Interview Prep logo

Interview Prep

Community
jamditis
interview-prep

Interview preparation and recording-consent law. Use for research, question frameworks, one-party or all-party consent rules.

Overview

Publisherjamditis
Repositoryclaude-skills-journalism
Skill nameinterview-prep
Stars
397
Forks
64
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by jamditis on GitHub. Read the source before you install it.

Installation

Install the Interview Prep AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jamditis/claude-skills-journalism.git /tmp/claude-skills-journalism
mkdir -p .claude/skills
cp -r /tmp/claude-skills-journalism/journalism-core/skills/interview-prep .claude/skills/interview-prep
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Interview Prep in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Interview Prep on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Interview Prep is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Interview preparation

Interviews fail in the preparation, not the conversation. This skill covers pre-interview research, question design, logistics, and follow-up.

When to use

  • Preparing to interview a source
  • Developing question frameworks for recurring interview types
  • Managing interview logistics and consent
  • Planning follow-up after initial interviews
  • Training new reporters on interview technique

Pre-interview research checklist

Background research

markdown
## Source background check

### Public records
- [ ] Professional licenses verified
- [ ] Court records checked (civil/criminal)
- [ ] Business registrations confirmed
- [ ] Property records (if relevant)
- [ ] Campaign finance (if political figure)
- [ ] SEC filings (if corporate)

### Professional background
- [ ] LinkedIn profile reviewed
- [ ] Current employer confirmed
- [ ] Previous employers noted
- [ ] Published work reviewed
- [ ] Conference appearances checked
- [ ] Professional associations

### Social media audit
- [ ] All platforms identified (X, Bluesky, Threads, Mastodon, Instagram, Facebook, LinkedIn, TikTok, YouTube, Substack, etc.)
- [ ] Post history reviewed
- [ ] Connections/followers analyzed
- [ ] Previous statements on topic found
- [ ] Any deleted content recovered? (See **web-archiving** skill for Wayback / Archive.today retrieval)

### Media appearances
- [ ] Previous interviews found
- [ ] Statements consistent with current position?
- [ ] Other journalists' assessments
- [ ] Any retractions or corrections involving them?

Context research

markdown
## Topic preparation

### Essential knowledge
- [ ] Key facts about the topic confirmed
- [ ] Timeline of events established
- [ ] Other stakeholders identified
- [ ] Conflicting accounts noted
- [ ] Documents/data reviewed

### What to know before you dial
- [ ] How do they fit into the story?
- [ ] What do I NEED from this interview?
- [ ] What might they be reluctant to discuss?
- [ ] What have they said publicly before?

Question framework

The essential questions

Every interview should be built to answer:

  1. What happened? (Facts)
  2. Why did it happen? (Causes)
  3. What did you do/decide/see? (Actions)
  4. What does it mean? (Significance)
  5. What's next? (Implications)

Question types

TypePurposeExample
Open-endedGet the full story"Walk me through what happened that day."
ClarifyingPin down details"When you say 'soon after,' do you mean minutes or hours?"
ProbingGo deeper"Why do you think that happened?"
Follow-upCatch inconsistencies"Earlier you said X, but now you mentioned Y. Help me understand."
ConfrontationalChallenge statements"Documents show [fact]. How do you respond?"
ClosingEnsure completeness"Is there anything I didn't ask that you think I should know?"

Question templates by interview type

Profile interview:

markdown
1. Background: "Tell me about where you grew up / how you got started."
2. Turning point: "When did you realize [X] was your path?"
3. Challenge: "What was the hardest moment in [period]?"
4. Values: "What principle guides your work?"
5. Future: "What are you working on next?"

Investigative interview:

markdown
1. Establish rapport: Non-threatening background questions first
2. Timeline: "Walk me through [event] from the beginning."
3. Details: "Who else was there? What did you see/hear?"
4. Documentation: "Do you have any records of this?"
5. Corroboration: "Who else can confirm this?"
6. Response: "What did [other party] say when you raised this?"

Expert/explainer interview:

markdown
1. Credentials: "What's your expertise in this area?"
2. Plain language: "Explain [concept] as if I'm not a specialist."
3. Context: "How common/unusual is [situation]?"
4. Significance: "Why does this matter?"
5. Sources: "Where can I learn more? Who else should I talk to?"

Victim/sensitive interview:

markdown
1. Control: "Take your time. You can stop at any point."
2. Open: "Tell me what you're comfortable sharing."
3. Specific: "Can you describe [specific detail]?"
4. Impact: "How has this affected you?"
5. Agency: "What do you want people to understand?"
6. Check-in: "Are you okay to continue?"

Recording and consent

Recording laws by state

State recording-consent law is jurisdiction-specific and shifts. Some states distinguish telephone from in-person recording; others treat electronic communications under a separate statute; case law in several states (e.g., Massachusetts, Michigan, Connecticut) has narrowed or expanded the original statutory rule.

The single most reliable reference is the Reporters Committee for Freedom of the Press Reporter's Recording Guide at rcfp.org/reporters-recording-guide. It is maintained continuously and provides per-state breakdowns covering one-party vs. all-party consent, phone-vs-in-person distinctions, hidden-recording rules, and federal preemption.

General categories:

  • One-party consent (federal default). You can record without telling the other person if you are a party to the conversation. You should tell them anyway for ethical reasons.
  • All-party (two-party) consent. All participants must consent. As of 2025-2026 this category includes (non-exhaustive, verify against RCFP before relying): California, Florida, Illinois, Maryland, Massachusetts, Montana, Nevada, New Hampshire, Pennsylvania, Washington. Several other states (Connecticut, Michigan, Oregon, Delaware, Vermont, Hawaii) apply two-party rules in some contexts but not all, RCFP has the per-context details.
  • Cross-state calls. When the parties are in different states, the stricter state's law generally controls. If you are in a one-party state interviewing someone in a two-party state, get consent.

Always do, regardless of jurisdiction:

  • State clearly at the start: "I'm recording this interview. Is that okay?"
  • Get affirmative consent on the recording itself.
  • Note the consent in your notes.

This protects you legally everywhere and is the ethical baseline.

Consent template

markdown
## Recording consent

Date: [date]
Interviewer: [your name]
Subject: [their name]
Medium: [phone/video/in-person]

[At start of recording:]
"This is [your name] with [publication], interviewing [their name] on [date].
I'm recording this conversation. Do I have your permission to record?"

[Their response: yes/no]

"And you understand this may be used for publication?"

[Their response: yes/no]

Attribution guidelines

On the record (default)

  • Everything can be published with full name and title
  • This is the standard expectation unless otherwise agreed

On background

  • Information can be used, but source not identified by name
  • Agree on description: "a senior official," "someone familiar with the matter"
  • Confirm exact wording before interview ends

Deep background

  • Information can guide reporting but cannot be attributed at all
  • Verify independently before publishing
  • Rarely appropriate, push for at least background

Off the record

  • Information is for your knowledge only
  • Cannot be published or used to seek confirmation elsewhere
  • Agree to this BEFORE they share information, not after
  • If they say something on the record then try to take it off, you can refuse

Clarifying attribution

markdown
Before starting:
"Just to be clear on attribution, are we on the record?"

If they request otherwise:
"I'd prefer on the record. What concerns you about that?"

If they insist:
"Okay, we'll go on background. What description can I use?"

Document it:
"So I can refer to you as [agreed description], is that right?"

Interview logistics

Scheduling template

markdown
## Interview request

To: [source name]
Subject: Interview request - [topic] - [publication]

[Name],

I'm a [title] at [publication] working on a story about [brief, honest description].

I'd like to speak with you because [why they're relevant]. The interview would take approximately [realistic time estimate].

Are you available [specific days/times]? I can do phone, video, or in-person, whatever works best for you.

Please let me know if you have questions about the story.

[Your name]
[Contact info]

Pre-interview checklist

markdown
## Day-of checklist

### Equipment
- [ ] Primary recorder charged/working
- [ ] Backup recorder ready
- [ ] Notebook and pens
- [ ] Printed questions/documents
- [ ] Business cards

### Logistics
- [ ] Location confirmed
- [ ] Contact's phone number for day-of
- [ ] Tested video/phone connection
- [ ] Quiet space secured

### Preparation
- [ ] Questions reviewed and prioritized
- [ ] Documents to reference ready
- [ ] Timeline of facts clear in mind
- [ ] Backup questions if interview goes short

During the interview

Opening

  • Small talk to build rapport (brief)
  • Confirm time available
  • State recording and get consent
  • Start with easy, open questions

Active listening

  • Let them finish sentences
  • Use silence, don't fill every pause
  • Take notes even if recording
  • Note non-verbal cues separately

Real-time verification

  • Ask for specifics: dates, names, locations
  • Request documentation during interview
  • Ask "How do you know that?"
  • Note inconsistencies for follow-up

Closing

  • "Is there anything I didn't ask that I should have?"
  • "Who else should I talk to?"
  • "Can I follow up if I have more questions?"
  • Thank them for their time

Follow-up protocols

For recording backup, transcription tooling, and quote verification mechanics, use the interview-transcription skill. The notes here cover only the post-interview editorial steps that aren't covered there.

Immediate (same day)

  • Back up recording (see interview-transcription for storage and naming)
  • Note observations not on recording (body language, environment, off-mic remarks)
  • Send thank-you if appropriate

Within 48 hours

  • Fact-check claims against available records
  • Identify gaps requiring follow-up
  • Add source to contacts database

Before publication

  • Verify quotes are accurate
  • Confirm attribution terms
  • Offer to read back quotes if promised
  • Give chance to respond to characterizations (if newsworthy)

Difficult situations

They want to go off the record mid-interview

"Before I agree to that, let me hear what you want to tell me, and then we can discuss how to handle it."

They refuse to answer

"I understand you can't discuss that. Can you point me to someone who can?"

They're hostile

Stay calm. Keep questions factual. "I'm just trying to understand what happened."

They're crying/emotional

Pause. "Take your time. We can stop whenever you need."

They lie

Don't accuse. Present contradicting evidence: "Documents show [X]. Can you help me understand the discrepancy?"


Good interviews require good preparation. The conversation is the easy part.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Interview Prep AI skill do?

Interview preparation and recording-consent law. Use for research, question frameworks, one-party or all-party consent rules.

Why use Interview Prep on TypingMind?

Because you install it once and use it with any model. Interview Prep is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Interview Prep in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jamditis/claude-skills-journalism/tree/master/journalism-core/skills/interview-prep. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Interview Prep?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Interview Prep?

As many as you like. As long as a model supports skills, you can use Interview Prep with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Interview Prep AI skill free?

Yes. It is published on GitHub by jamditis under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇