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/an8079/take-skills/deep-interviewnpx skills add an8079/take-skills --skill deep-interviewgit clone --depth 1 https://github.com/an8079/take-skillsWrote 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/an8079/take-skills/deep-interview)<a href="https://agentmods.dev/skills/an8079/take-skills/deep-interview"><img src="https://agentmods.dev/badge/skills/an8079/take-skills/deep-interview.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 5.1 | $0.00000 | $0.01577 |
| Opus 5 | $0.00000 | $0.00788 |
| Sonnet 5 | $0.00000 | $0.00315 |
| Haiku 4.5 | $0.00000 | $0.00158 |
Grade A, and why
deep-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 6d 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
deep-interview — Socratic Deep Interview Protocol
name
deep-interview
description
苏格拉底式深度访谈技能:通过连续追问挖掘用户真实需求、隐含假设和未被言明的约束。与 deep-dive(技术深挖)不同,deep-interview 是人本需求挖掘——关注"为什么"而非"怎么做"。每次访谈以"三层真相"(表面需求 / 深层动机 / 元动机)为导向,直到用户确认已触及核心。
when to activate
用户说以下话时激活:
- "我想做一个产品"
- "deep interview"
- "帮我理清需求"
- "我有个想法"
- "苏格拉底"
- 用户提出模糊或高层次的请求("帮我做一个 App"、"做个好的网站")
- 需求不清晰但用户急着要方案时
激活策略:当用户需求过于抽象(无具体指标、用户画像、技术约束),且尚未被其他技能处理时触发。
protocol
核心原则
- 不预设答案:用户说什么追问什么,不引导到预设结论
- 一次一问:每次只问一个问题,避免多重问题导致信息混乱
- 追问 5 层:直到用户说"对,这就是核心"或主动停止
- 记录沉默:用户沉默时等待 3 秒,不急着补充
- 收敛确认:每层追问后复述理解,寻求确认
第一层:表面需求(Surface Need)
目标:弄清用户想要什么
协议步骤:
- 复述用户原话:"所以你想..."
- 追问:"具体指什么?"
- 追问:"你期望的最终效果是什么样的?"
- 判断:当用户开始用"不只是...而且是..."这样的句式时,说明已触及第二层
示例问题:
- "你说的 XX,具体指什么?"
- "你希望最后呈现出来是什么样子的?"
- "用户打开这个功能时,第一眼应该看到什么?"
- "这个功能上线后,你怎么判断它是成功的?"
第二层:深层动机(Deep Motivation)
目标:理解用户为什么想要这个
协议步骤:
- 引入动机词:"你希望解决什么问题?"
- 追问原因链:"为什么这个对你重要?"
- 每回答一次,再问一次"为什么这对你重要?"(3~5 次)
- 判断:当回答开始涉及个人价值、情感、职业目标时,说明已触及深层
示例问题:
- "为什么你想要这个?"
- "这背后解决的是一个什么问题?"
- "如果没有这个,你会面临什么?"
- "这个问题困扰你多久了?"
- "对你来说,理想状态是什么样的?"
- "做到什么程度你会说'这就对了'?"
第三层:元动机(Meta Motivation)
目标:理解用户的元动机——他为什么会在此刻提出这个需求
协议步骤:
- 追问情境:"是什么触发你今天想到这个?"
- 追问约束:"你有哪些不能做的事?"
- 追问边界:"有没有你绝对不想的方案?"
- 判断:当用户开始主动给出解决方案时,说明已触及元动机
示例问题:
- "是什么让你今天想到这个?发生了什么事?"
- "你有预算/时间/技术限制吗?"
- "有没有你绝对不想用的技术或方案?"
- "这个问题如果不解决,最坏的结果是什么?"
- "谁会对这个决定说 No?为什么?"
收敛阶段:综合确认(Synthesis)
在完成所有层级的追问后,输出结构化总结:
## 🎯 需求画像
### 表面需求
[一句话描述用户要什么]
### 深层动机
[背后的真正问题/动机]
### 元动机
[触发事件 + 约束边界]
### 目标用户
[如果用户没说,推断并确认]
### 成功标准
[量化指标,至少 2 个]
### 明确排除
[用户明确不想的方案/技术/方向]
### 核心问题
[一句话:这个问题不解决,用户会怎样?]
最后问一句:"以上这些,你最想先解决哪个?"
examples
Example 1:用户说"我想做一个学习 App"
Agent 响应:
Agent: 你想做学习 App,具体是指什么?有什么功能?
User: 就是帮学生复习考试的
Agent: 所以是帮助学生准备考试。具体是哪类考试?
User: 高考
Agent: 高考复习现在的痛点是什么?是什么让你想做这个?
User: 主要是内容太多,学生不知道从哪里开始
Agent: 内容太多导致无从下手。那么你觉得理想状态是?
User: 学生一打开就知道今天该复习什么
Agent: 一打开就知道该复习什么。你希望这个'知道'是系统自动算出来的,还是学生自己选的?
User: 系统自动算的,因为学生自己不会规划
Agent: (触及深层动机)所以系统的价值是替学生做规划。那你希望系统的规划依据是什么?
User: 根据考试时间来倒推
Agent: 好。让我确认一下:你希望做一个 App,通过倒推考试时间来自动规划每天的复习内容,帮助高考学生解决'内容太多不知道从哪开始'的问题。对吗?
User: 对!
Agent: 那这个 App 上线后,你怎么判断它是成功的?
User: 如果学生用了之后成绩平均提高 10 分
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.
- 6d ago First seen · 160 lines · 0 tokens per session scan A 4a20ec5f1059
deep-interview is a skill published in the GitHub repository an8079/take-skills (4 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,577 tokens. 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…