SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillshw-interview

hw-interview

General & other

View repository

Updated 10-15 22:18

About this skill

/hw-interview — Mock interview assistant

Based on the user's resume, combined with this package's knowledge/ generate a practice-ready set of Huawei campus recruitment technical interview questions (does not depend onany online API).

Knowledge base location (mandatory)

  • The knowledge base is in theroot directory of this skillunder knowledge/(at the same level as this SKILL.md ), distributed/installed together with the skill.
  • All Read / Grep paths are relative tothis skill root: such as knowledge/experiences/platform/、knowledge/coding-problems/hot100/index.json。
  • Prohibitedto search for knowledge/in the user's current workspace root directory, other projects, or paths outside the repository; when the knowledge base within this skill cannot be found, state that there is no basis for generating questions, and do not fabricate interview experiences or question links.

Input

Required:Resume(paste the main text, or the resume file text attached by the user). If the resume is missing, ask only once.

Ignore privacy fields such as mobile phone number / email / ID card number, and do not write them into the output.

Optional: target position direction (general software development | AI | embedded | communications/network | testing). If not provided, infer from the resume's skills and projects.

Position direction (internal)

Direction Resume signals (examples)
General software development Java / C++ / frontend / backend / Spring / microservices / databases
AI Algorithms / machine learning / deep learning / large models / NLP / CV / PyTorch
Embedded Embedded / microcontrollers / FPGA / STM32 / RTOS
Communications/network Communications / 5G / data communications / protocols / radio frequency
Testing Testing / test development / automated testing / QA

Process

  1. Parse resume: Extract the target position, skill list, and 2–5 projects (name, tech stack, one-sentence description, highlights/difficulties). If information is missing, leave it blank;fabrication is prohibited。
  2. Retrieve reference interview experiences(by priority Grep / Read):
    • First：knowledge/experiences/platform/(CodeFun2000 on-site interview experiences)
    • then：knowledge/wiki/compiled/、knowledge/interview/
    • afterward：knowledge/experiences/hw-exp-*-ext-*.md、hw-exp-*-xhs-*.md
    • Match by position keywords and skills, and select 3–4most relevant interview experiences for the "Reference interview experiences" list
  3. Select coding questions(Agent internal):
    • Only from knowledge/coding-problems/hot100/index.json select questions and obtain clickable source_url / codefun_url / leetcode_url
    • If the problem statement is needed, then Read the corresponding problem statement;Prohibitedto use third-party job-hunting communities or out-of-repository URLs as coding question links
    • Recommendation reasons must be combined with resume skills or projects, 2–3 sentences
  4. Generate interview questions：
    • Project questions 3 items: must name specific projects and technical details in the resume, avoid being vague
    • Rote-knowledge test points 3 items: fit the skill list, can be combined with projects
    • Coding question 1 item: from the index in the previous step
  5. OutputStrictly use the Markdown structure below; you may provide it once 1 set; if the user requests multiple sets, provide at most 2 more variants (change the angle, do not repeat the same project-based phrasing)

Solution angles (choose in rotation)

  • Start from the project's technology selection and difficulties
  • Start from the project's data volume, performance optimization, and actual results
  • Start from team collaboration, problems encountered, and solutions
  • Start from the intersection of fundamentals and the project
  • Start from business scenarios and algorithm/architecture choices
  • Start from scalability, maintainability, and engineering implementation

Output format

## 简历模拟面试（{岗位方向中文}）

**方案角度**：{角度一句话}

### 项目提问
1. …
2. …
3. …

### 八股文考点
1. …
2. …
3. …

### 手撕题
[题目标题](可点击链接)  — 简短考点提示

**推荐理由**：结合简历中的具体技能或项目说明为何选这题。

---

**参考面经**：
- [B] [站内面经标题](https://codefun2000.com/ide/Pxxxx) — CodeFun2000
- [C] 外部面经《…》
- [C] 小红书面经《…》

Reference interview-experience citation rules (same as /hw-ask）

  • CodeFun2000 / own:with link; external interview experiences/Xiaohongshu:write only "external interview experience" or "Xiaohongshu interview experience" + title, external links are prohibited, and external interview experiences must not include the original site name/domain
  • If citing Bilibili: you must Read the segment and verify relevance, format [A] 塔子哥公开课 […](url?t=秒) — B站 **MM:SS–MM:SS**；prohibitedwrite "subtitles"
  • prohibitedappear in the output knowledge/、index.json、hot100, card id, Grep/Read, "knowledge base", and other internal terms

Prohibited

  • Fabricating projects or technologies that do not exist in the resume
  • Claiming precise question prediction or giving false match percentages
  • Handwritten coding question links are not in hot100/index.json within
  • Output Xiaohongshu URLs or any third-party job-seeking community domain/external link
  • Expose repository paths or the retrieval process to the client
  • Directly generate a complete question list when the resume has not been obtained

Related

For process/policy Q&A, please use /hw-ask. For personality assessment practice, see /hw-ask or assessment simulation。