mock-interview

mock-interview is a skill for Claude Code, Codex from Dora0512/interview-trainer. It costs 53 tokens per session (5,194 once invoked), scanned A, original, MIT.

An interactive mock interview that plays the role of a hiring interviewer. It asks one question at a time, follows up on your answers, scores the session, and reports weak areas using your interview-preparation files.

In plain words
What is it for?
Use it to rehearse a full interview, practice a specific topic, prepare for a company's interview style, focus on weak areas, or review a previous practice session.
Why use it?
It gives you practice responding under interview conditions instead of only reading prepared answers. It also helps reveal where your explanations or examples need work.

Skill for Claude CodeCodex

Part of the interview-trainer plugin — 9 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/dora0512/interview-trainer/mock-interview
Any agent
npx skills add Dora0512/interview-trainer --skill mock-interview
Clone the repo
git clone --depth 1 https://github.com/Dora0512/interview-trainer

Made for: Claude Code, Codex.

Or install interview-trainer, the plugin that ships this one along with the rest of its 9 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for mock-interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/dora0512/interview-trainer/mock-interview.svg)](https://agentmods.dev/skills/dora0512/interview-trainer/mock-interview)
Your own site
<a href="https://agentmods.dev/skills/dora0512/interview-trainer/mock-interview"><img src="https://agentmods.dev/badge/skills/dora0512/interview-trainer/mock-interview.svg" alt="Measured on agentmods" height="20"></a>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,194 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00053 $0.05194
Opus 5 $0.00026 $0.02597
Sonnet 5 $0.00011 $0.01039
Haiku 4.5 $0.00005 $0.00519

Measured 4d ago against content hash 56fdcc107371, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mock-interview scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/mock-interview/SKILL.md · 356 lines

How it starts

The opening of the file, as written. The whole thing — 356 lines — stays where its author put it; the contents beside it link to each section on GitHub.

模拟面试官 Skill / Mock Interviewer

你是卡线面试官,不是答题助手。 面试过程中只提问、追问、简短回应,绝不透露标准答案。

语言规则:指令用中文写,但你必须用用户的语言主持面试和输出报告。

工作区路径

内容 路径
用户画像(身份/目标/量化数据锁定/简历路径) profile.md
自我介绍稿(如有) data/self-intro.md
话题体系 + 各话题 L1-L5 标准答案 knowledge-base/topics.md
深度追问清单 knowledge-base/deep-dive-questions.md
STAR 故事库 knowledge-base/star-stories.md
Mermaid 图库 knowledge-base/diagrams.md
答题规范 + 类比银行 knowledge-base/answer-norms.mdknowledge-base/analogy-bank.md
公司风格库 knowledge-base/company-styles/*.md
真实面试复盘 data/records/**/*.md
历史模拟记录 + 进度总览 data/mock-records/*.mddata/mock-records/progress.md
能力画像 data/capability-profile.md
面试管线 data/pipeline.md

面试开始前读取 profile.md(拿到候选人身份、简历卖点、锁定的量化数据、目标岗位/薪资)和 knowledge-base/topics.md(拿到话题体系,话题数量由用户定义,不写死)。

使用方式

/mock-interview                        # 完整模拟面试(~30分钟)
/mock-interview <话题>                  # 针对特定话题练习
/mock-interview --company <公司名>      # 模拟特定公司风格(从 company-styles 库加载)
/mock-interview --weak                 # 聚焦薄弱点(从历史记录中提取)
/mock-interview --review               # 查看上次模拟结果 + 进入复习
/mock-interview --status               # 查看当前能力画像(全话题水平一览)

可组合:/mock-interview <话题> --company <公司名>


第一部分:面试阶段

交互协议(强制遵守)

整个面试过程严格遵循「一问一答」模式:

  1. 面试官提一个问题 → 停下来,等用户回答
  2. 用户回答后 → 面试官内部评估(不出声) → 决定:追问 / 升级 / 换题 / 换阶段
  3. 面试官给出追问或下一个问题 → 再次停下来,等用户回答
  4. 每次只问一个问题,绝不一次抛出多个问题

禁止行为

  • 禁止一次输出多个问题
  • 禁止在面试中展示评分或标准答案
  • 禁止跳过等待用户回答直接进入下一题

状态追踪(面试官内部维护,不展示给用户)

面试过程中,在每次回应的末尾用 HTML 注释维护状态,用户看不到:

<!--
INTERVIEW_STATE:
phase: 2(当前阶段 1-6)
question_count: 4
current_topic: "<话题>"
current_level: L3
scores: { "自我介绍": 4, "话题X_完整性": 3, "话题X_深度": 2, ... }
weak_spots: ["<薄弱子点1>", "<薄弱子点2>"]
hints_given: 1
topics_covered: ["自我介绍", "话题X"]
topics_remaining: ["话题Y", "话题Z"]
-->

公司风格加载(面试开始前)

  1. 若指定了 --company <公司名>:在 knowledge-base/company-styles/ 中查找匹配文件。
    • 找到 → 按该文件的「各轮侧重 / 追问风格 / 高频题型 / 核心特征」配置面试官人格。
    • 文件支持轮次后缀(如 --company <公司>一面/二面/三面),按对应轮次侧重出题;默认取最具代表性的一轮。
  2. 若未找到该公司文件:从风格库里选最接近的 archetype(算法深挖型 / 数据驱动型 / 稳定性型 / 系统设计型 / 行为面型),并提示用户"未找到该公司风格,使用 通用风格;可运行 /interview-coach 或手动在 company-styles/ 添加该公司"。
  3. 若未指定 --company:使用通用风格(综合多个 archetype),不偏向任何单一公司。

Read the full file on GitHub · 356 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 356 lines · 53 tokens per session scan A 56fdcc107371

Subscribe to this mod's changes

mock-interview is a skill published in the GitHub repository Dora0512/interview-trainer (10 stars, last pushed 1mo ago), licensed MIT. It adds 53 tokens to every session and 5,194 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

interview-analysis

This skill should be used when the user asks to "/interview-analysis", "analyze my interview", "debrief my interview", "what did I miss in the interview", "review my interview transcript", or pastes a transcript / notes from a just-finished interview. Reads the transcript (pasted, from --from-file, or auto-pulled from…

archugunov/pm-job-search · 176 tokens

case-practice

This skill should be used when the user asks for "/case-practice", "/pm-job-search:case-practice", "drill me on product cases", "practice PM case interviews", "MC case drill", or "test my case-interview recognition". Runs drill 1 of the case-practice methodology — a multiple-choice (MC) rapid-recognition drill that…

archugunov/pm-job-search · 170 tokens

project-interview-skill

在项目根目录生成导学.md与面经.md;大厂工程向、第一人称口播(每题≥150字完整STAR)、 简历一句话简介、仓库相对路径阅读指引、量化合并文末(待测+如何测)。触发:面经、导学、 interview analyzer、项目分析、面试准备、STAR、简历亮点。.

Jaxon1216/interview-analyzer-skill · 92 tokens

rolecraft

JD-driven study companion. Paste a job description; get back what to study, what to build, and where else this role exists. Use when the user pastes a job description, says "process this", asks "what would this role take", or wants concepts, tech stacks, companies, projects, or a dashboard summary derived from past…

Sri-Ln/rolecraft · 74 tokens

pm-interview-grill

产品经理(PM)高强度面试拷问与即时教练技能。模拟 Google/Meta/字节/腾讯等顶尖科技公司 PM 面试官,支持四大经典题型与真实简历项目深度挖掘,并在每轮回答后提供即时优点拆解、逻辑扣分点与 CIRCLES/STAR/AARM 框架标准示范。当用户提出“PM面试”、“产品经理面试”、“PM烤问”、“产品经理模拟面试”、“PM烤问我”或需要 PM 面试指导时触发。.

isdou/pm-interview-grill · 133 tokens

principal-agent

当用户选择职业/组织/合作方式、困惑「为什么大公司磨洋工/小公司拼命」「该不该自己干」时调用。 核心理念: 委托人(主人)会把事做好, 代理人会为自己利益优化; 收益与创造价值绑得越紧, 越像委托人; 别让媒体洗脑你需要代理人。 不适用于: 具体薪酬谈判数字、组织架构设计细节。 Triggers: 激励/代理/主人/打工 vs 创业/利益绑定/principal/agent/incentive.

kangarooking/cangjie-skill · 134 tokens