Expert Interviewing And Information Extraction logo

Expert Interviewing And Information Extraction

Community
MichaelRochonnn
Expert Interviewing and Information Extraction

Use when conducting expert interviews to extract critical business information, handling interviewees who resist with "I don't know" or "I have no ideas", or maintaining professional relationships through proper follow-up protocols.

Overview

PublisherMichaelRochonnn
Repositorymckinsey-bcg-consulting
Skill nameExpert Interviewing and Information Extraction
Stars
77
Forks
16
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Expert Interviewing And Information Extraction 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.
    https://github.com/MichaelRochonnn/mckinsey-bcg-consulting/tree/main/expert-interviewing-mckinsey
  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/MichaelRochonnn/mckinsey-bcg-consulting.git /tmp/mckinsey-bcg-consulting
mkdir -p .claude/skills
cp -r /tmp/mckinsey-bcg-consulting/expert-interviewing-mckinsey .claude/skills/michaelrochonnn-expert-interviewing-and-information-extraction
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Expert Interviewing And Information Extraction 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 Expert Interviewing And Information Extraction 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 Expert Interviewing And Information Extraction 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.

Expert Interviewing and Information Extraction

When to Use

  • Need to gather specific information from subject matter experts or stakeholders
  • Facing interviewees who claim ignorance or lack of ideas
  • Conducting interviews in sensitive or tense environments
  • Following up after significant time investments by interviewees

Core Workflow

1. Apply Seven Core Interview Strategies

Leverage Authority: Have the interviewee's boss arrange the meeting and communicate importance. When interviewees know their superiors support the interview, misleading or敷衍 responses decrease significantly.

Use Two-Person Teams: Conduct interviews in pairs:

  • One person asks questions while the other takes notes
  • Prevents missing non-verbal cues due to note-taking distraction
  • Provides dual perspectives and specialized expertise
  • Ensure questioner and note-taker maintain synchronization

Listen, Don't Lead:

  • Avoid seeking simple yes/no answers
  • Obtain open-ended, detailed responses through active listening
  • Speak minimally; ensure only that the interview stays on topic
  • Remember: Interviewees usually know their industry better than you

Paraphrase Extensively:

  • Restate interviewee answers in organized form
  • Confirms correct understanding
  • Provides opportunity for interviewees to add information or emphasize key points

Use Indirect Approaches:

  • Avoid interrogation-style questioning
  • Excessive pressure triggers defensive mechanisms and potential refusal to cooperate
  • Maintain conversational tone rather than aggressive questioning

Limit Question Quantity:

  • Focus on 2-3 critical questions; avoid wasting time on known information
  • Recognize that business interviews are often unpleasant experiences
  • Stop before reaching hostility or non-cooperation; leave room for future contact

Apply the Columbo Strategy:

  • Basic: When leaving, pretend to remember one last question and turn back—often yields crucial information
  • Advanced (Super Columbo): Wait 1-2 days, then return casually asking a follow-up question—reduces aggression and increases information flow

2. Push Past "I Have No Ideas"

When interviewees respond with "I have no ideas" or "I don't know":

  • Interpret the Excuse: Recognize this usually means "I'm too busy," "I'm not smart enough," or "I'm too lazy"
  • Treat as Challenge: View this as a starting point, not an endpoint—like a sculptor removing everything that doesn't look like an elephant
  • Ask Specific Questions: Drill down with targeted questions (e.g., "Do you know competitor advertising spending?")
  • Accept Educated Guesses:
    • Numbers need not be 100% accurate
    • Estimates within 2x of actual values are acceptable for business decisions
    • Precision sufficient for decision-making is the standard
  • Maintain Standards: Do not accept "I have no ideas" from yourself or others; with thought and investigation, useful information always exists

3. Execute Post-Interview Protocol

For interviews exceeding 30 minutes:

  • Timing: Return to office and write immediately
  • Format: Use company letterhead with carefully crafted, personalized language
  • Content:
    • Express appreciation for their time
    • Demonstrate professionalism
    • Avoid generic templates; customize to avoid computer-generated appearance
  • Value: Leaves positive impression and builds long-term relationships; significant returns possible (e.g., clients displaying letters for years)

Key Principles

  • Persistence Over Acceptance: Do not accept surface-level ignorance; dig deeper with specific questions
  • Relationship Management: Maintain goodwill for future information needs
  • Precision Standards: Accept directional accuracy over perfect precision for business decisions

Output

Detailed information sufficient for business decision-making, maintained professional relationships, and documented insights for analysis.

Frequently asked questions

What does the Expert Interviewing And Information Extraction AI skill do?

Use when conducting expert interviews to extract critical business information, handling interviewees who resist with "I don't know" or "I have no ideas", or maintaining professional relationships through proper follow-up protocols.

Why use Expert Interviewing And Information Extraction on TypingMind?

Because you install it once and use it with any model. Expert Interviewing And Information Extraction 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 Expert Interviewing And Information Extraction in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MichaelRochonnn/mckinsey-bcg-consulting/tree/main/expert-interviewing-mckinsey. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Expert Interviewing And Information Extraction?

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 Expert Interviewing And Information Extraction?

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

Is the Expert Interviewing And Information Extraction AI skill free?

It is published on GitHub by MichaelRochonnn. Check the repository for licensing terms. 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 👇