Token导航 LogoToken导航

Agent Skill · 研究检索

interview-conducting(采访进行)

interview-conducting 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

interview-conducting 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为执行命令;许可证为 MIT,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 57,063。

总安装 441周安装 18GitHub Stars 61下载 143核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:interview-conducting(采访进行)
来源仓库:https://github.com/melodic-software/claude-code-plugins
仓库路径:skills/interview-conducting
安装命令:
npx skills add https://github.com/melodic-software/claude-code-plugins --skill interview-conducting
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/melodic-software/claude-code-plugins --skill interview-conducting

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

该技能用于查找、检索和筛选相关信息。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。适合根据关键词或任务场景快速定位候选结果。可通过 npx 命令从指定 GitHub 仓库安装使用。使用前需确认权限范围及是否涉及联网或文件操作。

interview-conducting 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/interview-conducting

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/melodic-software/claude-code-plugins --skill i…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要执行命令,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

interview-conducting 怎么安装?

在终端执行 npx skills add https://github.com/melodic-software/claude-code-plugins --skill interview-c…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

interview-conducting 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

interview-conducting 需要什么权限?

权限级别是执行命令。安装流程涉及命令执行,可能通过 npx skills add https://github.com/melodic-software/claude-code-plugins --skill interview-conducting;npx skills add melodic-software/claude-code-plugins --skill "interview-conducting" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

interview-conducting 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

interview-conducting 用的人多吗?

公开数据是累计安装 441 次,近一周安装 18 次,下载 143 次,GitHub 61 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

interview-conducting 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要执行命令,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 不能接受 Skill 在你机器上执行命令的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
interview-conducting

采访进行 · 本页

44161执行命令MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Interview Conducting Skill

AI-led stakeholder interviews using research-backed LLMREI patterns for effective requirements elicitation.

When to Use This Skill

Keywords: stakeholder interview, requirements interview, LLMREI, elicit requirements, talk to stakeholder, interview session, user interview, customer interview

Invoke this skill when:

  • Conducting a structured requirements interview with a stakeholder
  • Exploring user needs through conversation
  • Gathering requirements from subject matter experts
  • Clarifying and deepening understanding of requirements

Interview Modes

Real Stakeholder Interview

When interviewing an actual person through the chat interface:

mode: real_stakeholder
approach:
  - Use AskUserQuestion tool for structured questions
  - Allow natural conversation flow
  - Adapt questions based on responses
  - Summarize and confirm understanding periodically

Simulated Interview (Solo Mode)

When no real stakeholder is available:

mode: simulated
approach:
  - Spawn persona agent via Task tool
  - Conduct interview with simulated stakeholder
  - Mark requirements with lower confidence
  - Flag items needing real stakeholder validation

Interview Structure (LLMREI Pattern)

Phase 1: Opening (2-3 minutes)

Goals:

  • Establish rapport
  • Set expectations
  • Explain the process

Questions:

  • "Thank you for your time. Could you briefly describe your role and how you interact with this project?"
  • "What outcomes would make this interview successful for you?"

Phase 2: Context Gathering (5-10 minutes)

Goals:

  • Understand stakeholder perspective
  • Identify key concerns
  • Map relationships

Question Types:

  • Role-based: "How does your team currently handle X?"
  • Priority-based: "What are your top three concerns about this project?"
  • Relationship-based: "Who else should we talk to about X?"

Phase 3: Requirements Exploration (15-25 minutes)

Goals:

  • Elicit functional requirements
  • Identify non-functional requirements
  • Uncover constraints and assumptions

Question Pathways:

Start with open-ended → Follow up with specifics → Validate understanding

Example:
Q1: "What should the system do when a user logs in?"
Q2: "You mentioned 'quick access to dashboard' - what does quick mean to you?"
Q3: "So the login should complete in under 2 seconds and show the dashboard. Is that right?"

Phase 4: Validation (5-10 minutes)

Goals:

  • Summarize key requirements
  • Verify understanding
  • Identify gaps

Techniques:

  • Read back requirements for confirmation
  • Ask "What have we missed?"
  • Prioritize using MoSCoW

Phase 5: Closing (2-3 minutes)

Goals:

  • Thank stakeholder
  • Explain next steps
  • Offer follow-up

Question Types

Context-Independent Questions

General questions applicable to any interview:

QuestionPurpose
"What is your primary goal for this system?"High-level vision
"Who are the main users?"User identification
"What existing systems does this replace/integrate with?"Context mapping
"What would failure look like?"Risk identification

Context-Deepening Questions

Follow up on stakeholder responses to get specifics:

Pattern: [Stakeholder says X] → "When you say X, what specifically do you mean?"

Examples:
- "fast" → "What response time are you expecting? Under 1 second?"
- "secure" → "What specific security requirements apply? Authentication methods?"
- "easy to use" → "Can you describe what easy means? Any specific workflows?"

Context-Enhancing Questions

Introduce considerations the stakeholder may not have mentioned:

Pattern: Suggest possibilities based on domain knowledge

Examples:
- "Have you considered how this works on mobile devices?"
- "What happens if the user loses connectivity mid-operation?"
- "How should the system handle peak load during [known busy period]?"

Requirement Extraction

As requirements emerge, capture them in this format:

requirement:
  id: REQ-{number}
  text: "{requirement statement}"
  source: interview
  stakeholder: "{role}"
  timestamp: "{ISO-8601}"
  type: functional|non-functional|constraint
  priority: must|should|could|wont
  confidence: high|medium|low
  raw_quote: "{exact stakeholder words if notable}"

Common Mistakes to Avoid

MistakePrevention
Very long questionsKeep questions concise and focused
Multiple unrelated questionsOne question at a time
Leading questionsUse neutral language
Skipping NFRsExplicitly ask about performance, security, usability
No summaryRecap periodically to verify understanding
RushingAllow silence; stakeholders often add important details

Interview Summary Template

After each interview, generate:

interview_summary:
  session_id: "INT-{number}"
  stakeholder_role: "{role}"
  duration_minutes: {number}
  date: "{ISO-8601}"
  autonomy_level: "{guided|semi-auto|full-auto}"

  key_themes:
    - "{theme-1}"
    - "{theme-2}"

  requirements_elicited:
    - id: REQ-{number}
      text: "{requirement}"
      confidence: high|medium|low
      type: functional|non-functional|constraint
      priority: must|should|could

  follow_up_needed:
    - "{question or topic needing clarification}"

  stakeholder_quotes:
    - "{notable direct quote}"

  observations:
    - "{interviewer observation about needs or concerns}"

  next_steps:
    - "{recommended action}"

Delegation

For specific techniques, delegate to:

  • LLMREI patterns: Load references/llmrei-patterns.md from parent skill
  • Stakeholder simulation: Invoke stakeholder-simulation skill
  • Domain research: Invoke domain-research skill for background

Output Location

Save interview results to:

.requirements/{domain}/interviews/INT-{number}.yaml

Related

  • elicitation-methodology - Parent hub skill
  • stakeholder-simulation - For simulated interviews
  • gap-analysis - Post-interview completeness checking

平台分布

Antigravity

32.45%
按下载量换算46

trae

21.26%
按下载量换算30

windsurf

18.09%
按下载量换算26

Claude Code

13.53%
按下载量换算19

Codex

8.81%
按下载量换算13

Gemini CLI

3.09%
按下载量换算4

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

执行命令

安装流程涉及命令执行,可能通过 npx skills add https://github.com/melodic-software/claude-code-plugins --skill interview-conducting;npx skills add melodic-software/claude-code-plugins --skill "interview-conducting" 联网下载 Skill 或依赖。用户安装前应确认命令来源、仓库内容和执行环境。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills