Home / yuecao365 / offercome · src/lib/mock-interviews/skills/ai-agent/SKILL.md · GitHub

ai-agent skillA

ai-agent is agent-read markdown (skill) from yuecao365/offercome: Agent 开发与运行时怎么面:循环与工具、RAG、上下文与记忆、评测、安全、成本。Agent 与 LLM 应用岗读。.

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

## 面试官在意什么

Agent 开发工程师(也叫 LLM 应用开发、AI 工程师、Agent harness / infra / 运行时)做的是模型外面那一圈:把基座模型变成可上线的产品能力,并让它稳定、可控、可查、可付得起。往上是应用层:搭 RAG 链路、设计 Agent 的工具与状态、写和维护提示词、建评测集、处理安全与合规;往下是运行时层:循环怎么跑、工具怎么分级、上下文怎么控成本、跑到一半停了怎么续、跑完了怎么评、失败怎么回灌到下一版。2026 年这一层已经有公认的做法(Claude Code、Codex、Manus 的公开资料收敛到同一张表):事件优先的循环、工具按读 / 写 / 需确认分级、执行类工具隔离、子 agent 有独立上下文与预算、缓存命中率当一等指标、记忆与技能外化到模型之外、长任务可停可续、评测看轨迹不只看结果。

这个方向简历注水率极高:很多"RAG 项目"只是教程改了数据源,很多"Agent 平台"只是框架调用。面试官最在意四件事:一是什么归代码什么归模型,说得出边界与理由;二是有没有评估闭环(评测集、指标、回归)和真实的失败案例(死循环、误调工具、上下文爆、缓存全失、召回失败)与修法;三是评测有没有轨迹级的指标而不只是成功率;四是能不能说清模型能力的边界、什么时候不该用大模型,以及对自己用的 coding agent 有没有切身体感。

校招侧重:注意力机制与 tokenizer 的基本概念、能用 API 搭一个带检索的问答并解释每一步、能把一次 agent 执行拆成步、写过带预算和终止条件的循环、能设计一个最小评测集。社招侧重:线上事故排查、成本账、评估体系设计、多 agent 与子 agent 的边界、沙箱与权限模型、durable execution、轨迹调试工具、把失败模式沉淀成技能或规则的机制。纯框架名词题(LangGraph 有哪些节点类型、最新模型是什么)越来越少,"给你一个故障现象或业务场景,现场设计并说清改哪一层"越来越多。

怎么问才像这个方向的面试官:
- 考"什么归代码什么归模型"的判断与理由,不考框架 API;候选人提到任何框架,追它替你做了什么、你自己写了什么。
- 每道题都要有"怎么验证"和"坏了怎么查":候选人说了任何机制或优化手段,立刻追评测集、指标、前后对比、失败案例与回归用例。
- 简历上的 RAG / Agent 项目必须深挖到一次真实故障与归因链路;只有 demo 叙事、没有评测环节、没有预算与终止条件的标记为危险信号。
- 结合规模出题:日均几百次调用的项目不问集群调度与多租户,日均百万次的必须追成本账、缓存与降级。
- 不考名词时效:不问"最新模型是什么""某框架新版本改了什么"。
…

Read the whole file at its exact version.

How to install

Latest version
mdr add yuecao365/offercome/ai-agent@git:20260920.a4843f5
Exact content
mdr add yuecao365/offercome/ai-agent@sha256:85e4521ff575d90d

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_cgsrcbmsmxobg74e.svg)](https://markdownregistry.com/a/art_cgsrcbmsmxobg74e)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260920.a4843f5 latest2026-09-20 a4843f5 13,540 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (13540 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

GitHub

yuecao365/offercome · 23 stars · license MIT · pushed 2026-09-23 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cgsrcbmsmxobg74e
GET https://markdownregistry.com/api/v1/resolve?ref=yuecao365/offercome/ai-agent
GET https://markdownregistry.com/api/v1/blob/85e4521ff575d90de58c96d2c69f6bbc678a3c3301f28778b7d6090dec019a46

Your agent 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.

More from yuecao365/offercome

AGENTS.md agents
yuecao365/offercome · AGENTS.md
git:20260921.abf64ee · audit A · 23 stars
CLAUDE.md claude
yuecao365/offercome · CLAUDE.md
git:20260803.e553cde · audit B · 23 stars
agent-runtime skill
yuecao365/offercome · src/lib/mock-interviews/skills/agent-runtime/SKILL.md · Agent 运行时深挖:循环与事件、工具协议与沙箱、子 agent、预算终止、恢复、输出契约。
git:20260920.a4843f5 · audit A · 23 stars
ai-algorithm skill
yuecao365/offercome · src/lib/mock-interviews/skills/ai-algorithm/SKILL.md · 大模型算法怎么面:Transformer、预训练、后训练与对齐、RL、微调、Embedding、评测。LLM 算法岗读。
git:20260920.a4843f5 · audit A · 23 stars
ai-app-testing skill
yuecao365/offercome · src/lib/mock-interviews/skills/ai-app-testing/SKILL.md · AI 应用测试深挖:非确定性输出、幻觉与 RAG 评估、Agent 链路审计、安全对抗、回归门禁、AI 生成用例。
git:20260920.a4843f5 · audit A · 23 stars
ai-infra skill
yuecao365/offercome · src/lib/mock-interviews/skills/ai-infra/SKILL.md · 大模型推理与训练基础设施怎么面:KV cache、调度、并行、量化算子、服务指标、训练集群。AI Infra 岗读。
git:20260920.a4843f5 · audit A · 23 stars
algorithm skill
yuecao365/offercome · src/lib/mock-interviews/skills/algorithm/SKILL.md · 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。
git:20260920.a4843f5 · audit A · 23 stars
android skill
yuecao365/offercome · src/lib/mock-interviews/skills/android/SKILL.md · Android 怎么面:生命周期、Compose、协程与 Flow、性能、启动。JD 点名 Android 时读。
git:20260920.a4843f5 · audit A · 23 stars
backend skill
yuecao365/offercome · src/lib/mock-interviews/skills/backend/SKILL.md · 后端怎么面(栈无关):缓存、消息队列、接口、可靠性、可观测、容量、发布。服务端岗读。
git:20260920.a4843f5 · audit A · 23 stars
cpp skill
yuecao365/offercome · src/lib/mock-interviews/skills/cpp/SKILL.md · C++ 后端怎么面:内存模型、RAII、STL 性能、多线程与原子、IO 模型、现代 C++。JD 点名 C++ 时读。
git:20260920.a4843f5 · audit A · 23 stars
cs-fundamentals skill
yuecao365/offercome · src/lib/mock-interviews/skills/cs-fundamentals/SKILL.md · 计算机基础怎么面:操作系统、网络、数据结构与算法、数据库原理。技术岗校招兜底。
git:20260920.a4843f5 · audit A · 23 stars
data-engineering skill
yuecao365/offercome · src/lib/mock-interviews/skills/data-engineering/SKILL.md · 数据工程怎么面:数仓建模、离线与实时链路、调度、数据质量、湖仓。数据开发与数仓岗读。
git:20260920.a4843f5 · audit A · 23 stars

Every file in yuecao365/offercome

Browse by kind, by grade A, or by owner.