Token导航 LogoToken导航TokenDH.com
研究检索权限需确认github未标认证来源可访问许可证需确认审计通过

interview面试准备

Agent Skill

interview 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。

总安装

235

周安装

10

GitHub Stars

35

下载量

82
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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(面试准备)
来源仓库:https://github.com/kazdenc/builder-skills
仓库路径:skills/interview
安装命令:
npx skills add https://github.com/kazdenc/builder-skills --skill interview
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。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/kazdenc/builder-skills --skill interview

简介

interview 用于查找、检索和筛选相关信息,支持关键词和任务场景定位。

  • 适用于 Codex、Claude、Cursor、Gemini CLI 中的信息快速筛选需求。
  • 通过 npx skills add 命令从 GitHub 仓库安装,需结合原始 README 确认具体用法。
  • 安装前建议确认权限范围、维护状态,以及是否会触发联网或文件读写操作。
  • 该技能当前分类为研究检索,实际功能以来源仓库描述为准。

SKILL.md

User Interviews

This skill operates in two modes. Pick the one that matches what you have.

  • GENERATE — You have a topic or feature area. You need an interview script.
  • ANALYZE — You have a transcript (or notes). You need structured insights.

GENERATE Mode — Build an Interview Script

Structure every interview in three acts:

┌─────────────────────────────────────────┐
│  1. WARM-UP (5 min)                     │  Build rapport, set context
│  2. CORE QUESTIONS (30–40 min)          │  Explore the job, past behavior
│  3. WRAP-UP (5 min)                     │  Open floor, next steps
└─────────────────────────────────────────┘

Warm-Up

Set the participant at ease. Explain there are no wrong answers, you're learning from them, and they can skip anything. Ask one or two easy background questions to get them talking.

Core Questions

Use these question types, in roughly this order:

TypePurposeStarter
ContextUnderstand their world"Walk me through a typical day when you..."
BehavioralSurface real past actions"Tell me about the last time you..."
JTBDUncover the job and switching triggers"What were you trying to accomplish when you decided to..."
ProcessMap their current workflow"What happened next? And after that?"
EmotionalFind pain and delight"How did that make you feel? What was the hardest part?"
MagnitudeGauge importance"How big a deal is that for you? What's at stake?"

Follow every answer with "Why?" or "Can you tell me more about that?" until you reach concrete specifics.

Wrap-Up

Ask "Is there anything I should have asked but didn't?" — this regularly surfaces the most valuable insight of the session. Thank them and explain what happens next.

Good vs Bad Questions

Bad (avoid)Why it failsGood (use instead)
"Would you use a feature that does X?"Hypothetical — people can't predict future behavior"Tell me about the last time you needed to do X."
"Don't you think this is frustrating?"Leading — suggests the answer"How do you feel about that part of the process?"
"Do you like A or B better?"Binary — closes exploration"What matters most to you when you're doing this?"
"How often would you use this?"Speculative frequency"How often did you do this in the past month?"
"Users like you typically want..."Primes agreement"What do you wish were different?"

Output

Produce the script as a numbered list of questions, grouped by section, with follow-up prompts indented beneath each question. Include a short interviewer note at the top covering the research goal, who to recruit, and session logistics.


ANALYZE Mode — Extract Insights from a Transcript

Work through the transcript systematically. Pull out five things:

ExtractWhat to look for
ThemesRecurring topics or patterns across answers
JobsWhat the participant was trying to accomplish (verb + object + clarifier)
NeedsHow they measure success — stated or implied (direction + measure + object)
Pain pointsWhere the current process breaks down, causes frustration, or wastes time
OpportunitiesUnmet needs, workarounds, or moments of high emotional energy

How to work through it

  1. Read the full transcript before highlighting anything.
  2. Tag each meaningful quote with one or more of the five categories above.
  3. Group related quotes into clusters. Name each cluster with a short theme label.
  4. For each cluster, write one insight statement: "[Who] needs to [job] but struggles with [pain] because [root cause]."
  5. Rank opportunities by how often they appear and how strongly participants reacted.

Output

Produce a structured summary with:

  • Research context — who was interviewed, when, about what
  • Top themes — ranked list with supporting quotes
  • Jobs identified — written as proper job statements
  • Key pain points — with severity and frequency indicators
  • Opportunities — specific, actionable, tied back to evidence

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

35.3%
按下载量换算29

Claude

29.34%
按下载量换算24

Cursor

18.36%
按下载量换算15

Gemini CLI

8.35%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills