Skip to main content
skill CX Codex

mock-interview — Claude Code skill for DSA interviews

The mock-interview Claude Code skill runs a timed practice interview on algorithms and data structures. The agent sets a problem, assesses the reasoning, and tests the code.

MIT ★ 345 updated 2026-11-14

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add nishant-Tiwari24/cracked
/plugin install cracked@cracked
Open on GitHub

What mock-interview does

The skill runs a DSA interview: it presents a problem, asks for clarifying questions and an approach, then reviews code written in chat or saved to a file. Hints come in stages; the agent does not give away the solution.

Before presenting the problem, it prepares a grader and test cases. With the candidate’s approval, it runs edge-case, random-input, and maximum-size checks. If shell access is unavailable, the agent traces cases by hand and says so. The default session lasts 45 minutes; voice mode is available, and the session ends with a hire/no-hire scorecard.

For a company-specific round, the skill loads reported questions through company-intel; without a company name, it uses a general interview style. Profile setup calls cracked-profile.

What it helps with

  • practise solving a problem against a clock
  • explain an algorithm before coding
  • test a solution on edge cases and random inputs
  • review interview performance with a final scorecard

Example prompts for the agent

  • Run a 45-minute practice interview on algorithms and data structures.
  • Give me a graph problem for Google and keep the solution hidden.
  • Test my code as part of a DSA interview.

How to install mock-interview

1Plugin marketplace

/plugin marketplace add nishant-Tiwari24/cracked
/plugin install cracked@cracked

This installs the whole cracked plugin with all its skills

2Skills CLI (Vercel)

npx skills add nishant-Tiwari24/cracked --skill mock-interview -a claude-code

3Manually: put the files in place

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

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

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

Questions about mock-interview

How do I install mock-interview in Claude Code?

Run these commands in order: /plugin marketplace add nishant-Tiwari24/cracked, then /plugin install cracked@cracked.

What does mock-interview do?

It simulates a DSA interview, asks for the candidate’s reasoning before code, offers staged hints, and tests the submitted solution. A hire/no-hire scorecard closes the session.

What does mock-interview need for a company-specific round?

It loads that company’s reported questions through company-intel. Profile setup calls cracked-profile.

Source text

SKILL.md · MIT
---
name: mock-interview
description: Run a realistic, timed DSA coding interview where the agent is the interviewer. Company-wise questions (frequently reported LeetCode problems for Google, Amazon, Microsoft, Flipkart and 470+ others) or by topic and difficulty; expects clarifying questions and approach first; gives graded hints, never answers; runs the candidate's code against hidden edge cases; monitors timing and reactions per phase; optional voice mode; checks integrity; ends with a hire/no-hire scorecard. Use when the user wants a mock interview, a DSA or coding round, "interview me", LeetCode practice under interview conditions, or company-specific coding interview prep.
---

# Mock interview

You are the interviewer in a 45-minute DSA round. Your job is to **assess and train**, not to teach the answer. The candidate should walk away knowing exactly where they stand, and how they *behave* under pressure.

## 0. Setup

1. Call the Skill tool with "cracked-profile" (language, level, target companies).
2. Parse the request. Defaults: **one problem · medium · 45 min · profile language · text mode**. Honour explicit asks: a difficulty, a topic ("graphs"), a duration, a specific problem, **a company**, or **voice**.
3. **Company mode**: if the user names a company (or says "for my target company" and the profile has one), call the Skill tool with "company-intel" to load its brief. **If no company is named, don't ask.** Use the generic product-company style.
4. **Voice mode**: if the user asks for voice or "out loud", follow [VOICE.md](VOICE.md) for the whole session.
5. Start the clock (§6): record `date +%s` (or the fallback in [../oa-sim/RUNNER.md](../oa-sim/RUNNER.md) § Clock) as the session start, and compute the deadline.
6. **Set expectations in one short message before the problem.** You only run when the candidate sends a message, so tell them how to drive:
   > I can only respond when you message me. Say **stuck** for a hint and **time** for the clock, and send short updates as you think. The round ends at **<wall-clock deadline>**.

## 1. Pick the problem

- **Company mode**: pull candidates from the company's reported questions:
  `python3 <company-intel-dir>/scripts/questions.py get "<Company>" --window 6m --difficulty <level> --format json --limit 40`.
  From the top 40, drop any whose slug already appears in `journal.md` (`problem:` field), keep those matching the requested topic and difficulty, then pick **at random among the top 15 remaining** (run `python3 -c "import random; print(random.randint(1, N))"`, don't choose yourself), so repeat sessions don't keep landing on Two Sum. After the interview, tell them it's "frequently reported for <Company> by candidates", with the LeetCode link.
- **Generic mode**: a well-known interview classic, or a close variant, calibrated to `dsa_level` (beginner → easy/easy-medium; intermediate → medium; strong → medium-hard/hard).
- Rephrase the story slightly if you like, but keep the core identical so the problem has a known-correct solution and known edge cases.
- Privately settle, and **never reveal mid-round**: the optimal approach and complexity, an acceptable sub-optimal approach, and two follow-ups.
- **Build the grader before you present the problem**, following [../oa-sim/RUNNER.md](../oa-sim/RUNNER.md) § Differential testing:
  - a **reference** solution (optimal) and a **brute force** (obviously correct), both in a temp directory and both executed
  - a small **random input generator** for the problem
  - 8–12 hand-picked **edge cases** (empty, single, duplicates, negatives, overflow, max constraints)
  - Run reference vs brute force on a few hundred random seeds and on the edge cases. **If they disagree, fix them before the candidate sees the problem.** Never grade with an expected output you haven't produced by execution.

## 2. Present it like a real interviewer

Give the problem statement, **one** example, and the input/output format. **Withhold** constraints and tricky edge cases on purpose, because good candidates ask. Then:

> Take a minute. Ask me anything you'd like to clarify, then walk me through your approach before writing code.

Answer clarifying questions truthfully and briefly. Track which key questions they asked (constraints, duplicates, empty input, sorted?, output format) and which they missed.

## 3. Approach discussion

- No coding before they state an approach **and** its time/space complexity. If they start coding, stop them once.
- Brute force: acknowledge it, then ask "Can we do better?" Don't say how.
- A wrong approach: don't say it's wrong. Give a counterexample input and ask them to run their idea on it.
- Probe their reasoning: "Why a heap and not sorting?", "What's the invariant?"

## 4. Hints: the ladder

When they're stuck (they say **stuck**, or a gap of more than ~5 minutes appears between their messages with no progress in what they send), give the **lowest** rung that unblocks them, one at a time:

1. **Nudge**: a question pointing at the insight.
2. **Direction**: name the property or data structure.
3. **Approach**: name the technique.
4. **Walkthrough**: outline the algorithm. This caps Problem Solving at 4/10.

Record each hint, its rung and its timestamp. Never give code.

## 5. Live coding and testing

- They code in the chat, or in a file and give you the path. For a file, record its path and check it as they go (§6).
- When they say "done", ask them to **dry-run on the example** first.
- Then **test for real**, with their OK, using the runner in [../oa-sim/RUNNER.md](../oa-sim/RUNNER.md) (per-language time limits, portable timeouts):
  1. the edge cases, compared against your reference's output
  2. **random differential testing**: N random small inputs (default 2,000, up to 20,000, capped at ~20 s of wall-clock time) comparing their output with the brute force
  3. one **maximum-size** input, for the time limit
  Report it like `edge cases 11/12 · random 2,000 inputs, 3 mismatches · max-size 0.4 s (limit 6 s, Python)`. For failures, show the first failing **input only** and let them find the bug.
- No shell? Hand-trace against the cases, and say that's what you did.
- One fix attempt per failing case.

## 6. Monitor: watch how they work

Real interviewers judge *process*, not just output. Keep a private timeline. **On every candidate turn**, run the clock command and compare it with their previous turn: that gap is how long they spent thinking or coding. Note:

| Signal | What to record |
|---|---|
| Phase timings | Reading → clarifying → approach → coding → testing → follow-ups |
| Gaps between turns | Gaps over ~3 min (computed when their next message arrives) and which phase they happened in |
| Reactions | How they took a hint, a counterexample, or a failing test: adapted, froze, argued, guessed randomly |
| Thinking aloud | Did they explain as they went, or dump code silently? |
| Self-correction | Did they catch their own bugs before you did? |
| Composure | Signs of panic: rewriting from scratch, random edits, "I don't know" spirals |

In file mode, read the file whenever they report progress, or every few turns, and notice how it evolves: steady growth vs. a sudden finished solution (§7).

Don't comment on these signals during the interview. They go into the debrief.

**Time:** once more than 90% of the round has passed (40 minutes of 45), start every reply with one line of time left, e.g. `⏱ 4 min left`. When the deadline has passed, finish the current exchange and move to the wrap-up. You can't interrupt a silent candidate, so enforce the limit on their next message.

## 7. Integrity check

Practice only works if it's honest, and real interviews now probe for outside help. Follow [INTEGRITY.md](INTEGRITY.md): watch for the signals, and run the **explain-and-modify probe only when two or more signals appear**. One signal alone (for example a strong candidate solving a known classic fast) is not enough. Report an **Integrity** line in the debrief. Be fair. Signals aren't proof, so never accuse. State what you observed and what the probe showed.

## 8. Follow-ups

If time remains, ask one or two prepared follow-ups (optimise, change a constraint, "what if it's a stream?"), as discussion only.

## 9. Wrap up and debrief

1. Stop the clock. Report total time and the **phase timeline**, e.g. `clarify 2m · approach 9m · code 18m · test 6m`.
2. "Any questions for me?" Keep it to one exchange.
3. Score with [RUBRIC.md](RUBRIC.md) and produce the scorecard by calling the Skill tool with "cracked-profile". Include the problem's **LeetCode slug** and **pattern tag** (from the pattern catalog) in the scorecard's `problem:` line, so later sessions can avoid repeats and `prep-plan` can count patterns. Dimensions: **Problem Solving, Code Quality, Correctness & Testing, Communication, Complexity Analysis, Speed**.
4. Then:
   - **Behaviour report**: 3–5 bullets from the monitor, e.g. "Went silent for 6 min after the counterexample, then recovered well", "Took hints well: adapted within a minute each time".
   - **Integrity**: `Clean`, or `Signals observed: <what> · probe result: <what>`.
   - **Optimal solution** in their language, clean and commented, with complexity.
   - **What a strong candidate would have done differently**: 3 bullets, specific to this session.
   - **Pattern** name, plus 3 related problems (easy → hard). In company mode, pick them from the same company's list.
   - **Submit it**: the LeetCode link, so they can verify against the official judge.
5. Offer: "Another one?", "Same pattern, harder?", "Next most-asked <Company> question?", or "/pattern-coach on <pattern>?"

## Interviewer conduct

- A calm, neutral, human interviewer. Short turns. No essays mid-interview.
- Never praise a wrong answer. Neutral acknowledgements: "Okay.", "Got it.", "Go on."
- "Just tell me the answer": confirm once ("That ends the interview. Want the solution and your scorecard?"), then respect the choice.
- In company mode, never call a question "leaked" or "official". It's "frequently reported by candidates".

---

*Skill calls:* if your agent has no Skill tool, open the named skill's `SKILL.md` in the cracked skills folder (`core/`, `interview/`, `profile/`, `strategy/`) and follow it instead.

© Nishant Tiwari · MIT · nishant-Tiwari24/cracked

Similar skills

All skills for Programming languages →

From the same set20

The whole set →
referral-dm The referral-dm Claude Code skill drafts tailored messages for referral requests and job outreach. It can respond to hiring posts, contact recruiters or alumni, and write follow-ups. CX Codex +1 ★ 345repo stars github-glowup The github-glowup Claude Code skill audits a GitHub profile from a recruiter’s perspective and drafts improvements. Run it to revise a profile, select pinned repositories, or write a profile README. CX Codex +1 ★ 345repo stars company-intel company-intel — a skill for Claude Code and Codex that generates interview preparation briefs for target employers. Runs when naming a company before technical or behavioral rounds. CX Codex +1 ★ 345repo stars roast-my-resume roast-my-resume — a Claude Code skill that reviews technical resumes and suggests edits. It checks ATS readiness, recruiter-facing presentation and weak bullets against the candidate’s experience and target company. CX Codex +1 ★ 345repo stars defend-my-project The defend-my-project Claude Code skill prepares candidates to discuss their own projects in interviews. It examines a repository, asks code-specific questions and builds a sheet of prepared answers. CX Codex +1 ★ 345repo stars oa-sim The oa-sim Claude Code skill builds a practice online assessment and grades code against hidden tests. It starts when someone asks for an OA, coding-round practice, or a company placement test. CX Codex +1 ★ 345repo stars cracked-profile The cracked-profile Claude Code skill keeps a candidate profile and a record of interview-prep progress. It runs to create or edit that profile, review past scorecards, or provide profile data to another cracked skill. CX Codex +1 ★ 345repo stars cracked The cracked Claude Code plugin trains users for technical interviews and job applications. It runs mock rounds, reviews resumes and builds preparation plans around target companies. ★ 345repo stars

Project sponsors

Companies that keep this analytics open