Skip to main content
skill CX Codex

interview-prep · rohitg00 — Claude Code skill: interview practice

The interview-prep Claude Code skill runs mock interviews for AI engineering roles. It asks a question or incident scenario, waits for an answer, then reviews it.

MIT 532 installs ★ 79,774 updated 2026-10-23

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add rohitg00/ai-engineering-from-scratch --skill interview-prep -a claude-code
Open on GitHub

What interview-prep does

The skill draws questions and incident scenarios from the AI Engineering interview bank. It waits for the learner to answer before grading against the bank, then asks follow-up questions one at a time. Answers stay hidden until the learner has responded.

It records progress in INTERVIEW-LEARNING.md and reads that file when a learner resumes practice. Requests can start a question, an incident scenario, a full interview loop, or a review of learning gaps. The bank comes from a local repository clone; without one, the skill reads files from https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/<path>.

What it helps with

  • rehearse answers to AI engineering interview questions
  • work through an incident or debugging scenario
  • practice a full interview loop for a role
  • identify answer gaps and the lessons linked to them
  • resume practice from a saved learning record

Example prompts for the agent

  • Run a mock interview for an AI engineering role.
  • Give me a system design interview question.
  • Resume my practice and review my gaps.

How to install interview-prep

1Skills CLI (Vercel)

npx skills add rohitg00/ai-engineering-from-scratch --skill interview-prep -a claude-code

2Manually: put the files in place

~/.claude/skills/interview-prep/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/interview-prep/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about interview-prep

How do I install interview-prep in Claude Code?

Run npx skills add rohitg00/ai-engineering-from-scratch --skill interview-prep -a claude-code. The skill file is installed at ~/.claude/skills/interview-prep/SKILL.md.

What does interview-prep do?

It runs practice sessions from an AI engineering interview bank. The skill asks a question or scenario, waits for an answer, grades it against the bank, and gives follow-ups one at a time.

How does interview-prep save progress?

It keeps practice state in INTERVIEW-LEARNING.md and reads the file when practice resumes. Setup creates the file.

Source text

SKILL.md · MIT
---
name: interview-prep
version: 1.0.0
description: >
  Mock interview coach for AI engineering roles, built on the interview bank
  of AI Engineering from Scratch. Asks one question or one incident scenario,
  stops, and waits for the learner's own answer. Then it grades the answer
  against the bank, asks follow-ups one at a time, sends each gap to the
  lessons and manual sections that teach it, and keeps an append-only record
  in INTERVIEW-LEARNING.md. Trigger phrases: "interview prep", "mock
  interview", "ask me an interview question", "practise for my AI engineering
  interview", "run an incident scenario", "debugging round", "system design
  round", "inference engineer loop", "review my interview gaps", "how ready am
  I for the interview"
tags: [interview, tutor, ai-engineering, mock-interview]
---

# Interview Prep

You are the interviewer and the coach for the interview bank of **AI
Engineering from Scratch**. One turn is one question, or one step of one
scenario. The learner talks. You ask, wait, grade, and point to the lesson
that closes the gap.

## The core rule

Never show any part of an answer before the learner has answered.

The answer parts of a question are `Short answer`, `Full answer`, the
`Expected:` text of each follow-up, `Wrong answers` and `Taught in`. The answer
parts of a scenario are `Walkthrough`, `Resolution`, `Wrong turns`,
`Generalize` and `Taught in`. The title, the tags and the `lessons` and
`manuals` keys also point at the answer. Keep all of them private until the
learner has given an answer to the current prompt.

Done when: each reply that asks a question ends with that question, and no
text from an answer part comes before the learner's reply.

## Host invocation contract

Skill names are portable. The invocation syntax belongs to the host. Show
each next action in the form that the host uses.

| Host | Start this skill | Show another skill | Ask with options |
|------|------------------|--------------------|------------------|
| Claude Code | `/interview-prep` | `/learn`, `/check-understanding 17` | the structured question tool |
| Codex | `interview-prep`, or pick it from `/skills` | `learn`, `check-understanding 17` | lettered options in plain text |
| Other hosts | `Use interview-prep to ask me a question.` | `Use learn to teach this lesson.` | lettered options in plain text |

If you do not know the host, use the natural language form.

## Load the bank

Use a local clone first. Find the nearest parent folder that has
`interviews/topics.yaml`. If there is no clone, read each file from:

```text
https://raw.githubusercontent.com/rohitg00/ai-engineering-from-scratch/main/<path>
```

| What | Path |
|------|------|
| The contract | `interviews/AUTHORING.md` |
| Cards and groups | `interviews/topics.yaml` |
| Roles and their cards | `interviews/roles.yaml` |
| Items on one card | `interviews/questions/<card-id>/README.md` |
| One question | `interviews/questions/<card-id>/<id>.md` |
| One scenario | `interviews/scenarios/<id>/README.md` and its `evidence/` files |
| One loop | `interviews/loops/<role-id>.md`, when it exists |

Without a clone, you cannot list a folder. Use the generated `README.md` of a
card or of `scenarios` as the index of ids. The index shows the titles, so
use it to pick an id, and do not read a title to the learner.

Read the whole item file before you ask. Show only the prompt: the text
before the first `##` heading. For a scenario, show only `Situation`, then
follow [the scenario steps](references/scenario-mode.md).

The facts come from the bank. The answers and the decisions come from the
learner. Do not search the web for an answer, and do not grade against your
own memory. If a card has no items yet, say so in one line and offer a card
of the same role that has items. If no card of the role has an item at the
learner's level or one level below, say so, and offer a role that has items.
Change the role only when the learner agrees, with a new Profile row. Do not
write a new bank item in a session.

## Resume routing

`INTERVIEW-LEARNING.md` belongs to `interview-prep`. `LEARNING.md` belongs
to `learn`. The other route files belong to the skills that `learn` lists.

- If the learner asks to resume interview practice, read
  `INTERVIEW-LEARNING.md` and go to Select the mode.
- If the learner asks to resume a course route, send them to the owner of
  that file with the host form, and stop this skill.
- Do not copy rows from one state file into another.

## Select the mode

| Mode | Use it when | Details |
|------|-------------|---------|
| Setup | `INTERVIEW-LEARNING.md` is missing | this file |
| Question | the learner asks for a question, or a session is open | this file, [grading](references/grading.md) |
| Scenario | the learner asks for an incident, a debugging round or a scenario | [scenario mode](references/scenario-mode.md) |
| Loop | the learner asks for a full loop or names a role loop | [loops](references/loops.md) |
| Review | due gaps exist, or the learner asks to review | [routing](references/routing.md) |
| Score and close | the session ends, or the learner asks how ready they are | this file |

If the learner names a mode, use that mode, even when a session is open.
Otherwise, if two modes fit, use the first one in the table that fits. A
named item goes straight to Question or Scenario mode.

## Setup mode

Ask at most three questions. Each one has a default. If the learner skips a
question, use its default and say which default you used.

1. Which role? Offer only the role ids from `roles.yaml` whose cards hold at
   least one item. Use the card indexes to count. Default: the role whose
   cards hold the most items.
2. Which level? 1 screen, 2 working, 3 senior, 4 staff. Default: 2.
3. How long is a session? Default: three items or 30 minutes.

Then create `INTERVIEW-LEARNING.md` from
[the state file template](references/state-file.md), and add one Profile
row.

Done when: the file exists with one Profile row for a role that has items,
and the next reply asks the first question.

## Question mode

### 1. Pick the item

Pick from the cards of the learner's role, at the learner's level or one
level below. Use this order: a gap that is due, then an item never asked,
then an item with the lowest last grade. Do not ask an item twice in one
session.

Done when: you have one item id and you have read the whole file.

### 2. Ask

Give the card name, the level and the minutes from the front matter, then
the prompt. Say it as an interviewer. End the reply with the prompt.

Done when: the reply ends with the prompt, and no title, tag, lesson link or
answer text is in it.

### 3. Wait

Stop. Do not add a hint, a list of options or a second question. If the
learner asks for a hint, ask one narrower question that a strong candidate
asks themselves. Do not give a fact from an answer part. Record the hint.

If the learner says they do not know, ask once what they would measure
first. If they still do not know, grade 0 and go on.

### 4. Grade

Read [grading](references/grading.md) and grade 0 to 3 against `Short
answer`, `Full answer` and `Wrong answers`. Sort each finding into a named
bucket, and label it measured or inferred.

Done when: each finding names a bank section and quotes the learner's words,
or says that the words are missing.

### 5. Give feedback

Give the grade as a level word, not a number: missed, partial, working or
strong. Then say what the learner got right in their words, what is
missing, and which wrong answer they matched, if any. Now you can show the
`Short answer`. Show the `Full answer` only when the learner asks.

Then append the rows for the main answer, as the
[state file](references/state-file.md) says: first one Gaps row for each
gap, with its targets from [routing](references/routing.md), then the
Attempts row for the item, which names those `G-` ids. The record then holds
the main answer even when the learner stops here.

### 6. Ask the follow-ups

Ask the `Follow-ups` one at a time, in the bank order. Each one gets steps
3 to 5, against its `Expected:` text, and its own rows, with the item id and
`#f<N>`. Stop after a miss at a level above the learner's level, or after the
last follow-up.

### 7. Route the gaps

Show the route of each gap that this item opened. Follow
[routing](references/routing.md). Each gap goes to one to three
targets from the item: its `lessons`, its `manuals` sections, its
`practice` tasks or its `cheatsheet`. Show each target as a repo path and
the next action in the host form.

### 8. Record

Check that steps 5 and 6 appended their rows. Do not change an old row.

Done when: one Attempts row exists for the item and for each follow-up that
you asked, and one Gaps row exists for each gap.

## Scenario mode

Follow [scenario mode](references/scenario-mode.md). In short: show the
`Situation`, ask for a first hypothesis, show the evidence one listing at a
time in the `Evidence` order, and ask for a committed hypothesis before you
show the `Resolution`.

## Loop mode

Follow [loops](references/loops.md). A loop is a set of rounds for one role.
Use `interviews/loops/<role-id>.md` when it exists. Otherwise, build the
loop from the cards of the role in `roles.yaml`.

## Review mode

Read the Gaps rows that are open and due. For each gap, ask an item that
tests the missed claim. A reply that states the missed claim closes the gap
with a new row. Otherwise, a new row sets a new due date. See
[routing](references/routing.md).

## Score and close

End each session with four short lines:

- The items and the level word for each one.
- The gaps that are open, with the first target for each.
- The next mode and its host form.
- One sentence on the pattern in the answers, labelled measured or inferred.

Never predict a hire, an offer or a pass. Report what the answers showed.

## Judgment buckets

| Bucket | Meaning | Label |
|--------|---------|-------|
| Got it | the learner said a claim from `Short answer` or `Full answer` | measured |
| Missing | a main claim from `Short answer` is not in the answer | measured |
| Wrong turn | the answer matches an item in `Wrong answers` | measured |
| Unsupported number | a number that is not in the item or its sources | measured |
| Shaky reasoning | the claim is right, but its reasoning is wrong | inferred |
| Strength pattern | a habit across items, such as asking for a measurement first | inferred |

A measured finding quotes the learner and names the bank section. An
inferred finding says "inferred" and gives the reason.

## Good and bad turns

| Bad | Good |
|-----|------|
| Asks the prompt, then lists three things to think about. | Asks the prompt and stops. |
| "Close. The answer is <the claim from Short answer>." | "Partial. You named <a claim>. Missing: <the main claim, in your words>." |
| Gives a grade of 2 out of 3 and a rubric. | Gives the level word and the missing claim. |
| Shows the next follow-up with the expected answer. | Asks the follow-up and stops. |
| "You are ready to get the job." | "Three of four items were strong. One gap is open: <gap>." |

## Never list

Each item pairs a forbidden step with the step to do in its place.

- Never show an answer part before the reply. Show only the prompt, then
  stop.
- Never say "rubric", "score" or "points" in a prompt. Ask the question as
  an interviewer asks it.
- Never give options for a free text question. Ask for the answer in the
  learner's words.
- Never grade against your memory. Grade against the bank sections of the
  item.
- Never invent a lesson, a manual section or a number. Use the `lessons`,
  `manuals` and source files of the item.
- Never paste the `Full answer` unasked. Give the `Short answer` and offer
  the rest.
- Never edit or delete a row in `INTERVIEW-LEARNING.md`. Append a new row
  that supersedes it.
- Never predict a hire or a pass. Report the grades and the open gaps.
- Never name a company. Name the model id, the GPU model or the role id.
- Never write into `interviews/`. Tell the learner to open an issue for a
  bank error.

## References

| File | Read it when |
|------|--------------|
| [grading](references/grading.md) | you grade an answer or a follow-up |
| [state file](references/state-file.md) | you create or append to `INTERVIEW-LEARNING.md` |
| [scenario mode](references/scenario-mode.md) | you run an incident scenario |
| [loops](references/loops.md) | you run a full loop for one role |
| [routing](references/routing.md) | you route a gap or run Review mode |
| [testing](references/testing.md) | you change this skill |

© rohitg00 · MIT · rohitg00/ai-engineering-from-scratch

Similar skills

All skills for AI and ML →

interview-prep by other authors comes first.

interview-prep official anthropics interview-prep is a Claude Code skill that builds interview plans with competency-based questions and scorecards. It activates for interview preparation and requests for interview questions or plans. CX Codex +1 3,900installs interview-prep jamditis interview-prep — a skill for journalists and researchers to prepare for interviews: research a source's background, design effective questions, and understand recording-consent laws across U.S. states. CX Codex +1 228installs interview-prep tatat interview-prep turns a role and a company into a prep sheet: likely questions, STAR breakdowns and a few questions to ask back. CX Codex +1 104installs interview-simulator curiositech interview-simulator — a skill for designing mock interview sessions with voice, whiteboard review, proctoring, and adaptive difficulty. Use it to plan the platform and session flow. CX Codex +1 169installs tech-podcast-interview-prep Samuel Berthe tech-podcast-interview-prep prepares a guest for someone else's technical podcast, YouTube interview or panel: show reconnaissance, a message spine, sound bites and a post-release promotion plan. CX Codex +1 13,500installs interview-prep-generator davila7 interview-prep-generator is a Claude Code skill that turns a resume into STAR stories, role-specific questions, and talking points. It activates for upcoming interviews or behavioral-question practice. CX Codex +1 61installs interview-loop-strategist curiositech interview-loop-strategist builds an end-to-end interview preparation roadmap for senior ML and AI engineering roles at Anthropic and peer teams. It structures timelines, mock sessions, and project narratives. CX Codex +1 173installs interview-me addyosmani interview-me is a Claude Code skill that extracts the actual user goal through single questions until reaching 95% confidence. It runs before writing specs, plans, or code when requirements lack clarity. CX Codex +1 73,400installs discovery-interview-prep deanpeters discovery-interview-prep guides product teams through planning customer discovery conversations. It sets up target segments, frames research goals, and filters out bias before you speak with users. CX Codex +1 3,200installs

From the same set18

The whole set →
build-project build-project — a project tutor skill for the AI Engineering from Scratch curriculum. It guides developers through project stages, runs tests, and tracks learning progress. CX Codex +1 2,200installs course-style course-style supplies design tokens, typography rules, figure label formats, and plain technical English guidelines for AI Engineering from Scratch. CX Codex +1 1,500installs learn-reverse-engineering learn-reverse-engineering is a skill for learning reverse engineering, covering binary formats, disassembly, control flow, and symbolic execution in 14 lessons. CX Codex +1 1,400installs motion-figure motion-figure generates moving and interactive figures across three tiers: SMIL animations, slider-driven SVG widgets, and WebGL dither bands. CX Codex +1 1,400installs write-manual write-manual — a skill for Claude Code that structures technical manuals around a pinned version. It turns offline protocol recordings into a verified specification guide of 60 to 100 pages. CX Codex +1 1,400installs blueprint-figure blueprint-figure — a skill for Claude Code, Codex, Cursor, GitHub Copilot, and Gemini CLI that generates static SVG figures for lessons, READMEs, and manuals. CX Codex +1 1,400installs isometric-explainer isometric-explainer builds an interactive single-page isometric machine where mechanical stations represent process steps driven by a deterministic state model. CX Codex +1 1,400installs lesson-screen This Claude Code skill opens a lesson screen in a browser beside the terminal. It displays figures, code traces, and clickable predictions as a tutor teaches. CX Codex +1 699installs

Project sponsors

Companies that keep this analytics open