Is the ML Interview Cheat Sheet skill free?

Yes. The skill itself is free from wanshuiyin/Auto-claude-code-research-in-sleep. SkillProof publishes the install command and an independent test verdict at no cost.

What is the ML Interview Cheat Sheet SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.

How do I install ML Interview Cheat Sheet?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use ML Interview Cheat Sheet with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

ML Interview Cheat Sheet

Generates 600-1000 line Chinese ML/LLM interview cheat sheets with derivations, code, and tiered Q&A.

by wanshuiyin · wanshuiyin/Auto-claude-code-research-in-sleep

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.8/10
Tested: Jul 13, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 8422693

⚠ The author changed this skill after we tested it. The verdict below describes the version we ran on Jul 13, 2026; it's queued for a re-test.

A scoped KV-Cache mini-run showed the gap concretely: the skill version derived O(N²d)→O(Nd) properly, added an MHA/MQA/GQA/PagedAttention comparison table and tiered L1/L2/L3 collapsible Q&A, versus the baseline's flat unanswered question list — output is Chinese by design, with English technical terms inline. Real setup cost: it needs the whole ARIS repo cloned (not just this skill folder) for its style-reference file and render script, plus a working codex MCP connection for the mandatory cross-model review gate the SKILL.md leans on as its core quality claim.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 4/5

What ML Interview Cheat Sheet does

Produces a long-form Chinese-language interview-prep tutorial on one ML/LLM topic: formulas with derivations, 50-80 line from-scratch PyTorch, comparison tables, and 25 tiered interview questions (L1/L2/L3) with collapsible answers. Triggers on phrases like '写面试 cheat sheet', '出一份 X 速查', or a request for a 600-1000 line Chinese tutorial on a narrow ML topic; explicitly declines topics outside ML/LLM or too broad to scope.

How to install ML Interview Cheat Sheet

git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
cd Auto-claude-code-research-in-sleep
mkdir -p ~/.claude/skills
cp -r skills/interview-cheatsheet ~/.claude/skills/interview-cheatsheet

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger ML Interview Cheat Sheet

/interview-cheatsheet Generates 600-1000 line Chinese ML/LLM interview cheat sheets with derivations, code, and tiered Q&A.

It also activates on plain-language prompts like these:

Write me a 600-1000 line Chinese interview cheat sheet on attention mechanisms
I need a Chinese ML interview prep tutorial on KV cache with derivations and code
帮我写一份关于强化学习 RLHF 和 PPO 的中文面试速查表，包含公式推导和代码实现

Frequently asked questions

Is the ML Interview Cheat Sheet skill free?: Yes. The skill itself is free from wanshuiyin/Auto-claude-code-research-in-sleep. SkillProof publishes the install command and an independent test verdict at no cost.
Does ML Interview Cheat Sheet work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 13, 2026. Verdict: Works with setup. A scoped KV-Cache mini-run showed the gap concretely: the skill version derived O(N²d)→O(Nd) properly, added an MHA/MQA/GQA/PagedAttention comparison table and tiered L1/L2/L3 collapsible Q&A, versus the baseline's flat unanswered question list — output is Chinese by design, with English technical terms inline. Real setup cost: it needs the whole ARIS repo cloned (not just this skill folder) for its style-reference file and render script, plus a working codex MCP connection for the mandatory cross-model review gate the SKILL.md leans on as its core quality claim.
What is the ML Interview Cheat Sheet SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
How do I install ML Interview Cheat Sheet?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use ML Interview Cheat Sheet with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.