agentleFS
mnbresearchmnbresearch/mnb-claude-skills/interview-prep-coach/SKILL.md

interview-prep-coach

Skill1 starsChanged 4 months agoMITView on GitHub

Prepare candidates for specific job interviews with company research, likely questions, structured answers, and mock practice. Use when someone is preparing for an interview: researching a company before an interview, building answers to behavioural questions, prepping for a technical or role-specific round, structuring STAR-format stories, preparing questions to ask the interviewer, or doing a mock interview. Triggers on "help me prep for an interview at [company]", "interview questions for [role]", "how do I answer 'tell me about yourself'", "STAR method for my experience", "mock interview me", "what should I ask the interviewer", or "I have a [role] interview tomorrow". Tailors prep to the specific role, company, and candidate rather than generic advice.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    If they haven't shared their background, get at least the highlights - prep is built on their real experiences, not hypotheticals.

    line 33
  2. Distinctive:

    Look up, if not known:

    line 38
  3. Distinctive:

    Use this to predict the questions.

    line 45
  4. Distinctive:

    Run a mock: ask a question, let them answer, give specific feedback on content and delivery.

    line 93
  5. Distinctive:

    Match answers to what they value: If the company prizes ownership, pick stories showing ownership.

    line 106
  6. Distinctive:

    Never fabricate experiences or coach the candidate to lie.

    line 132
  7. Distinctive:

    Don't invent facts about the company - research or flag as unknown.

    line 134
  8. Distinctive:

    Keep advice honest. If a candidate's answer is weak, say so and help fix it - false confidence fails in the real room.

    line 135

≈ “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

Interview Prep Coach

Prepare a candidate for a specific interview, not interviews in general. Generic advice ("be confident, research the company") is useless. Real prep means: what will THIS company likely ask for THIS role, what are the candidate's actual strongest stories, and how do they deliver them well.


Workflow

Step 1: Establish the specifics

Get the context that makes prep useful:

  • Company and role (exact title)
  • Interview stage (screening, technical, final, panel?)
  • The candidate's background (resume, key experiences)
  • Time until the interview (shapes how much to cover)
  • Any known format (case study, live coding, presentation?)

If they haven't shared their background, get at least the highlights - prep is built on their real experiences, not hypotheticals.

Step 2: Research the company and role (search)

Look up, if not known:

  • What the company does, recent news, their product, their stage
  • The role's likely responsibilities and what they're screening for
  • The company's values/culture (they often ask behavioural questions mapped to these)
  • Common interview formats reported for this company/role (Glassdoor-type intel)
  • Recent developments they might expect the candidate to know

Use this to predict the questions. A fintech PM interview and a SaaS sales interview need completely different prep.

Step 3: Build the question bank

Assemble likely questions in these buckets:

Behavioural (almost always asked):

  • Tell me about yourself
  • Why this company / why this role
  • A challenge you overcame
  • A conflict and how you handled it
  • A failure and what you learned
  • Leadership / initiative example
  • Why are you leaving / why the switch

Role-specific (varies):

  • Technical questions for the domain
  • Case/scenario questions
  • Portfolio/past-work deep dives

Company-specific:

  • Questions tied to their product, market, or recent news
  • Values-based questions matching their stated culture

Step 4: Build strong answers

For behavioural questions, use STAR, but naturally (not robotically):

  • Situation - brief context
  • Task - what needed to happen
  • Action - what THEY specifically did (the meat - use "I" not "we")
  • Result - the outcome, quantified if possible, plus what they learned

Draw answers from the candidate's actual experiences. Help them pick their strongest 4-5 stories that can flex to cover many questions. A great story about a hard project can answer "challenge," "leadership," AND "conflict" with different framing.

Step 5: Prep their questions for the interviewer

Strong candidates ask sharp questions. Help them prepare 3-4 that:

  • Show they researched the company
  • Reveal genuine interest in the role's substance
  • Aren't answerable by a quick Google (don't ask "what does your company do")
  • Good examples: about the team's current challenges, how success is measured in the role, what the first 90 days look like, why the role is open

Step 6: Mock practice (if they want)

Run a mock: ask a question, let them answer, give specific feedback on content and delivery. Be constructive but honest - a mock that only praises doesn't prepare them for a tough interviewer.


Answer quality rules

  • "Tell me about yourself" is not your life story. It's a 60-90 second pitch: present role → key relevant experience → why you're here talking to them. Practice it until it's smooth.
  • Use "I" for behavioural answers. Interviewers assess what YOU did. "We" hides your contribution.
  • Quantify results. "Improved the process" is weak. "Cut turnaround from 5 days to 2" is strong.
  • Have a real failure story. "I'm a perfectionist" is a non-answer everyone sees through. A real failure with a real lesson shows maturity.
  • Match answers to what they value. If the company prizes ownership, pick stories showing ownership.
  • Be concise. Rambling kills interviews. Answer, support with one example, stop.

Role-specific notes

Technical roles: Prep the fundamentals for the stack, be ready to talk through past projects in depth, expect live problem-solving. Practice explaining your thinking out loud.

Product/PM: Expect product sense and case questions ("how would you improve X"), metrics questions, and prioritization scenarios. Have a framework but don't be robotic.

Sales/BD: Expect role-play, "sell me this pen" style, and questions about your pipeline/process. Show you understand their sales motion.

Finance/consulting: Expect technical (valuation, case math) plus fit. Know your resume cold - they will drill into every line.

Leadership roles: Expect scenario questions about managing people, conflict, and strategic tradeoffs. Show judgment, not just experience.


Hard rules

  • Never fabricate experiences or coach the candidate to lie. Help them frame REAL experiences compellingly - that's the whole job.
  • Don't invent facts about the company - research or flag as unknown.
  • Keep advice honest. If a candidate's answer is weak, say so and help fix it - false confidence fails in the real room.
  • This is a stressful time for people. Be encouraging and practical, not intimidating.

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.