Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计通过

ideationideation 搜索

Agent Skill

ideation 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

1,548

周安装

51

GitHub Stars

9

下载量

420
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

3

许可证

MIT

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:ideation(ideation 搜索)
来源仓库:https://github.com/nbbaier/agent-skills
仓库路径:skills/ideation
安装命令:
npx skills add https://github.com/nbbaier/agent-skills --skill ideation
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/nbbaier/agent-skills --skill ideation

简介

用于查找、检索和筛选相关信息。ideation 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

  • 适合根据关键词或任务场景快速定位候选结果。
  • 通过 GitHub 安装,支持 Codex、Claude、Cursor 等宿主。
  • 安装前建议确认权限范围和维护状态。
  • 可能触发联网、命令执行或文件读写操作。

SKILL.md

Ideation

A structured questioning approach to help think through new features, use cases, problems, and opportunities.

How This Works

Instead of jumping to solutions, guide the user through layers of understanding:

  1. Problem/Opportunity Space - What's the real issue or opportunity?
  2. Context & Constraints - What's the environment and limitations?
  3. User & Stakeholder Lens - Who's affected and how?
  4. Solution Exploration - What are the options?
  5. Validation & Risks - How do we know it works?

Questioning Framework

Layer 1: Surface Understanding

Start here to clarify what they're actually trying to do:

  • "What triggered this idea? What happened that made you think of this?"
  • "In one sentence, what problem are you trying to solve?"
  • "Who would benefit if this existed?"
  • "What does success look like?"

Layer 2: Problem Depth

Dig into the mechanics of the problem:

  • "Why does this problem exist? What's the root cause?"
  • "How are people solving this today? What's wrong with that approach?"
  • "What's the cost of not solving this? (time, money, frustration)"
  • "Is this a hair-on-fire problem or a nice-to-have?"

Layer 3: Context & Constraints

Understand the boundaries:

  • "What technical constraints exist? (stack, integrations, performance)"
  • "What resources are available? (time, team, budget)"
  • "What's non-negotiable vs. flexible?"
  • "What have you tried before that didn't work?"

Layer 4: User Perspective

Get specific about who you're building for:

  • "Walk me through the user's current workflow without this solution."
  • "What's the most painful step? Where do they give up?"
  • "What would they say if you asked them about this problem?"
  • "Are there different user segments with different needs?"

Layer 5: Solution Exploration

Now explore options:

  • "What's the simplest version that would still be useful?"
  • "What would the ideal solution look like with no constraints?"
  • "What existing solutions come close? What's missing?"
  • "What are 3 completely different approaches to this?"

Layer 6: Validation & Risk

Stress-test the idea:

  • "How would we know if this is working?"
  • "What could go wrong? What are the biggest risks?"
  • "What assumptions are we making that might be wrong?"
  • "What's the smallest experiment we could run to learn more?"

Process

  1. Listen first - Let them explain the idea before questioning
  2. One question at a time - Don't overwhelm with multiple questions
  3. Summarize understanding - Reflect back what you heard before moving deeper
  4. Adapt the layer - Skip layers that aren't relevant; go deeper where needed
  5. Capture insights - Periodically summarize key discoveries
  6. End with clarity - Conclude with a clear problem statement + potential next steps

Output Artifacts

After the ideation session, offer to create:

  • Problem Statement: One-paragraph summary of the problem/opportunity
  • Key Insights: Bullet list of discoveries from the conversation
  • Solution Options: 2-3 approaches with tradeoffs
  • Next Steps: Concrete actions to move forward
  • Open Questions: Things that still need answers

Example Opening

When the skill is triggered, start with:

"Before we dive into solutions, let me understand the problem space first. What triggered this idea? What's the situation or pain point you're seeing?"

Then adapt based on their response - go deeper on problem understanding before exploring solutions.

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

04

需要参考平台分布和安装热度时

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

OpenCode

29.21%
按下载量换算123

Antigravity

21.02%
按下载量换算88

Claude Code

18.58%
按下载量换算78

Codex

11.82%
按下载量换算50

Gemini CLI

7.96%
按下载量换算33

Cursor

3.56%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。

来源信息

继续浏览同类 Skills