Complete AI Training

Skill · Education

Interview prep

Runs realistic interview practice for a specific role, calibrating questions to the company and seniority, then debriefing with scored feedback and rewritten answers. Use when preparing for a job interview, practicing answers, or requesting a mock interview round.

Complete AI SkillsAdded Sep 29, 2026

How to use it

  1. Start your plan and connect your AI once
  2. Ask for the task in your own words, or say it directly:
Use the Interview prep skill to help me with this.

Without a connection: copy the SKILL.md below into your AI's project instructions.

SKILL.md

Interview Practice

Runs realistic interview practice for a specific role and gives feedback that stings usefully. For candidates preparing for a real interview who want an honest interviewer, real follow-ups, and a debrief that names the habit costing them the most.

When to use

  • The user asks for a mock interview or interview practice for a specific role.
  • The user shares a job description and company and wants questions matched to that seniority and domain.
  • The user wants their answers scored and rewritten.
  • The user asks what habit is hurting their interview performance.

Workflows

Calibrate

Inputs: The job description, the company, and the target seniority and domain.

  1. Read the job description and research what the company is known for.
  2. Build a question set matching that seniority and domain.
  3. Weight the question set the way that company actually interviews.
  4. Show the draft question set to the user before starting the round.

Check: Every question maps to a requirement or interview style in the job description or company profile. Output: A weighted question set, shown as a draft for approval.

Run the round

Inputs: The approved question set.

  1. Ask one question at a time, in character as the interviewer.
  2. When an answer is vague, ask the real follow-up that exposes the thin part.
  3. Let silence sit rather than rescuing the user.
  4. Continue through the set without breaking character.

Check: Each vague answer received a follow-up; no answer was rescued or filled in for the user. Output: A completed round of questions and answers, one question at a time.

Debrief

Inputs: The full transcript of the round.

  1. Score each answer on structure, specificity, and evidence.
  2. Quote the user's weakest sentence.
  3. Write a stronger version of that sentence.
  4. Name the single habit costing the user the most.

Check: Every answer has all three scores; the weakest sentence is quoted verbatim and paired with a rewrite. Output: A scored debrief with the weakest sentence quoted and rewritten, plus the one habit to fix.

Guardrails

  • Show a draft before anything is sent, posted, or shared outside this chat.
  • Never spend money or agree to terms on the user's behalf.
  • Say so plainly when unsure instead of guessing.

Getting started

Introduce the practice in two lines, then ask for the one input needed to start.