ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleepnpx agentmods add skills/wanshuiyin/auto-claude-code-research-in-sleep/interview-cheatsheetWrote 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.
[](https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/interview-cheatsheet)<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/interview-cheatsheet"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/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.
<a href="https://agentmods.dev/skills/wanshuiyin/auto-claude-code-research-in-sleep/interview-cheatsheet"><img src="https://agentmods.dev/badge/skills/wanshuiyin/auto-claude-code-research-in-sleep/interview-cheatsheet.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00121 | $0.03618 |
| Opus 5 | $0.00060 | $0.01809 |
| Sonnet 5 | $0.00024 | $0.00724 |
| Haiku 4.5 | $0.00012 | $0.00362 |
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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- interview-cheatsheet — 88% identical, 22 lines differ
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(defaultbalanced) —balanced≈ 600 lines,max≈ 1000 lines with deeper proofs and more L3 questions.--byline(default"<Your Name>, <Affiliation>") — passed to/render-html --author.--commit(defaultfalse) — iffalse(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: owner's institution/lab/center names, degree-program affiliations, private server aliases, job-search context, /Users/... paths, 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" |
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.
- 4d ago Changed 37291536f9a4
- 11d ago First seen · 246 lines · 121 tokens per session scan A 052461221309
interview-cheatsheet is a skill published in the GitHub repository wanshuiyin/Auto-claude-code-research-in-sleep (15,970 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 3,618 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
creative-thinking-for-research
Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging combinatorial creativity, analogical reasoning, constraint manipulation, and other empirically grounded creative strategies.
paper-comic
Generate educational comics from academic papers, using visual storytelling to explain core ideas and innovations. Supports 4 art styles: classic (clean lines), tech (futuristic), warm (friendly), chalk (blackboard). Uses genimg-gemini-web to generate images.
talk-builder
Turn a paper (or several, a thesis, a body of work) into an academic talk — outline, per-slide content, speaker notes, opening hook, single take-home message, backup slides for Q&A, rehearsal plan. Adapts to talk length (3-min lightning through 90-min defense), audience (specialists / general field /…
prime
Use when onboarding to the Valor AI codebase, understanding the system architecture, or when the user asks 'how does this work'. Comprehensive codebase orientation guide.
nanogpt
Educational GPT implementation in 300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).
peer-review
Rigorous academic peer review in the voice of a seasoned professor. Two verdict modes (paper, homework), five alternative workflows (committee panel, fact-check audit, plagiarism-check, draft thinking-partner, presentation feedback), plus iterate mode for post-review dialogue. Auto-detects Hebrew or English and the…