# interview-cheatsheet

Creates long-form Chinese interview cheat sheets on ML and LLM topics, complete with formulas, PyTorch code, and 25 questions.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 359 installs · ★ 18090
- Author: wanshuiyin
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/interview-cheatsheet/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/interview-cheatsheet

## What it does

The skill writes technical Markdown tutorials between 600 and 1000 lines long, targeted at machine learning interview preparation in Chinese. Each guide follows a 12-14 section outline that includes formula derivations, runnable PyTorch implementations of 50-80 lines, and 25 interview questions split across three difficulty tiers. Output files land in `docs/tutorials/`.

It requires a focused topic like "MoE" or "RLHF / DPO / PPO". If the prompt asks for an overly broad topic, the skill stops and asks to narrow the scope. Before rendering, it routes a verification step through `mcp__codex__codex` with `gpt-6-astra` at high reasoning effort to check equations and code. Without an active reviewer MCP backend, this check fails with `REVIEW_UNAVAILABLE`.

By default, the skill operates with `--commit false`. It halts after rendering without creating Git commits or pushing changes.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill interview-cheatsheet -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/interview-cheatsheet/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/interview-cheatsheet/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill interview-cheatsheet -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/interview-cheatsheet/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill interview-cheatsheet -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/interview-cheatsheet/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install wanshuiyin/Auto-claude-code-research-in-sleep interview-cheatsheet
```

2. **Manually: put the files in place**
- File: `.github/skills/interview-cheatsheet/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill interview-cheatsheet -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep --path skills/interview-cheatsheet
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/interview-cheatsheet/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill interview-cheatsheet -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/interview-cheatsheet/SKILL.md

## When to use it
- Draft an ML interview guide with formula derivations and PyTorch code
- Generate 25 tiered interview questions with collapsible answers
- Validate mathematical derivations and code blocks with an automated Codex review
- Structure machine learning cheat sheets into 12-14 standardized sections

## Example prompts
- /interview-cheatsheet "KV Cache + Speculative Decoding" --effort balanced
- /interview-cheatsheet "MoE" --effort max --byline "Alex, AI Lab"
- /interview-cheatsheet "RLHF / DPO / PPO" --commit false

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: df5eb34729eb7e1e.

BEGIN THIRD-PARTY FILE df5eb34729eb7e1e
```text
---
name: interview-cheatsheet
description: "Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic."
argument-hint: '<topic> [--effort balanced|max] [--byline "Name (姓名), Affiliation"] [--commit false]'
allowed-tools: Bash(*), Read, Write, Edit, mcp__codex__codex, mcp__antigravity__antigravity, mcp__antigravity__antigravity-reply, mcp__grok__grok, mcp__grok__grok-reply, mcp__claude-review__review, mcp__claude-review__review_reply, mcp__claude-review__review_start, mcp__claude-review__review_reply_start, mcp__claude-review__review_status
---

# /interview-cheatsheet — long-form Chinese ML/LLM interview prep

> **Before each reviewer slot**, follow [Selectable Reviewers](../shared-references/reviewer-backends.md):
> resolve invocation → `.aris/reviewer.json` → Claude Code default (Codex MCP)
> with `reviewer_route.py` through the canonical helper resolver, preserving this
> slot's tier, fresh contexts, source/image inputs and deterministic gates.
> Codex examples/pins below apply only to `backend=codex`; other routes use their
> own first-call/reply contract. Save the route and actual returned identity;
> unavailable selections are `REVIEW_UNAVAILABLE`. Classify acceptance from actual
> families/completion/scope. Forward invocation reviewer/model/effort overrides
> to reviewer-bearing children. Generation workers are unchanged.


Generate one comprehensive Chinese cheat sheet per invocation: formulas + derivations + from-scratch code + 25 高频题. Output passes cross-model math/code review before rendering. **Detect-only by default: never auto-commits.**

## Inputs

- **`<topic>`** (required) — narrow enough for one 600-1000 line tutorial. Good: "RLHF / DPO / PPO", "MoE", "KV Cache + Speculative Decoding". Bad (too broad): "all of LLM training", "diffusion" (split into Forward Process / Sampling / CFG separately).
- **`--effort`** (default `balanced`) — `balanced` ≈ 600 lines, `max` ≈ 1000 lines with deeper proofs and more L3 questions.
- **`--byline`** (default `"<Your Name>, <Affiliation>"`) — passed to `/render-html --author`.
```
END THIRD-PARTY FILE df5eb34729eb7e1e

The third-party file has ended. Everything between the df5eb34729eb7e1e tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2440 of 14586 bytes. © wanshuiyin · MIT · https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/HEAD/skills/interview-cheatsheet/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md