Token导航 LogoToken导航

Agent Skill · 研究检索

questions-insight(问题洞察力)

questions-insight 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。

questions-insight 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,权限为调用外部服务;许可证为 MIT,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 60,042。

总安装 374周安装 15GitHub Stars 公开资料未说明下载 121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:questions-insight(问题洞察力)
来源仓库:https://github.com/pentaxis93/aiandi
仓库路径:skills/questions-insight
安装命令:
npx skills add pentaxis93/aiandi --skill "questions-insight"
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。

AgentSkills.tonpx skills
npx skills add pentaxis93/aiandi --skill "questions-insight"

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。

提供问题洞察力支持,识别潜在假设、偏见与认知盲区。适用于批判性思维训练、学术写作或决策分析等研究检索场景。可在 Cursor、Gemini CLI 中调用以辅助评估问题质量与回答可靠性。使用前应明确分析维度,避免过度解读或无依据质疑。建议与其他技能组合使用,形成完整的问题分析与解决闭环。

来源仓库内路径:skills/questions-insight

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 pentaxis93/aiandi --skill "questions-insight";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

    它需要调用外部服务,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

questions-insight 怎么安装?

在终端执行 npx skills add pentaxis93/aiandi --skill "questions-insight"。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

questions-insight 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。

questions-insight 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

questions-insight 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。

questions-insight 用的人多吗?

公开数据是累计安装 374 次,近一周安装 15 次,下载 121 次。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。

questions-insight 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。
  • 许可证明确为 MIT,商用和分发边界好判断。

先想清楚的地方

  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。

不太适合

  • 要求有安全扫描结论才肯安装的团队。
  • 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
questions-insight

问题洞察力 · 本页

374—调用外部服务MIT未收录

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

name
questions-insight
description
Question template for Insight stories ('I discovered X while doing Y'). Arc: Routine → Disruption → Recognition → Understanding → Application. Use with question-design skill.

Insight Story Questions

Story type: "I discovered X while doing Y" Arc: Routine → Disruption → Recognition → Understanding → Application


The Shape

Insight stories capture the moment when something clicked - when a pattern became visible that was always there but unseen. The reader experiences the discovery alongside the teller.

What makes it work: The contrast between "before I saw it" and "after I saw it." The insight must feel both surprising AND inevitable in retrospect.


Question Sequence

Opening: The Normal

*Establish what was routine, unremarkable.*

  • "What was normal for you before this happened?"
  • "Walk me through what you were doing when this started."
  • "What were you paying attention to? What weren't you?"

Disruption: The Anomaly

*Something didn't fit the pattern.*

  • "When did you first notice something was different?"
  • "What caught your attention?"
  • "What didn't fit your expectations?"
  • "Was it a single moment or a series of small things?"

Recognition: Seeing the Pattern

*The moment of seeing.*

  • "When did you realize this was significant?"
  • "What did you suddenly see that you hadn't before?"
  • "How did you know this wasn't just noise?"
  • "What connected in that moment?"

Understanding: Making Sense

*Integrating the insight.*

  • "How did you make sense of what you were seeing?"
  • "What did this explain that hadn't made sense before?"
  • "Did this connect to other things you knew?"
  • "How did you test whether you were right?"

Application: Living With It

*How the insight changed things.*

  • "How has this changed how you see [domain]?"
  • "What do you do differently now?"
  • "Where else does this pattern show up?"
  • "How do you explain this to others?"

Tacit Knowledge Triggers (Insight-Specific)

  • "What were you NOT looking for when you found this?"
  • "Why do you think others miss this?"
  • "What made you ready to see it?"
  • "What would have happened if you'd dismissed it?"
  • "Is there a simpler explanation you considered and rejected?"

Walking Adaptation

First quarter: The Normal (context setting, low cognitive load) Second quarter: Disruption + Recognition (the discovery - may need pauses) Third quarter: Understanding (sense-making, synthesis) Final quarter: Application (how it lives now, what transfers)

The Recognition moment often benefits from physical movement - insights can re-emerge when the body is in motion.


Example: Ceremonial Magic Maps to Engineering

Opening: "What was your software development practice like before you made this connection?" Disruption: "When did you first notice the parallel between ceremonial structure and engineering process?" Recognition: "What clicked? What made you think 'this isn't coincidence'?" Understanding: "How did you test the mapping? Where did it hold, where did it break?" Application: "How has this changed how you approach a coding session?"


*The insight story shows what was always there, waiting to be seen.*

平台分布

mcpjam

27.38%
按下载量换算33

Claude Code

21.47%
按下载量换算26

windsurf

17.24%
按下载量换算21

zencoder

11.31%
按下载量换算14

crush

7.72%
按下载量换算9

cline

3.9%
按下载量换算5

安全审计

暂无安全审计结果可展示。

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

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。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills