After Recording
- [ ] Asked "What didn't I ask that I should have?"
- [ ] Captured any off-mic gold
- [ ] Thanked them genuinely
- [ ] Noted key timestamps for editor
## For Founders/Entrepreneurs
- "What was the lowest moment, and how did you get through it?"
- "What's the decision you'd make differently?"
- "What does your inner critic say to you?"
## For Authors/Experts
- "What changed in your thinking while writing this?"
- "What's the critique of your work that stings because it's partially true?"
- "What question do you hope someone asks you?"
## For Executives/Leaders
- "Tell me about a time you were wrong about someone."
- "What's a decision you made that was right but unpopular?"
- "What do you know now that you wish you knew at 30?"
## For Creatives
- "Walk me through the moment you knew this project would work."
- "What did you have to unlearn?"
- "What's the thing you made that you thought would succeed but didn't?"
name: podcast-interview
category: audio
subcategory: podcast
version: 1.0
author: MKTG Skills
source_expert: NPR Training, Tim Ferriss
source_work: NPR's Podcast Start Up Guide, The Tim Ferriss Show
difficulty: intermediate
estimated_value: $500-2,000 per interview (equivalent preparation time)
tags: [podcast, interview, research, questions, guests]
created: 2026-01-26
updated: 2026-01-26
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Create and train AI learning plugins with AgentDB's 9 reinforcement learning algorithms. Includes Decision Transformer, Q-Learning, SARSA, Actor-Critic, and more. Use when building self-learning agents, implementing RL, or optimizing agent behavior through experience.
Design LLM applications using LangChain 1.x and LangGraph for agents, memory, and tool integration. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
Provide read-only NemoClaw maintainer policy. Use for questions about Issue Type, labels, Project fields, release labels, triage, duplicates, blocked items, and maintainer decisions. Trigger keywords - maintainer policy, workflow policy, project workflow, issue type, labels, label taxonomy, needs labels, project status, blocked issue, duplicate issue, daily release label, release train, triage policy.
Run stepped HTTP load tests with ab/wrk, ramping concurrency levels to collect p50/p90/p99 latency, detect performance inflection points, and recommend optimal concurrency. Triggered by requests like 'load test this URL', 'benchmark my API', 'find the max concurrency', or mentions of p99 latency, throughput saturation, or capacity planning.
Record episodes for an agentic env via teleoperation (keyboard, SO-ARM leader, or VR) into HDF5. Use when the user wants to teleop or record human demos.
| Investigate outliers, rare events, spikes, and suspicious records in datasets. Use as an explicit anomaly-analysis helper when you want concrete anomaly-detection workflow guidance, not generic data validation or end-to-end ML ownership.
Run any question, idea, or decision through a council of 5 AI advisors who independently analyze it, peer-review each other anonymously, and synthesize a final verdict. Based on Karpathy's LLM Council methodology. MANDATORY TRIGGERS: 'council this', 'run the council', 'war room this', 'pressure-test this', 'stress-test this', 'debate this'. STRONG TRIGGERS (use when combined with a real decision or tradeoff): 'should I X or Y', 'which option', 'what would you do', 'is this the right move', 'validate this', 'get multiple perspectives', 'I can't decide', 'I'm torn between'. Do NOT trigger on simple yes/no questions, factual lookups, or casual 'should I' without a meaningful tradeoff (e.g. 'should I use markdown' is not a council question). DO trigger when the user presents a genuine decision with stakes, multiple options, and context that suggests they want it pressure-tested from multiple angles.
Take guia-matthieu/podcast-interview from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.