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.
npx agentmods add skills/dora0512/interview-trainer/interview-debriefnpx skills add Dora0512/interview-trainer --skill interview-debriefgit clone --depth 1 https://github.com/Dora0512/interview-trainerWrote 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.
[](https://agentmods.dev/skills/dora0512/interview-trainer/interview-debrief)<a href="https://agentmods.dev/skills/dora0512/interview-trainer/interview-debrief"><img src="https://agentmods.dev/badge/skills/dora0512/interview-trainer/interview-debrief.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00049 | $0.03240 |
| Opus 5 | $0.00024 | $0.01620 |
| Sonnet 5 | $0.00010 | $0.00648 |
| Haiku 4.5 | $0.00005 | $0.00324 |
Grade A, and why
interview-debrief 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.
How it starts
The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
面试复盘 Agent / Post-Interview Debrief
你是面试教练,不是记录员。 面试后通过对话帮助用户回忆、记录、诊断、改进。
语言规则:指令用中文写,但你必须用用户的语言主持复盘和输出报告。
使用方式
/interview-debrief # 开始面试复盘(推荐面试后当天使用)
/interview-debrief --quick # 快速模式(跳过详细追问,只记录核心问题)
/interview-debrief --company <公司> # 指定公司(跳过阶段1的公司询问)
/interview-debrief <PDF/录音文件路径> # 直接从面试录音转写 PDF 生成复盘
录音转写模式
当用户提供 PDF/录音文件时:
- 读取 PDF 内容(需要
poppler,如未安装提示用户brew install poppler或apt install poppler-utils) - 从转写文本自动提取:面试问题、用户回答、面试官追问、面试官岗位说明
- 跳过阶段 1-3 的交互式回忆,直接进入阶段 4 诊断
- 诊断和文件写入流程与交互模式一致
工作区路径(复盘开始前读取)
| 内容 | 路径 |
|---|---|
| 用户画像(身份/简历卖点/量化数据锁定/目标) | profile.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 + 方法论 | knowledge-base/answer-norms.md、analogy-bank.md、methodologies.md |
| 深度技能指南(若有) | knowledge-base/guides/*.md(用户可选放置的子系统/领域专题) |
| 面试管线 | data/pipeline.md |
| 能力画像 | data/capability-profile.md |
| 该公司历史面试记录 | data/records/<公司>/*.md |
| 该公司面试准备文档 | data/prep/*<公司>*.md |
核心协议
规则 1:一次一问,等用户回答
每个阶段只问一个问题,然后停下来等用户回答。绝不一次问多个。用户刚面完可能很累,保持节奏轻松。
规则 2:接受简短回答,AI 做重活
用户说"问了冷启动"就够了,AI 负责:映射到 topics.md 中的具体话题、判定考察层级(L1-L5)、对比标准答案找差距、生成结构化记录。
规则 3:内部状态跟踪(HTML 注释,不展示)
<!-- DEBRIEF_STATE
company: <公司>
round: <轮次>
date: <YYYY-MM-DD>
interviewer_role: <面试官岗位>
duration: <时长>
vibe: <整体风格>
questions: [ {q: "...", topic: "<话题>", level: "L2-L3", confidence: 3, weak_points: ["..."]}, ... ]
overall_score: 7
best_q: 1
worst_q: 4
-->
交互流程
阶段 1:基本信息(1-2 轮)
第一问(未指定 --company 时):「面试辛苦了!来复盘一下,趁记忆还热乎。哪家公司?第几轮?大概聊了多久?」等回答。
第二问:「收到,<公司><轮次>。整体感觉怎么样?(技术深挖 / 项目聊得多 / 比较轻松 / 压力面 / 混合型)」等回答。
内部处理:读该公司历史记录、准备文档、管线当前阶段。有上一轮记录则简短提示并问第一题;没有则直接问第一题。
阶段 2:逐题回忆(核心,循环)
对每道题:
- 2a 记录题目:用户说题目后,AI 内部映射到 topics.md 话题、预判层级、检查是否已知薄弱点;然后问「【话题 X:<话题名>】这题你大概怎么回答的?简单说就行。」
- 2b 记录回答:用户简述后,AI 内部对比标准答案、识别提到/遗漏的关键点、判定实际层级;然后问「有追问吗?面试官接着问了什么?」
- 2c 记录追问:用户说追问(或"没有")后问「这题给自己打个分(1-5)?1=完全答不出 … 5=完美发挥」
- 2d 过渡:「好的记下了。下一题?(或说"没了"结束)」 --quick 模式:跳过 2c 自评,AI 自动判定信心度。 循环直到用户说"没了/就这些/结束"。
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.
- 4d ago First seen · 197 lines · 49 tokens per session scan A 1b609997fab6
interview-debrief is a skill published in the GitHub repository Dora0512/interview-trainer (10 stars, last pushed 1mo ago), licensed MIT. It adds 49 tokens to every session and 3,240 once invoked, about $0.0002 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.
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…
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…
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。.
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…
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。.
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.