D
DPWonder/ai-interview-practice
Practise for an AI screening interview (the kind Mercor, micro1 and similar platforms run) inside your coding…
在 GitHub 查看 ↗链接已于 2026-11-13 核查 · HTTP 200 · 打开的是厂商自己的官网
安装与配置
客户端配置（取自该仓库的安装命令）
{
"mcpServers": {
"dpwonder-ai-interview-practice": {
"command": "npx",
"args": ["skills"]
}
}
}解析自我们于 2026-11-12 抓取的该仓库 README；我们未执行过。
command/args 来自仓库写明的安装命令；不确定时请以该项目 README 为准。
VS Code（.vscode/mcp.json —— 键名是 servers）
{
"servers": {
"dpwonder-ai-interview-practice": {
"command": "npx",
"args": ["skills"]
}
}
}VS Code 顶层键是 <code>servers</code>，其余与上面那份相同。
Claude Code（命令行）
claude mcp add --transport stdio dpwonder-ai-interview-practice -- npx skills
Claude Code 不收 JSON 文件，用这条命令直接加。
配置项的键名以你的客户端为准：客户端与 CLI
- ★ 数取值
- 0 ★ · DPWonder/ai-interview-practice · 取自 GitHub 搜索 API · （2026-11-13 20:00:50 核对）
- 来源明细
- 从该仓库的 GitHub 页面直接读取 · 条目类型：开源项目
- 收录与活跃
- 收录于 2026-11-13 · 最近见到 2026-11-14 · 共见到 2 次 · 被 3 个来源列出
- 评分构成
- 综合分 303 · 3 个来源 · repo
- 安装
npx skills
常见问题（答案都来自我们的记录）
怎么安装？
该仓库给出的安装命令是
npx skills。我们的记录里它是仓库自己提供的；不保证在你的客户端上直接可用。它适合谁 / 用来做什么？
我们把它归在这些标签下: Agent 技能。标签来自条目自身，不是我们强加的分类。
谁维护它、还在更新吗？
仓库
DPWonder/ai-interview-practice；我们收录于 2026-11-13；最近见到 2026-11-14。这里没有"官方认证"或"质量评级"——我们只记录来源与时间。# AI interview practice
以下摘录自该仓库的 README（片段） · 在 GitHub 读完整 README →
A skill for your coding agent that runs a practice AI screening interview for developers.
It asks real interview questions for your role and level, one at a time, checks each answer with
simple published word rules that quote your own words back, and asks a follow-up about your case.
English and Spanish.
Use it before an AI screening interview: the kind where an AI interviewer asks about your past
work and a written result is made from your answers, as platforms such as Mercor and micro1 run
them. This skill is not affiliated with any of them and does not have their questions. It
practises the general format: one real case, what you did yourself, why, and how it turned out.
Roles: backend, frontend, full-stack, data and ML, DevOps and SRE, mobile. Levels: junior,
mid-level, senior. The full question bank is readable here:
English and
Spanish.
## Install
### Claude Code
As a plugin, from this repository:
/plugin marketplace add DPWonder/ai-interview-practice
/plugin install ai-interview-practice@aethel-practice
Or from your shell: claude plugin marketplace add DPWonder/ai-interview-practice, then
claude plugin install ai-interview-practice@aethel-practice.
Or as a personal skill, without the plugin system:
git clone https://github.com/DPWonder/ai-interview-practice.git
mkdir -p ~/.claude/skills
cp -R ai-interview-practice/skills/ai-interview-practice ~/.claude/skills/
Then ask for it in plain words, for example "run a mock AI screening interview with me, backend,
senior". As a plugin you can also start it with /ai-interview-practice:ai-interview-practice; as
a personal skill, with /ai-interview-practice.
### Other agents
With the open skills installer, which copies the skill into the folder your agent reads:
npx skills add DPWonder/ai-interview-practice
Or copy the folder skills/ai-interview-practice by hand:
Codex: ~/.agents/skills/ (all projects) or .agents/skills/ in a repository.
Cursor: ~/.cursor/skills/ or ~/.agents/skills/ (all projects), or .cursor/skills/ or
.agents/skills/ in a project.
Any agent that reads SKILL.md files: put the folder wherever it looks for skills.
## Example session
This is an example, shortened. The answers are made up.
You: Mock AI interview please: backend, mid-level, English.
Agent: Question 1 of 4
Walk me through an outage or a serious bug you helped resolve, from the first
alert to the fix. What did you check first, and why?
You: Last March our checkout API started timing out at lunch, with about 2,000
requests a minute. I traced the slow calls to one query that scanned the whole
orders table. I added an index instead of a cache, because a cache would have
shown stale prices and the index fixed the cause. After that, p95 latency went
from 900 ms to 120 ms and the timeouts stopped.
Agent: Quick check (not a score)
Counts as an answer: 67 words.
A real example. Spotted: "Last March our checkout API started timing out..."
What you did yourself. Spotted: "I traced the slow calls to one query..."
Why you chose it. Spotted: "I added an index instead of a cache, because..."
How it turned out. Spotted: "After that, p95 latency went from 900 ms to 120 ms..."
It asks real interview questions for your role and level, one at a time, checks each answer with
simple published word rules that quote your own words back, and asks a follow-up about your case.
English and Spanish.
Use it before an AI screening interview: the kind where an AI interviewer asks about your past
work and a written result is made from your answers, as platforms such as Mercor and micro1 run
them. This skill is not affiliated with any of them and does not have their questions. It
practises the general format: one real case, what you did yourself, why, and how it turned out.
Roles: backend, frontend, full-stack, data and ML, DevOps and SRE, mobile. Levels: junior,
mid-level, senior. The full question bank is readable here:
English and
Spanish.
## Install
### Claude Code
As a plugin, from this repository:
/plugin marketplace add DPWonder/ai-interview-practice
/plugin install ai-interview-practice@aethel-practice
Or from your shell: claude plugin marketplace add DPWonder/ai-interview-practice, then
claude plugin install ai-interview-practice@aethel-practice.
Or as a personal skill, without the plugin system:
git clone https://github.com/DPWonder/ai-interview-practice.git
mkdir -p ~/.claude/skills
cp -R ai-interview-practice/skills/ai-interview-practice ~/.claude/skills/
Then ask for it in plain words, for example "run a mock AI screening interview with me, backend,
senior". As a plugin you can also start it with /ai-interview-practice:ai-interview-practice; as
a personal skill, with /ai-interview-practice.
### Other agents
With the open skills installer, which copies the skill into the folder your agent reads:
npx skills add DPWonder/ai-interview-practice
Or copy the folder skills/ai-interview-practice by hand:
Codex: ~/.agents/skills/ (all projects) or .agents/skills/ in a repository.
Cursor: ~/.cursor/skills/ or ~/.agents/skills/ (all projects), or .cursor/skills/ or
.agents/skills/ in a project.
Any agent that reads SKILL.md files: put the folder wherever it looks for skills.
## Example session
This is an example, shortened. The answers are made up.
You: Mock AI interview please: backend, mid-level, English.
Agent: Question 1 of 4
Walk me through an outage or a serious bug you helped resolve, from the first
alert to the fix. What did you check first, and why?
You: Last March our checkout API started timing out at lunch, with about 2,000
requests a minute. I traced the slow calls to one query that scanned the whole
orders table. I added an index instead of a cache, because a cache would have
shown stale prices and the index fixed the cause. After that, p95 latency went
from 900 ms to 120 ms and the timeouts stopped.
Agent: Quick check (not a score)
Counts as an answer: 67 words.
A real example. Spotted: "Last March our checkout API started timing out..."
What you did yourself. Spotted: "I traced the slow calls to one query..."
Why you chose it. Spotted: "I added an index instead of a cache, because..."
How it turned out. Spotted: "After that, p95 latency went from 900 ms to 120 ms..."
收录徽章（可选）
想把收录标记放进 README 就复制这行，可选，不影响收录。
[](https://anclum.com/zh/s/dpwonder-ai-interview-practice/)
- 来源
- github · https://github.com/DPWonder/ai-interview-practice
- 按领域浏览
- Agent 技能
- 收录来源
- 3 个独立来源
- 收录于
- 今天
同类推荐
所属领域与标签
每个标签都能点进去看同类的全部条目。数字是当前库里的真实条数。