interview-cheatsheet

interview-cheatsheet is a skill for Claude Code from wanshuiyin/ARIS-in-AI-Offer. It costs 171 tokens per session (3,750 once invoked), scanned A, a copy of interview-cheatsheet, MIT.

A long Chinese study guide about a focused machine-learning or large-language-model topic, combining explanations, formulas, PyTorch code, comparisons, and interview questions. PyTorch is a Python library for building and training neural networks.

In plain words
What is it for?
It is for preparing ML or LLM interviews on topics such as reinforcement learning, preference optimization, mixture-of-experts models, or KV caching.
Why use it?
It gathers theory, worked derivations, implementation examples, and interview practice into one topic-specific reference.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions Codex.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/yangruofeng/Desktop/aris_paper_discussion/aris_repo/docs/tutorials/attention_tutorial.md.

Good fit It is for preparing ML or LLM interviews on topics such as reinforcement learning, preference optimization, mixture-of-experts models, or KV caching.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for interview-cheatsheet

README.md
[![agentmods](https://agentmods.dev/badge/skills/wanshuiyin/aris-in-ai-offer/interview-cheatsheet/github.svg)](https://agentmods.dev/skills/wanshuiyin/aris-in-ai-offer/interview-cheatsheet)
Your own site
<a href="https://agentmods.dev/skills/wanshuiyin/aris-in-ai-offer/interview-cheatsheet"><img src="https://agentmods.dev/badge/skills/wanshuiyin/aris-in-ai-offer/interview-cheatsheet/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for interview-cheatsheet

Your own site · 80×15
<a href="https://agentmods.dev/skills/wanshuiyin/aris-in-ai-offer/interview-cheatsheet"><img src="https://agentmods.dev/badge/skills/wanshuiyin/aris-in-ai-offer/interview-cheatsheet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 171 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,750 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00171 $0.03750
Opus 5 $0.00086 $0.01875
Sonnet 5 $0.00034 $0.00750
Haiku 4.5 $0.00017 $0.00375

Measured 12d ago against content hash 3710ced66e68, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

interview-cheatsheet scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to interview-cheatsheet — 22 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/interview-cheatsheet/SKILL.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

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 "Ruofeng Yang (杨若峰), Shanghai Jiao Tong University") — passed to /render-html --author.
  • --commit (default false) — if false (default), stop after rendering; user reviews and commits. Never push without explicit user approval.

Style guide — STRICT (read docs/tutorials/attention_tutorial.md as canonical reference)

Section skeleton (12-14 sections)

## §0 TL;DR — callout intro line + numbered list of 5-7 takeaways
## §1 直觉 — why this matters; analogy; one-paragraph mental model
## §2 核心公式 — main formula + derivation (variance / scaling / boundary)
## §3 实现细节 — 50-80 line from-scratch PyTorch
## §4-7 变体 / 工程实践 / 常见 bug — variants, comparison tables, footguns
## §8 复杂度 / 资源 — time + memory complexity
## §9 与相关方法对比 — placement in the ecosystem
## §10 25 高频面试题 — L1 (10 必会) + L2 (10 进阶) + L3 (5 顶级 lab), all with <details><summary> collapsible answers
## §A 附录 (optional) — sanity-check output, reference list

Conventions — bake the established lessons in

Rule Why Example
Heading format ## §N Title with space after §N Older versions had §0TL;DR glued ## §0 TL;DR Cheat Sheet
Math in table cells: use \lvert ... \rvert not |...| | inside markdown table = cell separator → row break $\text{score}_{ij} - m \cdot \lvert i-j \rvert$
Callouts with body list: split into callout intro line + separate list Otherwise the list's first item is swallowed by the callout, then items 2..N restart numbering at 1 > 💡 **Sampler 选择** — 按 NFE/质量排序如下。- Euler …- Heun …
Callout prefixes only: 💡 ⚠️ (others won't get class) renderer maps these to callout-info/warn/good/bad > ⚠️ **FP16 overflow** — 即使除了 √d_k …
Math: $...$ inline, $$...$$ display, $$\boxed{...}$$ for key boxes MathJax CDN; literal in source
Code: ```python fences, real PyTorch that would run reviewer will check executability
Personal-info banlist: SJTU JHC, JHC PhD, Server5, job market, /Users/..., specific lab/company names reviewer flags as FAIL byline goes via --author at render time, not in body
Language: Chinese primary, English technical terms in-place matches established cheat-sheet style "softmax 饱和", "vector field"

Read the full file on GitHub · 246 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 246 lines · 171 tokens per session scan A 3710ced66e68

Subscribe to this mod's changes

interview-cheatsheet is a skill published in the GitHub repository wanshuiyin/ARIS-in-AI-Offer (476 stars, last pushed yesterday), licensed MIT. It adds 171 tokens to every session and 3,750 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to interview-cheatsheet, differing in 22 lines, and is treated as a copy.

Related

Other skills, from other repositories

learning-notes-automation

A workflow for turning videos, podcasts, and articles into structured learning notes. It extracts key ideas and creates flashcards that can be imported into Anki, a spaced-repetition study app.

chubbyguan/chubbyskills · 58 tokens

andrej-karpathy-v2

ANDREJ KARPATHY — SKILL COMPLETA v2.0 workflow skill. Use this skill when the user needs Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo and the operator should preserve the upstream workflow, copied support…

diegosouzapw/awesome-omni-skills · 94 tokens

ai-engineering-curriculum

Use when structured AI engineering curriculum — 382 skills + 99 prompts across 20 phases covering ML, deep learning, LLMs, agents, and production systems. Use when learning AI, building AI skills,.

oyi77/1ai-skills · 50 tokens

minimind-learning

A Chinese-language learning assistant for MiniMind, a small language-model project, that records study notes and recognizes common machine-learning terms.

joyehuang/minimind-notes · 76 tokens

andrej-karpathy

Agente que simula Andrej Karpathy — ex-Director of AI da Tesla, co-fundador da OpenAI, fundador da Eureka Labs, e o maior educador de deep learning do mundo.

henryalouf/ruflow · 47 tokens

geoffrey-hinton

Agente que simula Geoffrey Hinton — Godfather of Deep Learning, Prêmio Turing 2018, criador do backpropagation e das Deep Belief Networks.

tmolavi/mcp-agent-skills-hub · 42 tokens