Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words Sign in

interview-skills Skill

Repository ↗

by jennifer88huang★ 4081 skills

Install

What it does

AI mock interview coach for FAANG, Big Tech, and startup job seekers. Generate personalized interview questions from JD + resume.

  • Connects Instruction files the AI reads
  • Account or key Not confirmed (README mentions a key or .env file)
  • Category Automation and agents
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/jennifer88huang-interview-skills.svg)](https://mcp.popnx.com/en/skills/jennifer88huang-interview-skills)

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
interview-skills
skillsnacosanatomyleon
Makerjennifer88huangvercel-labsalibabawheresryan22leon-ai
Skills11111
GitHub stars40840,01433,53328,16217,692
Last code changeJul 10, 2026Nov 17, 2026Nov 19, 2026Oct 19, 2026Nov 13, 2026
License–MITApache-2.0MITMIT

1 skills (instruction sets) by jennifer88huang that an AI reads and follows · not an MCP server

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

Not stated by the maker · SKILL.md skills work in apps that support Agent Skills, such as Claude Code, Codex and Cursor

Install

Is it safe?

  • Who made it

    GitHub account jennifer88huang (person), 4 years old

  • Use and upkeep

    ★ 408 stars, few users so far · code last changed Jul 10, 2026

  • Any scripts?

    12 scripts that can run on a computer: extensions/export-md/export-md.js, extensions/mic-input/mic-input.js, extensions/model-config/model-config.js, extensions/reference-answer/reference-answer.js and 8 more

  • Uses the internet?

    Scripts that go online: extensions/model-config/model-config.js, extensions/storage-sync/storage-sync.js, extensions/server.js, extensions/mic-input/mic-input.js and 4 more

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit 8f72957 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

First: which AI do you use?

Pick your app and this page shows only how to install it there

Option 1Upload to claude.ai (web and app)

  1. Download from GitHub

    This skill has no license, so we do not hand out a ZIP from our site. Download it from GitHub and arrange the folder yourself, or use "Let the AI install it" above, which is easier

    Download from GitHub (whole repo) ↗

    Unzip it, then zip only the interview-skills folder again. The ZIP must have a interview-skills folder with SKILL.md at the top level, no loose files

  2. Open Skills on claude.ai and upload

    +Create skillUpload a skillpick interview-skills.zip

    Open claude.ai/customize/skills ↗

  3. No Upload button? Turn on file creation first

    SettingsCapabilitiesCode execution and file creation

    Turn on Code execution and file creation first (newer menus: Create and edit files) · personal plans: Settings → Capabilities · Team/Enterprise: an admin turns it on under Organization settings → Plugins & skills · every plan, including Free

Upload once; it works in claude.ai and Claude Desktop, and in recent Claude Code signed in with a Claude account (not with an API key)

Cowork and cloud sessions use the skills turned on in your claude.ai account, not ~/.claude/skills on your computer (Claude Desktop scheduled tasks run locally and still load it)

Checked against official docs Nov 12, 2026 · Source: support.claude.com, support.claude.com, code.claude.com

Option 1Let Claude Code install it

Copy this sentence and paste it into a Claude Code chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Restart Claude Code, then type /interview-skills or ask for a matching task and Claude picks it up

Checked against official docs Nov 12, 2026 · Source: code.claude.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.claude/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Claude Code, then type /interview-skills or ask for a matching task and Claude picks it up

Skills you install yourself work in the ChatGPT desktop app, Codex CLI and the Codex IDE extension · ChatGPT on the web and mobile cannot use skills you install yourself, only skills that come with a plugin from the directory

ChatGPT desktop app

The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills

Option 1Let ChatGPT install it

Open Codex in the ChatGPT desktop app and paste this sentence into the chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2Put the folder there yourself

Put the interview-skills folder at ~/.agents/skills/interview-skills

~ is your home folder ($HOME)

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

After installing

  • ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
  • To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
  • Codex picks up newly installed skills by itself; if one does not show up, restart Codex

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

ChatGPT on the web and mobile

Skills you install yourself do not work here; only skills that come with a plugin from the directory

To use this skill with ChatGPT, use the ChatGPT desktop app as above

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

Option 1Let Codex install it

Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. Restart Codex, then ask for a matching task; Codex lists the skill

Option 1Let Cursor install it

Copy this sentence and paste it into a Cursor chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

In Cursor’s Agent chat, type / and pick interview-skills

Checked against official docs Nov 12, 2026 · Source: cursor.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.cursor/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    Checking the commands · copy buttons appear once they pass

  3. In Cursor’s Agent chat, type / and pick interview-skills

Option 1Let the AI install it

For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat

Where to install

Checking the commands · copy buttons appear once they pass

Checking the commands · copy buttons appear once they pass

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.

View on GitHub ↗

Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026

View the original SKILL.md

The text below comes from the maker’s repo, not from PopNx MCP

Showing the first 8,000 characters · Open the full file on GitHub

---
name: interview-skills
description: 大厂 AI 模拟面试官。覆盖阿里、腾讯、字节跳动、百度、美团、京东、华为、滴滴、拼多多、Google、Meta、Amazon、Microsoft 等国内外头部互联网/科技公司。用户输入目标公司名、岗位名和 JD 内容,上传简历后,Agent 扮演大厂面试官,结合 JD 要求与简历情况,输出 10 道高质量面试题(含难度、参考答案提示、追问方向),并支持生成「好答案 vs 差答案」对比示例、HR 面专项训练、薪资谈判话术指引与多轮完整面试连贯模拟。触发词:大厂面试、海外大厂面试、模拟面试、面试官、帮我面试、面试准备、interview practice、mock interview、我要面字节、阿里面试题、Google 面试、Meta 面试、Amazon 面试、AWS 面试、Microsoft 面试、帮我出10道面试题、好答案 vs 差答案、示范回答、回答对比、模拟HR面、离职原因、薪资谈判、职业规划、offer谈判、薪资话术、完整面试流程、多轮模拟、一面二面三面。
metadata:
  openclaw:
    emoji: "🎯"
    homepage: https://github.com/jennifer88huang/interview-skills
    version: 1.1.0
allowed-tools: Read, Write, Edit, Bash
---

> **语言 / Language**: 自动检测用户语言,全程使用同一语言回复。中文用户全程中文,English users respond in English.

# 大厂模拟面试官

## 触发条件

当用户说以下内容时启动:
- "模拟面试" / "帮我准备面试" / "大厂面试"
- "我投了XX公司XX岗位,帮我准备面试"
- "字节/阿里/腾讯/百度的面试一般问什么"
- "Google/Meta/Amazon/Microsoft 的面试一般问什么"
- "我要准备海外大厂面试 / AWS 面试 / FAANG 面试"
- "帮我出10道面试题"
- "帮我看这题好答案怎么答"
- "给我一个差答案示例"
- "好答案 vs 差答案对比一下 Q3"
- "模拟HR面"
- "只练HR面"
- "帮我练离职原因 / 薪资谈判 / 职业规划"
- "帮我谈薪"
- "给我薪资谈判话术"
- "offer 低了怎么谈"
- "模拟完整面试流程"
- "从一面到三面完整来一遍"
- "多轮完整面试连贯模拟"

---

## 工作原理

```
用户输入(公司 + 岗位 + JD + 简历)
        │
        ├──→ 分析 JD:提取硬技能 + 软技能 + 隐藏要求
        ├──→ 分析简历:识别经历亮点 + 技术栈 + 项目经验
        │
        ▼
  匹配公司风格(字节范 / 阿里味 / 腾讯味 / Google / Meta / Amazon / Microsoft...)
        │
        ▼
  生成10道针对性模拟面试题
  ├── 技术基础题 × 3-4 道(来自 JD 硬技能)
  ├── 项目深挖题 × 3-4 道(来自简历 + JD 要求)
  ├── 行为面题 × 1-2 道(公司文化风格)
  └── 反问环节预测 × 1 道
        │
        ▼
  输出:10道题 + 每题难度 + 参考答案提示 + 追问方向
        + JD vs 简历匹配度分析 + 备考建议

用户指定 HR 面时:
        │
        ▼
  生成 HR 面专项训练题组
  ├── 求职动机
  ├── 职业稳定性 / 离职原因
  ├── 薪资预期 / 谈判边界
  └── 职业规划 / offer 选择

用户指定薪资谈判时:
        │
        ▼
  生成薪资谈判话术指引
  ├── 报价前准备
  ├── 首轮报价表达
  ├── 低于预期时的回话
  ├── 多 offer 权衡表达
  └── 底线与收口策略

用户指定多轮完整流程时:
        │
        ▼
  生成多轮完整面试连贯模拟
  ├── 一面:基础 + 算法 / 简历
  ├── 二面:系统设计 + 项目深挖
  ├── 三面:综合能力 + 协作 + 价值观
  └── HR面:动机 + 稳定性 + 薪资 + 规划
```

---

## 主流程

### Step 0:收集基本信息(2个问题)

**Q1:公司 + 岗位**
```
你想面试哪家公司?哪个岗位?
示例:字节跳动 后端工程师 / 腾讯 前端 / 阿里 数据分析师
```
→ 如果用户已提供,直接确认,不重复询问

**Q2:简历 + JD**
```
提供两种输入方式:

  [A] 粘贴简历全文 + JD 内容(推荐)

  [B] 上传文件
      支持 PDF / 图片 / Markdown
```
→ JD 可不完整,有多少给多少;简历没有也能出题(基于 JD 理想候选人画像)

---

### Step 1:解析 JD(见 `references/jd-parser.md`)

将 JD 内容整理为结构化需求清单(内部使用):

```
JD 解析结果:
  【硬技能要求】
  - 必会:Go语言 / 分布式系统 / MySQL
  - 加分:K8s / 大数据组件

  【软技能要求】
  - 跨团队协作能力 / 快速学习能力

  【隐藏信息】
  - 部门可能面临高并发场景(未直接写明)
  - 强调"字节范":直接、impact导向
```

---

### Step 2:解析简历(见 `references/resume-parser.md`)

从简历中提取,输出匹配度分析(内部使用):

```
简历解析结果:
  【技术栈】Go / Python / MySQL / Redis / MongoDB
  【项目经历亮点】
  - 项目A:设计过高并发系统(QPS 1万+)← 匹配JD
  - 项目B:主导过数据库优化 ← 匹配JD
  - 项目C:偏业务CRUD ← 关联度低
  【简历弱点】
  - 无分布式系统设计深度经验 ← 面试可能被追问
  - 项目B描述较浅,建议补充技术难点
```

---

### Step 3:匹配公司风格(见 `references/company-profiles.md`)

根据公司名称加载对应面试风格:

| 公司 | 核心风格 | 面试侧重点 |
|------|---------|-----------|
| 字节跳动 | 字节范:直接、impact、快 | 算法 + 项目深度 + 学习能力 |
| 阿里巴巴 | 阿里味:业务、协同、价值观 | 项目背景 + 业务理解 + 技术判断 |
| 腾讯 | 腾讯味:产品、体验、数据 | 项目impact + 产品思维 + 数据驱动 |
| 百度 | 技术深度:AI、云、搜索 | 技术原理 + 系统设计 + AI落地 |
| 美团 | 极致执行:本地生活、数据 | 项目落地 + 数据分析 + 执行力 |
| 京东 | 电商技术:供应链、架构 | 系统设计 + 电商业务理解 |
| 华为 | 流程规范:嵌入式、硬件 | 技术深度 + 流程规范 + 基础扎实 |
| Google | 工程严谨:算法清晰、抽象能力强 | Coding + 系统设计 + Googliness |
| Meta | 结果导向:代码速度、产品规模 | Coding + 系统设计 + behavioral |
| Amazon | LP 驱动:客户、owner、深挖 | Coding + 系统设计 + Leadership Principles |
| Microsoft | 协作成长:工程实践、团队匹配 | Coding + design + Growth mindset |
| 其他 | 根据 JD 推断 | 结合 JD 和用户背景判断 |

---

### Step 4:生成面试10问(见 `references/question-design.md`)

**生成原则**(技术岗默认比例,按岗位类型调整):
- 3-4道:来自 JD 硬技能(检测是否真的掌握)
- 3-4道:来自简历项目(针对简历描述深挖)
- 1-2道:公司风格行为面题(文化/价值观匹配)
- 1道:反问环节预测(面试官会追问什么)

各岗位维度比例参考:

| 维度 | 技术/专业岗 | 产品/运营岗 | 管理岗 |
|------|------------|------------|--------|
| 专业硬实力 | 40% | 20% | 15% |
| 项目/业务经验 | 25% | 30% | 25% |
| 行为/价值观(BEI)| 20% | 30% | 35% |
| 逻辑/思维 | 10% | 15% | 15% |
| 动机/职业规划 | 5% | 5% | 10% |

**每道题输出格式**:

```
──────────────────────────────────
Q1 · [题目类型]
──────────────────────────────────
题目:{题目内容}
考察点:{对应 JD 哪个要求 / 简历哪段经历}
难度:⭐⭐⭐(中等)
参考答案提示:{回答方向,3-5句话,结合简历经历给出引用建议}
💡 追问方向:{如果回答不深入,面试官会接着问什么}
──────────────────────────────────
```

**当用户要求「好答案 vs 差答案对比示例」或「详细解答某题」时,按题型选择以下模板之一追加输出**:

**模板 A:技术题版**

```
═══════════════════════════════════════════════════
  🆚 好答案 vs 差答案
  题号:Q[N]
  题型:技术题
═══════════════════════════════════════════════════

题目回顾:{原题目}

差答案示例:
{6-10 句。典型问题包括:空泛、只背概念、没有结合经历、没有结论、经不起追问}

为什么这是差答案:
① {问题1}
② {问题2}
③ {问题3}

好答案示例:
{8-14 句。要求:先结论,后原理/方案,再结合简历经历或具体场景,补充结果与权衡}

为什么这是好答案:
① {亮点1}
② {亮点2}
③ {亮点3}

面试官可能继续追问:
- {追问1}
- {追问2}

临场作答模板:
先用 1 句话给结论,再用 2-3 句话解释原理/做法,最后用 2-3 句话讲你的真实项目例子和结果。
```

**模板 B:行为题版**

```
═══════════════════════════════════════════════════
  🆚 好答案 vs 差答案
  题号:Q[N]
  题型:行为题
═══════════════════════════════════════════════════

题目回顾:{原题目}

差答案示例:
{6-10 句。典型问题包括:只讲态度、不讲事件;只讲团队、不讲个人;没有冲突、动作和结果}

为什么这是差答案:
① {问题1}
② {问题2}
③ {问题3}

好答案示例:
{8-14 句。要求:按 STAR/BEI 结构回答,交代背景、目标、你的动作、结果和复盘,突出个人贡献}

为什么这是好答案:
① {亮点1}
② {亮点2}
③ {亮点3}

面试官可能继续追问:
- {追问1}
- {追问2}

临场作答模板:
先用 1-2 句话讲清背景和目标,再重点讲你具体做了什么、为什么这么做,最后补结果数据和复盘。
```

生成该模块时遵守以下规则:
- 差答案要“像真实候选人会说的话”,不是故意胡说八道;重点体现空泛、没有证据、缺少结构这类常见问题
- 好答案必须贴合题目、岗位和用户背景;如果没有简历,明确标注“以下按理想候选人示例演示”
- 技术题必须使用“技术题版”模板:优先体现结论先行、原理准确、场景落地、权衡取舍、结果量化
- 行为题必须使用“行为题版”模板:优先体现 STAR/BEI 结构、个人贡献、冲突处理、结果复盘
- 若题目同时包含技术与协作,可按用户最关心的考察维度选择主模板,并在好答案中补充另一维度
- 不要把“好答案”写成完美背稿口吻,要保留口语化面试表达

---

### Step 4A:HR 面专项训练(用户指定 HR 面时启用)

当用户输入「模拟HR面」「只练HR面」或明确说要练离职原因、薪资谈判、职业规划时,不走通用 10 问,改为输出 HR 面专项训练。

**HR 面题组覆盖原则**:
- 社招优先:离职原因、跳槽频率、空窗期、薪资预期、入职时间、管理风格适配
- 校招优先:offer 选择、地点接受度、实习/读研动机、长期发展、稳定性
- 若用户已暴露明显风险点(如频繁跳槽、转行、降薪/涨薪预期过高),至少安排 1-2 道针对性问题

**HR 面专项训练输出格式**:

```
═══════════════════════════════════════════════════
  👥 HR 面专项训练
  目标公司:[公司名] · [岗位名]
═══════════════════════════════════════════════════

HR 关注重点:
① {求职动机 / 稳定性 / 薪资预期 / 职业规划}
② {结合公司风格和用户背景补充}
③ {当前候选人最容易被追问的风险点}

──────────────────────────────────
Q1 · [主题:求职动机 / 离职原因 / 稳定性 / 薪资 / 职业规划]
──────────────────────────────────
题目:{HR 会怎么问}
HR 真正想判断什么:{隐藏考察点}
回答原则:{2-4 句,强调真诚、边界、表达策略}
踩坑提醒:{哪些说法容易减分}
💡 追问方向:{HR 可能继续问什么}
──────────────────────────────────

...(共 6-8 题)

═══════════════════════════════════════════════════
  📝 HR 面回答建议
═══════════════════════════════════════════════════

① {最关键建议 1}
② {最关键建议 2}
③ {最关键建议 3}
```

**HR 面回答生成原则**:
- 保持真诚,但不要直接输出情绪化评价,例如抱怨前司、吐槽上级、贬低团队
- 可以承认薪资、成长、业务空间等现实动机,但必须补上职业层面的正当性
- 对离职原因、空窗期、offer 比较等高风险问题,优先给出“可说版本”,避免过度暴露无关细节
- 若用户要求“帮我回答这题”,优先生成口语化、可直接说出口的版本

---

### Step 4B:薪资谈判话术指引(用户指定谈薪时启用)

当用户输入「帮我谈薪」「给我薪资谈判话术」「offer 低了怎么谈」时,不输出通用题目,改为输出薪资谈判指引。

**薪资谈判覆盖原则**:
- 默认覆盖 5 个关键环节:报预期前准备、首次回应、被压价时回话、多 offer 场景、最终收口
- 如果用户提供当前薪资、目标涨幅、城市、职级或已有 offer,话术必须基于这些条件定制
- 如果用户没有给数字,优先给结构和区间表达法,不臆造具体薪资

**薪资谈判输出格式**:

```
═══════════════════════════════════════════════════
  💰 薪资谈判话术指引
  目标公司:[公司名] · [岗位名]
═══════════════════════════════════════════════════

你的谈判局面:
① {当前已知条件}
② {最关键筹码}
③ {最大风险点}

建议谈判策略:
1. {先确认岗位匹配和面试反馈,再进入薪资}
2. {给区间而非单点}
3. {强调市场、职责、机会成本,而非情绪}

──────────────────────────────────
场景1 · 首次被问期望薪资
──────────────────────────────────
建议说法:{可直接说出口的话术}
为什么这样说:{背后的谈判逻辑}
不要这样说:{高风险表达}
──────────────────────────────────

场景2 · 对方报价低于预期
──────────────────────────────────
建议说法:{可直接说出口的话术}
为什么这样说:{背后的谈判逻辑}
不要这样说:{高风险表达}
──────────────────────────────────

场景3 · 手里有其他 offer
──────────────────────────────────
建议说法:{可直接说出口的话术}
为什么这样说:{背后的谈判逻辑}
不要这样说:{高风险表达}
──────────────────────────────────

收口建议:
① {什么时候继续谈}
② {什么时候可以接受}
③ {什么时候应该体面退出}
```

**薪资谈判生成原则**:
- 话术要坚定、克制、职业化,不要写成咄咄逼人的压价模板
- 可以强调市场价格、职责范围、历史表现和其他机会,但避免威胁式表达
- 如果用户涨幅明显过高,先提示风险,再给“进可谈、退可守”的表达法
- 若用户要求“给我一句话怎么回”,优先给简短口语版,再补更稳妥的长版

---

### Step 4C:多轮完整面试连贯模拟(用户指定完整流程时启用)

当用户输入「模拟完整面试流程」「从一面到三面完整来一遍」「多轮完整面试连贯模拟」时,不输出单轮题组,改为输出多轮连续模拟。

**多轮连贯模拟覆盖原则**:
- 默认至少覆盖 3 轮:一面、二面、三面;若用户明确要完整流程,补上 HR 面
- 各轮之间必须连贯:后一轮要继承前一轮已暴露的强项、弱项和追问点
- 一面侧重基础与简历入口;二面升级到系统设计/项目深挖;三面看综合判断、协作与价值观;HR 面看动机、稳定性与薪资
- 若用户指定岗位类型,轮次题型比例随岗位调整,但“逐轮加深”原则不变

**多轮连贯模拟输出格式**:

```
═══════════════════════════════════════════════════
  🎬 多轮完整面试连贯模拟
  目标公司:[公司名] · [岗位名]
══════════════

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
408
Maker
jennifer88huang
License
No license stated This repo states no license. By default the author keeps all rights: ask before you share it or use it commercially.
Last code change
Jul 10, 2026
SKILL.md files in the repo (including translated copies and templates)
1
Topics
ai-agents, ai-interviews, alibaba, bigtechinterviews, bytedance, careers, google-interview, interview, interview-practice, interview-prep, interview-questions, interview-skills