Przejdź do treści
Biblioteka skilli
AI i agenci · Pisanie

interview-cheatsheet

/interview-cheatsheet

Pisze długą ściągę do rozmów o modelach ML i LLM: wzory z wyprowadzeniami, kod PyTorch od podstaw, tabele i pytania rekrutacyjne.

Repozytorium
Athena ↗
Licencja
MIT
Ostatnia zmiana repozytorium
13.11.2026

Ocena i bezpieczeństwo

100/ 100Klasa: dobry
Format25 / 25
Frontmatter z nazwą i opisem, poprawna nazwa, opis do 1024 znaków, nazwa zgodna z folderem.
Odkrywalność25 / 25
Opis mówi, kiedy użyć skilla, ma sensowną długość i jest w 3. osobie.
Treść35 / 35
Co najmniej 150 słów i do 500 linii, nagłówki, listy kroków, przykłady albo kod.
Higiena15 / 15
Bez zaślepek typu TODO, bez ścieżek Windows, z licencją.
Ryzykobrak sygnałów w skanie
Pliki w paczce
1
Skrypty
0
Komentarze HTML
0
Adresy URL w SKILL.md
2
Przestarzałość

Brak sygnałów. Repozytorium zmienione 13.11.2026, bez odwołań do wycofanych modeli i API.

Licencja

MIT, otwarta: można używać i zmieniać, z zachowaniem informacji o autorze.

Co robi i kiedy

Pisze długą ściągę do rozmów o modelach ML i LLM: wzory z wyprowadzeniami, kod PyTorch od podstaw, tabele i pytania rekrutacyjne.

Wyzwalacze z opisu

Write an interview. cheat sheetWrite a copy. X AcademyGet me ready. Y Interview questionsHere

Argumenty

/interview-cheatsheet <topic> [--effort balanced|max] [--byline "Name (Name), Affiliation"] [--commit false]
Oryginalny opis (EN)

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 High-frequency interview questions (L1 Yes, I will. / L2 Step / L3 Top level lab). Use when the user says 'Write an interview. cheat sheet', 'Write a copy. X Academy', 'Get me ready. Y Interview questions', 'Here's a copy. X Quick check.', or wants a 600-1000 line Chinese tutorial on a specific ML topic.

Jak działa

  1. Inputs
  2. Style guide — STRICT (read docs/tutorials/attentiontutorial.md as canonical reference)
  3. Workflow
  4. Update the index
  5. Key invariants (the ARIS rules baked in)
  6. When NOT to use
  7. Reference invocations
  8. Reference style files
  9. Provenance
  10. Mirror description (additional to this open warehouse)
Sekcje z nagłówków SKILL.md, w oryginale · 255 linii, 2 022 słów
Podgląd SKILL.md
---
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 High-frequency interview questions (L1 Yes, I will. / L2 Step / L3 Top level lab). Use when the user says 'Write an interview. cheat sheet', 'Write a copy. X Academy', 'Get me ready. Y Interview questions', 'Here's a copy. X Quick check.', or wants a 600-1000 line Chinese tutorial on a specific ML topic."
argument-hint: '<topic> [--effort balanced|max] [--byline "Name (Name), 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 High frequency issues. 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`.
- **`--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 Intuition. — why this matters; analogy; one-paragraph mental model
## §2 Core formula — main formula + derivation (variance / scaling / boundary)
## §3 Realize Details — 50-80 line from-scratch PyTorch
## §4-7 Variant / Engineering practices / Common bug — variants, comparison tables, footguns
## §8 Complexity / Resources — time + memory complexity
## §9 Comparison with relevant methodologies — placement in the ecosystem
## §10 25 High-frequency interview questions — L1 (10 Yes, I will.) + L2 (10 Step) + L3 (5 Top level lab), all with <details><summary> collapsible answers
## §A Appendix (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 Selection** — Press NFE/Quality is sorted as follows.`<br/>`- Euler …`<br/>`- Heun …` |
| Callout prefixes only: `💡` `⚠️` `✅` `❌` (others won't get class) | renderer maps these to `callout-info/warn/good/bad` | `> ⚠️ **FP16 overflow** — Even if it's not. √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 Saturation", "vector field" |

### Eyebrow / subtitle / title naming

| Field | Pattern |
|---|---|
| `--eyebrow` | `Interview Prep · <Topic>` |
| `--subtitle` | one Chinese sentence describing scope (e.g. `Formula Deposition + From-Scratch Code + 25 High frequency (HF)L1 Yes, I will. · L2 Step · L3 Top level lab)`) |
| `--title` | `<Topic> Interview Cheat Sheet` or `<Topic> Quick Reference` |
| `--lang` | `zh-CN` |

### Slug
`<topic>` → kebab/snake-case `<slug>` for filenames. e.g. "RLHF / DPO / PPO" → `rlhf_dpo_ppo`.

## Workflow

### Step 1 — Plan structure (no files written)

Internally sketch:
- 12-14 section titles
- List of major formulas (with derivation outline for each)
- List of code blocks (skeleton + what it demonstrates)
- 25 interview questions sorted by L1 / L2 / L3 difficulty (each with one-line expected answer)
- Comparison table topics (e.g., "RLHF vs DPO vs IPO vs SimPO")

If the topic is too broad to fit in one cheat sheet, **stop and ask the user to scope** before drafting.

### Step 2 — Draft MD

Write directly to `docs/tutorials/<slug>_tutorial.md`. Follow the style guide. Length target: 600 lines (balanced) or 1000 lines (max), ±20%.

### Step 3 — Cross-model math/code review (codex gpt-6-astra xhigh, FRESH thread)

Invoke `mcp__codex__codex` with `model: gpt-6-astra`, `config: {model_reasoning_effort: xhigh}`, `sandbox: read-only`, fresh thread (never `codex-reply`).

Reviewer prompt:

```
You are reviewing a long-form Chinese interview-prep tutorial on <TOPIC> for math/code/factual correctness and style discipline.

## Files to read (READ-ONLY)
- Draft MD: <MD_PATH>
- Style reference: docs/tutorials/attention_tutorial.md
  (Read this only for STYLE — do NOT score the draft against the reference's content topic.)

## Return JSON with these 10 checks

1. formula_correctness — Independently re-derive each $$ display formula. Flag any error with file:line.
2. code_correctness — For each python block: would it run? Does it implement the stated math? Imports / shapes / device handling consistent?
3. interview_answer_correctness — Each L1/L2/L3 question's <details> answer. Specifically flag wrong year / wrong paper / wrong author / off-by-one indexing / inverted comparison.
4. historical_citations — Paper authors + year + venue. Flag wrong attributions (e.g., "DPO: Rafailov 2023 NeurIPS" must be checkable).
5. table_pipe_escape — Any markdown table cell containing `|x|` math (not `\lvert x \rvert`)? Cite line.
6. callout_list_collision — Any line matching the pattern `^> (?:💡|⚠️|✅|❌) \*\*[^*]+\*\* — (?:- |\d+\. )`? That swallows the list.
7. heading_consistency — All `## §N` and `### N.M` follow style guide (space after §N, no glued chars).
8. section_completeness — Sections §0..§10 (and §A if effort=max) present and non-trivial.
9. length_target — Within ±20% of target (600 for balanced, 1000 for max).
10. personal_info_leak — None of: the owner's institution / lab / center names, degree-program affiliations, private server aliases, job-search or recruitment context, absolute `/Users/...` paths. (Keep the concrete string banlist in local untracked notes — the public SKILL defines only the CATEGORIES; listing the real values here would itself be the leak.)

Return JSON:
{
  "verdict": "PASS | WARN | FAIL",
  "checks": {<check_name>: "pass|warn|fail with one-line note + file:line if applicable"},
  "blocking_issues": ["..."],
  "warnings": ["..."]
}

Verdict: PASS = all pass, WARN = at most cosmetic issues (length slight off / cosmetic style), FAIL = any math/code/factual error OR personal-info leak OR table-pipe / callout-list bug.
```

### Step 4 — Fix and loop (no hard cap — judge by trajectory)

For each FAIL issue, edit the MD. Then re-invoke codex with a **fresh thread** (never reuse threadId). Stop when verdict = PASS or WARN with no FAIL items.

**No hard round cap.** Use these heuristics instead:

- ✅ **Keep going** if each round's FAIL items are *shrinking, concrete, enumerable* (e.g., citation year fixes, off-by-one, single-line code bugs). The reviewer is doing useful work — let it converge.
- ⛔ **Stop and report** if the same issue keeps coming back (loop detected), or if the FAIL items shift to architectural / scope concerns that need user input, or if the round count exceeds ~6 without convergence.

Most tutorials converge in 3-5 rounds. Going to 5-6 rounds is fine if substantive bugs are still being caught — the Video Generation tutorial (May 2026) went to 5 rounds and the final 2 rounds caught real citation errors and an over-attribution to Sora's patch size that would have shipped otherwise.

### Step 5 — Render via /render-html

Call directly (do not invoke `/render-html` as a sub-skill; call its python script — gives clear control):

```bash
python3 skills/render-html/scripts/render_html.py docs/tutorials/<slug>_tutorial.md \
  --template academic \
  --out docs/tutorials/<slug>_tutorial.html \
  --title "<Topic> Interview Cheat Sheet" \
  --subtitle "<one-line scope summary>" \
  --eyebrow "Interview Prep · <Topic>" \
  --author "<byline>" \
  --lang zh-CN
```

`render_html.py` runs its own 13-check codex review automatically. If that FAILs, fix the MD (often a table-pipe or callout-list issue the math/code reviewer missed) and re-render. Note that `render_html.py` itself writes `<slug>_tutorial.review.json` for the render-stage audit.

### Step 6 — Combine audit trail

After both reviews pass, merge math/code review history + render review history into one `docs/tutorials/<slug>_tutorial.review.json`:

```json
{
  "skill": "interview-cheatsheet",
  "source": "docs/tutorials/<slug>_tutorial.md",
  "source_sha256_prefix": "<16-char prefix>",
  "output": "docs/tutorials/<slug>_tutorial.html",
  "topic": "<TOPIC>",
  "effort": "balanced | max",
  "byline": "<author string>",
  "math_code_review": {
    "verdict": "PASS",
    "rounds": [
      {"run": 1, "verdict": "...", "thread_id": "...", "issue": "...", "fix": "..."},
      ...
    ]
  },
  "render_review": {
    "verdict": "PASS",
    "rounds": [...]
  },
  "summary": "<one-line: N-round math/code review + M-round render review settled at PASS>",
  "rendered_at": "<YYYY-MM-DD>"
}
```

### Step 7 — Stop. Report to user.

Do **NOT** `git add` / `git commit` / `git push`. Report:

```
✅ /interview-cheatsheet "<TOPIC>" complete.

  Files:
    docs/tutorials/<slug>_tutorial.md          (<lines> lines, <bytes> bytes)
    docs/tutorials/<slug>_tutorial.html        (<bytes> bytes, <TOC> TOC entries)
    docs/tutorials/<slug>_tutorial.review.json

  Math/code review:  PASS after <N> rounds (<thread IDs>)
  Render review:     PASS after <M> rounds
  Length:            <actual> lines (target <effort>)

  Issues caught + fixed during review:
    - <one line per non-trivial fix>

  Suggested commit message:
    docs(tutorials): add <Topic> cheat sheet (rendered via /render-html)

  ⚠️ Did NOT auto-commit — user reviews and pushes manually.
  Also update docs/tutorials/README.md to add the new row.
```

## Update the index

After the tutorial passes, optionally append a row to `docs/tutorials/README.md`:

```
| **<Topic> Interview Cheat Sheet** | [`<slug>_tutorial.md`](<slug>_tutorial.md) | [`<slug>_tutorial.html`](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/tutorials/<slug>_tutorial.html) | <one-line topic list> |
```

Suggest the row to the user but let them edit it in themselves if they want to curate.

## Key invariants (the ARIS rules baked in)

| Invariant | How it's enforced |
|---|---|
| Executor != reviewer family | Claude drafts; gpt-6-astra reviews (math/code stage); gpt-6-astra reviews again (render stage) |
| Fresh thread per reviewer call | Step 3 + render's own gate both use `mcp__codex__codex` not `codex-reply` |
| Codex reasoning = xhigh | Hardcoded in Step 3 reviewer config |
| Personal info redaction | Both math/code reviewer and render reviewer check; banlist in style guide |
| Lessons-learned encoded | Table-pipe + callout-list collision rules in style guide AND review checks 5+6 |
| No silent failure | If review FAILs and the FAIL set is no longer shrinking (loop) or hits ~6 rounds without convergence, stop and report — don't push |

## When NOT to use

- Topic too broad — split into smaller scopes first
- Topic outside ML/LLM core — this style guide assumes math + code + Chinese; for general topics use a different format or write directly
- Already have a draft you want to edit — use Edit directly, this skill is for greenfield generation
- Don't want HTML output — call `/render-html` separately or skip Step 5

## Reference invocations

```
/interview-cheatsheet "RLHF / DPO / PPO"
/interview-cheatsheet "MoE (Mixture-of-Experts)" — effort: max
/interview-cheatsheet "KV Cache + Speculative Decoding"
/interview-cheatsheet "Long-context: RoPE / YaRN / NTK / MLA"
/interview-cheatsheet "Distributed Training (DDP / FSDP / ZeRO / TP / PP)"
/interview-cheatsheet "Quantization (GPTQ / AWQ / INT4 / FP8 / SmoothQuant)"
```

## Reference style files

- Style canonical: `docs/tutorials/attention_tutorial.md` + `.html`
- Style secondary: `docs/tutorials/flow_matching_tutorial.md` + `.html`
- Review audit format: `docs/tutorials/attention_tutorial.review.json`

## Provenance

Extracted from the two pilot tutorials (Attention + Flow Matching, May 2026). Both passed cross-model review; the attention tutorial required 3 review rounds — catching a table-pipe collision and a callout-list collision that were not obvious from the rendered output. Those lessons are now baked into the style guide and reviewer checks 5+6 so future tutorials don't repeat them.

## Mirror description (additional to this open warehouse)
- This document is considered upstream. ARIS mirrors in original;support files (scripts/、references/、../shared-references/)Not distributed with mirrors, full originals can be found at the upstream warehouse https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep 。
- If supporting documents are cited for implementation skills, then the relative path should be parsed from the upstream warehouse.

Wersje

RepozytoriumWynikLicencja
Ta strona · jiangfeng-strathclyde/Athena100MIT
wanshuiyin/Auto-claude-code-research-in-sleep100MIT
wanshuiyin/Auto-claude-code-research-in-sleep100MIT

Migawka bazy z 13.11.2026 · wersja paczki 8d1314c2fc4b (skrót SHA-256 całej paczki)

Pobrania w ostatnich 30 dniach: 0 · ranking

Zgłoś problem z tym skillem: szkodliwa treść, błędny opis albo prośba autora o usunięcie.

Podobne skille

  • 100cheatsheet
    Zamienia sylabus lub notatki w jednostronicową ściągę A4 z wzorami w dwóch kolumnach, gotową do wydruku.
  • 100oracle-cheatsheet
    Tworzy ściągę do skopiowania z bieżącej sesji: użyte polecenia, napotkane pułapki i odkryte skróty, w sekcjach z ikonami, blokach kodu i tabelach szybkiej referencji.
  • 100latex-cheatsheet
    Przygotowuje gęste ściągi do nauki w LaTeX i PDF: czterokolumnowe, kolorowe pozycje i ramki kodu, po angielsku lub chińsku.
  • 100latex-cheatsheet
    Przygotowuje gęste ściągi do nauki w LaTeX i PDF: czterokolumnowe, kolorowe pozycje i ramki kodu, po angielsku lub chińsku.
  • 90Interview Prep
    Przygotowuje do rozmów w programach badawczych, ćwicząc pytania i symulując przebieg wywiadu z promotorem.
  • 90interview-prep
    Tworzy ustrukturyzowane plany rozmów rekrutacyjnych z pytaniami kompetencyjnymi i kartami oceny dla osób przygotowujących się do rozmów z kandydatami.

Uwagi i zgłoszenia

Wiadomość trafi do Bartosza Sokolińskiego. Adres e-mail jest potrzebny tylko do odpowiedzi. Szczegóły w polityce prywatności.