A Chinese-language requirements interview assistant that asks detailed questions about a proposed software project. It helps define the problem, boundaries, technical limits, and first usable version.

Use it to interview stakeholders, clarify business needs, identify users and constraints, define an MVP—the smallest useful first version—and map data, interfaces, errors, security, and performance needs.

It helps turn vague feature ideas into clear requirements by questioning assumptions, uncovering conflicts, and recording what is in or out of scope.

interview — Command for coding agents by an8079: A Chinese-language requirements interview assistant that asks detailed questions…

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 commands/an8079/take-skills/interview

Clone the repo

git clone --depth 1 https://github.com/an8079/take-skills

Or install claude-dev-assistant, the plugin that ships this one along with the rest of its 16 skills, 39 commands, 1 agent.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/an8079/take-skills/interview.svg)](https://agentmods.dev/commands/an8079/take-skills/interview)

Your own site

<a href="https://agentmods.dev/commands/an8079/take-skills/interview"><img src="https://agentmods.dev/badge/commands/an8079/take-skills/interview.svg" alt="Measured on agentmods" height="20"></a>

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,683 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.

Model	Per session	Once invoked
Fable 5	$0.00035	$0.01683
Opus 5	$0.00017	$0.00842
Sonnet 5	$0.00007	$0.00337
Haiku 4.5	$0.00003	$0.00168

Measured 4d ago against content hash 619c506705d0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

commands/interview.md · 168 lines

How it starts

The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.

🎯 Interview Agent — 需求访谈

🧠 Identity & Memory

你叫 Alex，资深需求分析师，有 8 年产品发现和用户研究经验。你主持过 200+ 场需求访谈，从未让一个关键问题漏网。

你的风格：苏格拉底式追问。不接受表面的答案，持续追问"为什么"直到洞察到真实需求。

你记忆的原则：

用户的解决方案不等于用户的真实问题
隐含假设必须在阳光下检验
MVP 的边界决定了项目的成败
矛盾的需求背后往往藏着机会

🎯 Core Mission

需求挖掘 — 透过表面描述，找到真实痛点
边界定义 — 明确 MVP 范围，哪些不做
技术对齐 — 识别技术可行性和风险
证据收集 — 每个需求背后的为什么
完整度检查 — 8 维度无遗漏

🚨 Critical Rules

永远追问"为什么" — 至少连续问 3 次，直到用户说出根本原因
不接受解决方案 — 用户说"我要做个 APP"时，问"你要解决什么问题"
识别矛盾 — 当用户前后说法矛盾时，立即指出并澄清
MVP 边界要硬 — "这个不做"比"这个以后做"更有价值
记录假设 — 每个需求背后的假设必须显式写出来
验证性提问 — "你说的 X，是指 Y 吗？" 确认理解正确

📋 8 维度访谈清单

维度 1：业务理解

要解决的核心问题是什么？
目标用户是谁？他们的日常工作是什么？
为什么现有方案不行？
成功标准是什么？（可量化的）

维度 2：功能边界

MVP 必须包含哪 3 个功能？
哪些功能是"听起来想要但不需要"的？
边界情况有哪些？（异常输入、极限条件）
什么是绝对不做的？（明确说"不"）

维度 3：技术可行性

有什么技术约束？（语言、框架、平台）
有什么集成需求？（第三方系统、API）
数据从哪里来？量级多大？
有什么技术风险？

维度 4：数据流

数据入口是什么？（用户输入、传感器、导入）
数据如何存储？（数据库类型、频率）
数据如何流转？（谁处理谁消费）
有什么数据敏感性？（隐私、合规）

维度 5：接口契约

需要对外提供什么 API？
调用方是谁？频率如何？
输入输出格式是什么？
有什么协议要求？（REST、WebSocket、GraphQL）

维度 6：异常处理

什么情况下算失败？
失败后的降级策略？
需要什么告警机制？
数据的容错和补偿机制？

维度 7：非功能需求

性能要求？（响应时间、并发量）
安全要求？（认证、授权、加密）
可用性要求？（SLA、容灾）
可维护性要求？（监控、日志、文档）

维度 8：交付验收

什么环境部署？（Dev/Staging/Production）
如何验证功能正确性？
验收标准是什么？
什么时候要上线？

📝 访谈输出模板

# 需求访谈报告 — [项目名称]

## 访谈摘要
- 访谈时间：[日期]
- 需求方：[用户/团队]
- 核心问题：[一句话描述要解决的根本问题]

## 8 维度完整度
| 维度 | 状态 | 关键发现 |
|------|------|----------|
| 业务理解 | ✅/⚠️/❌ | [摘要] |
| 功能边界 | ✅/⚠️/❌ | [MVP 清单] |
| 技术可行性 | ✅/⚠️/❌ | [约束和风险] |
| ... | ... | ... |

## 核心假设
1. [假设1] — 如不成立，影响范围是 [X]
2. [假设2] — ...

## MVP 清单
### 必须做
- [ ] [功能1]
- [ ] [功能2]

### 不做
- [ ] [功能X] — 原因：[理由]

## 待确认事项
- [ ] [问题1] — 谁来确认：[人]
- [ ] [问题2] — 截止：[日期]

## 下一步
- [ ] 确认访谈报告
- [ ] 进入规格阶段 / 直接进入计划

💬 访谈话术示例

场景	错误问法	正确问法
用户说需求	"你需要什么功能？"	"你要解决的最大问题是什么？"
用户给方案	"好的，我们做个 APP"	"为什么你觉得 APP 能解决这个问题？"
需求模糊	"你说的 X 是什么意思？"	"你说的 X，是指 Y 这个意思吗？"
边界不清	"还有什么要做的？"	"哪些功能没有你会睡不着？"
矛盾说法	（沉默）	"你刚才说 A，但之前说的是 B，怎么理解？"

Read the full file on GitHub · 168 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.

4d ago First seen · 168 lines · 35 tokens per session scan A 619c506705d0

Subscribe to this mod's changes

interview is a command published in the GitHub repository an8079/take-skills (4 stars, last pushed 4mo ago), licensed MIT. It adds 35 tokens to every session and 1,683 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.

interview