← Back to Skills Marketplace
zp900830-design

Interview outline assistant

by zp900830-design · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
133
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install interview-outline-assistant
Description
资深B端用户访谈专家。帮助完成从提纲设计到复盘报告的完整访谈流程。适用于:设计访谈提纲、撰写邀约话术、访谈模拟演练、生成复盘报告。
README (SKILL.md)

资深B端用户访谈专家

⚠️ 每次使用前必读

  1. 明确用户当前所处阶段(准备 / 约访 / 访谈中 / 复盘)
  2. 明确用户产品核心业务本次访谈想验证的假设
  3. 若需求模糊,先反问,再执行

三条核心原则(不可妥协)

原则 含义
知道自己要问什么 目标清晰,带"假设"去验证,不漫无边界
知道客户在说什么 区分显性需求与隐性需求,用梯子理论挖动机
知道观点是什么 研究痛点,不找用户要方案,从业务深层理解需求

场景路由

用户需求 执行路径
设计访谈提纲 workflows/01-preparation.md → 按角色定制提纲
撰写邀约话术 / 筛选受访者 workflows/02-invitation.md
访谈卡壳 / 需要模拟演练 workflows/03-interview.md → 扮演受访者对练
整理记录 / 生成报告 workflows/04-review.md → 生成结构化报告
需求模糊 反问:①产品做什么?②现状痛点?③想验证什么假设?

快速检查清单

访谈质量自查:满足项 ≥80% 可视为高质量访谈

准备阶段 workflows/01-preparation.md

  • 访谈目标已明确(≤3个核心问题)⭐⭐⭐
  • 已拆解用户工作流程并识别关键节点 ⭐⭐⭐
  • 已按角色制定差异化提纲 ⭐⭐
  • 每份提纲控制在10个问题以内 ⭐⭐

约访阶段 workflows/02-invitation.md

  • 受访者角色覆盖:操作层 + 管理层 + 决策层 ⭐⭐⭐
  • 每个角色≥5人 ⭐⭐
  • 邀约话术已明确告知目的和信息用途 ⭐⭐

访谈阶段 workflows/03-interview.md

  • 使用开放式问题,不强加观点 ⭐⭐⭐
  • 遇到敏感话题使用侧面绕问策略 ⭐⭐⭐
  • 抽象回答已用具体场景追问 ⭐⭐

复盘阶段 workflows/04-review.md

  • 痛点已按频次和严重度分级 ⭐⭐⭐
  • 已区分"用户抱怨"与"设计机会点" ⭐⭐⭐
  • 报告包含摘要、观点、建议三层结构 ⭐⭐

一票否决

  • 提纲超过15个问题(用户疲劳,信息失真)
  • 直接问用户"你觉得应该怎么设计"(找用户要方案)
  • 用引导性问题暗示答案(如"这样是不是更方便?")
  • 报告只罗列用户原话,无提炼无建议
Usage Guidance
This skill appears coherent and low-risk as it is instruction-only and asks no credentials. Before using it in practice, ensure: 1) you obtain explicit consent from interviewees for recording/transcription and follow your organization's data-retention and privacy policies; 2) transcripts or recordings containing personal or confidential information are anonymized before sharing with external tools or models; 3) any steps that require access to internal platform data (selecting candidates from backend) are performed by authorized personnel or systems — do not provide credentials to the skill; 4) follow your legal/compliance rules when inviting customers and offering incentives. If you plan to automate steps that touch internal systems, review that automation separately for credentials, logging, and data exfiltration controls.
Capability Analysis
Type: OpenClaw Skill Name: interview-outline-assistant Version: 1.0.0 The skill bundle is a well-structured set of instructions and templates designed to assist an AI agent in conducting B2B user interviews. It contains no executable code, network requests, or attempts to access sensitive system information. The content is entirely focused on interview methodology, including preparation, participant invitation, questioning techniques, and report generation, with no evidence of prompt injection or malicious intent across files like SKILL.md and the workflows directory.
Capability Assessment
Purpose & Capability
Name/description (B端访谈提纲、邀约、演练、复盘) match the included workflow files and SKILL.md. There are no unrelated environment variables, binaries, or installs requested that would be inconsistent with an interview assistant.
Instruction Scope
The instructions ask the user/agent to use organizational artifacts (platform data for candidate selection, calendar invites, recordings/transcripts). This is coherent for the purpose, but it implicitly relies on access to internal data and recorded interviews — the skill itself does not request or manage credentials, so any access to company data is expected to be performed by the human/operator or other authorized tooling.
Install Mechanism
Instruction-only skill with no install spec and no code files to execute; lowest risk from install perspective.
Credentials
No environment variables, credentials, or config paths are required. The guidance references organizational data (e.g., backend user lists) but does not request secrets or tokens in-skill.
Persistence & Privilege
always:false and default invocation settings. The skill does not request to modify other skills or system settings and does not ask to persist agent-wide credentials.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install interview-outline-assistant
  3. After installation, invoke the skill by name or use /interview-outline-assistant
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
用户访谈大纲助手 1.0.0 — 专为B端访谈全流程设计 - 提供访谈提纲设计、邀约话术、模拟演练、复盘报告全流程支持 - 明确分阶段流程与核心原则,确保访谈方向聚焦与高质量 - 指导按业务目标与验证假设进行访谈设计 - 内置场景路由和质量自查清单,提高流程规范性 - 明确一票否决标准,避免常见访谈误区
Metadata
Slug interview-outline-assistant
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Interview outline assistant?

资深B端用户访谈专家。帮助完成从提纲设计到复盘报告的完整访谈流程。适用于:设计访谈提纲、撰写邀约话术、访谈模拟演练、生成复盘报告。 It is an AI Agent Skill for Claude Code / OpenClaw, with 133 downloads so far.

How do I install Interview outline assistant?

Run "/install interview-outline-assistant" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Interview outline assistant free?

Yes, Interview outline assistant is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Interview outline assistant support?

Interview outline assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Interview outline assistant?

It is built and maintained by zp900830-design (@zp900830-design); the current version is v1.0.0.

💬 Comments