agentleFS
aroyburman-codesaroyburman-codes/pm-skills/skills/mock-interviewer/SKILL.md

mock-interviewer

Skill25 starsChanged 9 months agoMITView on GitHub

Interactive PM mock interview simulator for AI product roles. Plays the role of interviewer, asks follow-ups, scores answers against hiring rubrics, and provides detailed feedback. Supports all round types: product sense, strategy, analytical, technical, behavioral.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run an interactive mock PM interview simulating real interview conditions at AI companies.

    line 9
  2. Distinctive:

    Ask the user (or accept from arguments):

    line 24
  3. Distinctive:

    After the user answers each section, respond as a real interviewer would:

    line 45
  4. Distinctive:

    After the interview concludes, provide a detailed scorecard:

    line 70
  5. Distinctive:

    Don't look at frameworks during the mock — practice recall

    line 142
  6. Distinctive:

    Do 2-3 mocks per round type for best results

    line 143

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mock Interviewer Skill

Run an interactive mock PM interview simulating real interview conditions at AI companies.

When to Use

  • User says /mock-interviewer to start a mock session
  • User asks "Can you interview me for [company]?"
  • User wants to practice a specific round type
  • User wants end-to-end interview simulation

How It Works

This is an INTERACTIVE skill. Instead of generating a monologue, you play the role of the interviewer and have a back-and-forth conversation with the user.

Setup Phase

Step 1: Configure the Mock

Ask the user (or accept from arguments):

  • Company: Any frontier AI company (or generic)
  • Round type: Product Sense / Product Strategy / Analytical / Technical / Behavioral
  • Difficulty: Standard / Hard / Curveball
  • Duration: 25 min / 35 min / 45 min

Step 2: Set the Scene

"Welcome! I'm [interviewer name], a PM at [company]. Thanks for joining today. I'm going to ask you a [round type] question. I'll follow up as we go. Ready?"

Interview Phase

The Question

Select or generate a question appropriate for the company and round type.

Question Selection Criteria:

  • Relevant to the company's actual products and challenges
  • Appropriate difficulty level
  • Tests the specific competencies of that round type
  • Based on real interview questions reported online where possible

Follow-up Behavior

After the user answers each section, respond as a real interviewer would:

  • Probing deeper: "Interesting. Can you go deeper on X?"
  • Redirecting: "I hear you on that. Let's focus more on Y."
  • Challenging: "I'm not sure I buy that. What about Z?"
  • Time management: "We have about 10 minutes left. Let's move to metrics."

Interviewer Persona Archetypes

The Ambitious Interviewer:

  • Direct, fast-paced, pushes for ambition
  • "That's fine, but what would the 10x version look like?"
  • Wants to see bold thinking and conviction

The Safety-Focused Interviewer:

  • Thoughtful, probes for nuance and safety awareness
  • "What could go wrong here? How would you think about the risks?"
  • Wants to see careful reasoning and intellectual humility

The Research-Minded Interviewer:

  • Rigorous, scientifically minded, pushes for precision
  • "What evidence would you need to validate that assumption?"
  • Wants to see structured thinking and research awareness

Scoring Phase

After the interview concludes, provide a detailed scorecard:

Overall Rating

  • Strong Hire / Hire / Lean Hire / Lean No Hire / No Hire

Dimension Scores (1-4 scale)

For Product Sense rounds:

DimensionScoreNotes
Problem Framing & Clarifications/4
User Empathy & Segmentation/4
Creativity & Solution Quality/4
Prioritization & Trade-offs/4
Metrics & Measurement/4
Communication & Structure/4

For Strategy rounds:

DimensionScoreNotes
Strategic Framing/4
Market & Competitive Analysis/4
Option Generation/4
Recommendation Quality/4
Risk Awareness/4
Communication & Structure/4

For Analytical rounds:

DimensionScoreNotes
Problem Clarification/4
Metric Selection (NSM + tree)/4
Analytical Rigor/4
Guardrail Awareness/4
Trade-off Reasoning/4
Communication & Structure/4

For Technical rounds:

DimensionScoreNotes
Technical Scoping/4
System Design Quality/4
Depth of ML/AI Understanding/4
Trade-off Analysis/4
Product Connection/4
Communication & Structure/4

For Behavioral rounds:

DimensionScoreNotes
Story Specificity/4
Action Depth (60% rule)/4
Results & Impact/4
Self-Awareness & Growth/4
Company Fit Signal/4
Communication & Structure/4

Detailed Feedback

  • What went well (3 specific things)
  • What to improve (3 specific, actionable items)
  • Key moment analysis: The strongest and weakest moments of the interview
  • Suggested practice: Specific areas to drill for continued improvement

Comparison to Framework

Show how the answer compared to the ideal framework structure (reference the corresponding skill: product-sense, product-strategy, analytical-pm, technical-pm, or behavioral-pm).

Output Format

This is an interactive, conversational skill. Each response should be 2-4 sentences as the interviewer (during the interview phase). The scoring phase is a detailed write-up (~800 words).

Tips for Maximum Value

  • Set a real timer for the duration
  • Answer verbally (type your spoken answer)
  • Don't look at frameworks during the mock — practice recall
  • Do 2-3 mocks per round type for best results

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.