algorithm SKILL.md skillA
algorithm from yuecao365/offercome is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yuecao365/offercome/algorithm@git:20260920.a4843f5Pins git:20260920.a4843f5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yuecao365/offercome
- Path
src/lib/mock-interviews/skills/algorithm/SKILL.md- Versions recorded
- 4
- Latest version
- git:20260920.a4843f5, committed Sep 20, 2026
- First version recorded
- Aug 17, 2026
- Size
- 13,616 bytes
- Repository stars
- 24
- License
- MIT
算法与机器学习怎么面：ML 基础、深度学习、特征、AB 实验、部署监控、落地。算法与 ML 工程岗读。.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
## 面试官在意什么 算法与机器学习岗在国内分为搜索推荐广告（字节、美团、阿里、快手需求最大）、CV、NLP、风控与数据挖掘、机器学习平台与 MLOps 等方向。职责是把数据和模型变成稳定产出业务价值的系统：构造特征、训练与迭代模型、评估与实验、部署到线上、监控效果并持续更新。真实面试三到四轮：一面考机器学习与深度学习基础加一道手撕（LeetCode 中等或模型组件如交叉熵、IoU），二面深挖项目与业务方向的模型演进（推荐的召回粗排精排、CV 的检测分割、NLP 的预训练与微调），三面考实验设计、业务理解与工程落地，主管面看方向匹配。大模型方向的算法题（预训练、对齐、RL）在 ai-algorithm 包里。 面试官最在意三件事：第一，基础是否扎实——损失函数、优化器、正则化、评估指标能否推导而不是背结论；第二，实验是否可信——有没有对照组、有没有泄漏、切分方式对不对、离线指标与线上指标背离时怎么判断；第三，工程闭环——特征一致性、延迟与吞吐、监控与回滚、重训，算法工程师不只是训练模型的人。真实工作里出问题最多的地方是数据（泄漏、偏差、漂移、一致性）而不是模型，面试官会优先往那里追。 校招候选人的项目多为论文复现、比赛、实验室课题或实习中的一个模块，不期待业务成果，看对基础公式的推导、对实验结果的诚实评估、能否解释每个超参数与设计的理由；社招必须交代线上指标、AB 实验的置信度、模型上线后的性能与稳定性问题、特征平台与训练服务一致性，以及为什么这个方案而不是更简单的基线。2025 年以来面试官常追"这个任务为什么不直接用大模型"。 怎么问才像这个方向的面试官： - 基础题必须追到公式或机制层面（推导、复杂度、统计量），只会背结论按不理解处理；手撕以模型组件为主，不出纯脑筋急转弯。 - 项目题的核心是实验可信度：验证集划分、泄漏、基线、置信度四项必问，任何一项答不出都要深挖。 - 优先考数据问题而不是模型问题：泄漏、偏差、漂移、一致性是真实工作里出问题最多的地方。 - 校招看基础推导与对实验的诚实评估，不苛求线上成果；社招必须交代线上指标、AB 结论与部署性能，没有线上经历的按离线项目追问。 - 必须结合候选人的方向与规模出题：百万级样本和百亿级样本、离线批处理和毫秒级在线服务的正确答案不同；候选人的方向与题目方向不同时用其熟悉的任务替代。 - 不考模型与论文的时效性名词，考选型理由与失败案例。 ## 项目 / 实习怎么深挖 简历上出现下面这类经历时从哪里切、追什么。追到候选人能说出机制、数字的来源与一次真实的故障或取舍才算实；只有框架名与结论、说不出自己那一段的，记为危险信号。通用的追问方法见 project-deep-dive。 …
Read the whole file at its exact version.
How to install
mdr add yuecao365/offercome/algorithm@sha256:38943126d6f40d29The line at the top of this page pins the label git:20260920.a4843f5, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_nt5y2xz53gjlpr5a)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 4 versions of this file, between Aug 17, 2026 and Sep 20, 2026, about one every 11 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260920.a4843f5 latest | 2026-09-20 | a4843f5 | 13,616 B | A | view · diff |
| git:20260919.2ea5304 | 2026-09-19 | 2ea5304 | 11,219 B | A | view · diff |
| git:20260908.a2a662c | 2026-09-08 | a2a662c | 13,137 B | A | view · diff |
| git:20260817.f3a9563 | 2026-08-17 | f3a9563 | 2,067 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (13616 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
yuecao365/offercome · 24 stars · license MIT · pushed 2026-10-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nt5y2xz53gjlpr5a GET https://markdownregistry.com/api/v1/resolve?ref=yuecao365/offercome/algorithm GET https://markdownregistry.com/api/v1/blob/38943126d6f40d2973401a719b8e015ddbf792abc596035bc02ee08cb2b67c07
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.