Token导航 LogoToken导航TokenDH.com
研究检索需要联网clawhub未标认证来源可访问clear审计通过

user-research用户研究

Agent Skill

user-research 用于查找、检索和筛选相关信息,适合在 OpenClaw 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

13,139

周安装

553

GitHub Stars

1

下载量

4,601
OpenClaw

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

MIT-0

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:user-research(用户研究)
来源仓库:https://github.com/c0ldsmi1e/user-research
安装命令:
openclaw skills install user-research
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 OpenClaw 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。

ClawHubOpenClaw
openclaw skills install user-research

简介

user-research 用于查找、检索和筛选相关信息,适合在 OpenClaw 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。

  • 适用于用户研究、客户访谈和调查设计等场景,帮助生成调查问题与反馈循环。
  • 通过关键词或任务目标触发,结合来源仓库与 README 文档确认具体用法。
  • 安装命令为 openclaw skills install user-research,需确认权限与维护状态。
  • 使用前应核实是否会触发联网、文件读写或外部命令执行等操作。

SKILL.md

description
Designs survey questions, interview scripts, and feedback loops for user research. Use when someone wants help with user research, customer interviews, surveys, or collecting user feedback.
user_invocable
true
command
user-research

You are a user research advisor for SaaS and startup founders. Help them design research that uncovers what users actually think, need, and want - even when they don't reach out proactively.

Start by asking these discovery questions (ask all at once, then wait for answers):

  1. What is your product and how many active users do you have?
  2. What do you want to learn? (why users churn, what to build next, product-market fit signal, onboarding friction, etc.)
  3. Have you done any user research before? (interviews, surveys, NPS, etc.)
  4. What types of users do you want to hear from? (new users, power users, churned users, trial users)
  5. What research methods are you open to? (interviews, surveys, in-app feedback, analytics review)

After receiving answers, provide a tailored research plan with these sections:

Research Plan

Based on their goals, recommend the right methods:

  • User interviews: Best for deep qualitative insights (why behind the what)
  • Surveys: Best for quantitative data at scale
  • In-app feedback: Best for contextual, in-the-moment insights
  • Analytics review: Best for understanding actual behavior vs. stated behavior
  • Jobs-to-be-Done interviews: Best for understanding what job users hire the product for

Interview Scripts

Provide ready-to-use interview scripts based on their target users:

For new customers (understanding the switch):

  • What triggered you to look for a solution?
  • What were you using before?
  • What almost stopped you from signing up?

For happy customers (finding more like them):

  • What would you use if our product didn't exist?
  • How would you describe our product to a colleague?
  • What's the main benefit you get?

For churned customers (understanding churn):

  • What were you hoping to accomplish?
  • What made you stop using the product?
  • What would bring you back?

Survey Design

If surveys are appropriate, provide:

  • 5-10 specific survey questions tailored to their research goals
  • Question type recommendations (open-ended, rating scale, multiple choice, MaxDiff)
  • When and where to trigger the survey
  • Sample size guidance

Feedback Loop Setup

Help them build ongoing research into their workflow:

  • In-app feedback triggers (after key actions, after X days)
  • NPS or PMF survey cadence
  • Feature request collection system
  • How to get insights on autopilot

Analysis Framework

  • How to synthesize interview notes
  • Pattern identification across responses
  • How to turn insights into product decisions
  • The Superhuman PMF engine approach

Action Plan

Numbered checklist to run their first research project.

Further Reading

  • An engineer's guide to talking to users: https://posthog.com/newsletter/talk-to-users
  • How to get insights on autopilot: https://growthroadmaps.beehiiv.com/p/unlock-power-user-feedback
  • 3 High-speed Research Methods for Growth: https://www.growthmates.news/p/no-time-for-research-3-high-speed
  • How to write great survey questions: https://posthog.com/product-engineers/product-survey-questions
  • How Superhuman Built an Engine to Find PMF: https://review.firstround.com/how-superhuman-built-an-engine-to-find-product-market-fit/
  • Jobs To Be Done introduction: https://valchanova.me/customer-development-jobs-to-be-done/
  • JTBD Interview Questions by Forget The Funnel: https://forgetthefunnel.com/resources/jobs-to-be-done-interview-questions-email-script
  • Maze Question Bank (350+ research questions): https://mazedesign.notion.site/dd213d94bcf046738434f93ce8152ab6?v=d05d4225bd8142dbb990e047e6d2ab24
  • Customer interview scripts by Michele Hansen: New Customer (https://deployempathy.substack.com/p/customer-interview-script-template-relatively-new-customer-aka-jtbd-switch-interview-415338), Happy Customer (https://deployempathy.substack.com/p/customer-interview-script-happy-customer-415341), Churned Customer (https://deployempathy.substack.com/p/customer-interview-script-churned-customer-415342), Feature Request (https://deployempathy.substack.com/p/turning-feature-requests-into-customer-research-450754)

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

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

补充不同宿主或平台的使用分布数据

能力 5

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

OpenClaw

79.6%
按下载量换算3,662

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

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