Token导航 LogoToken导航TokenDH.com
待分类只读github未标认证来源可访问许可证需确认审计通过

decision-making决策

Agent Skill

decision-making 用于处理 GitHub 仓库、Issue、Pull Request 和代码协作信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要围绕仓库状态、代码变更或协作事项进行整理时使用。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

186

周安装

8

GitHub Stars

2

下载量

65
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:decision-making(决策)
来源仓库:https://github.com/jonatasleon/thinking-router
仓库路径:skills/decision-making
安装命令:
npx skills add https://github.com/jonatasleon/thinking-router --skill decision-making
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/jonatasleon/thinking-router --skill decision-making

简介

专注于选项比较、优先级排序与不确定性下的响应策略。

  • 涵盖后果分析与假设检验,但不处理根本原因诊断。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。
  • 识别决策类型(可逆/不可逆)以匹配适当处理节奏。
  • 适合需要明确行动指引而非探索性分析的决策情境。
  • decision-making 属于待分类类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Decision Making

What this skill does

Use this skill when the main task is choosing what to do, what to do first, or how to act under uncertainty.

This domain covers option comparison, prioritization, consequence analysis, assumption checking, and response style.

When this domain is appropriate

Use it when the user is mainly asking:

  • which option is best
  • what should be prioritized now
  • what kind of decision this is
  • what consequences a decision may create
  • how to move under uncertainty or speed pressure

Do not use it when the real problem is root-cause diagnosis, system mapping, or message drafting.

Routing logic

  • classify decision type first -> frameworks/hard-choice-model.md
  • compare explicit options on shared criteria -> frameworks/decision-matrix.md
  • prioritize by impact vs effort -> frameworks/impact-effort-matrix.md
  • prioritize by urgency vs importance -> frameworks/eisenhower-matrix.md
  • test long-term consequences -> frameworks/second-order-thinking.md
  • check whether conclusions are over-interpreted -> frameworks/ladder-of-inference.md
  • force perspective balance -> frameworks/six-thinking-hats.md
  • decide iteratively in a fast-changing context -> frameworks/ooda-loop.md
  • match response style to context type -> frameworks/cynefin-framework.md
  • set the right speed/quality posture -> frameworks/confidence-determines-speed-vs-quality.md

Framework chaining

  • hard-choice-model.md -> decision-matrix.md when options are comparable and high impact
  • decision-matrix.md -> second-order-thinking.md to stress-test the leading option
  • ladder-of-inference.md -> any recommendation when assumptions seem fragile
  • cynefin-framework.md -> ooda-loop.md when the context is complex or chaotic
  • confidence-determines-speed-vs-quality.md after a choice to set execution pace

Execution policy

Before applying a framework:

  1. State the decision clearly.
  2. Name the options if present.
  3. Separate facts from assumptions.
  4. Choose the minimum framework or sequence needed.
  5. Follow the selected framework file's process exactly.
  6. End with a recommendation, tradeoff summary, and next action.

Output contract

  • Goal:
  • Chosen framework:
  • Why this framework:
  • Known facts:
  • Assumptions:
  • Reasoning:
  • Recommendation:
  • Tradeoffs:
  • Recommended next action:

Framework references

  • frameworks/six-thinking-hats.md
  • frameworks/eisenhower-matrix.md
  • frameworks/second-order-thinking.md
  • frameworks/decision-matrix.md
  • frameworks/impact-effort-matrix.md
  • frameworks/ladder-of-inference.md
  • frameworks/hard-choice-model.md
  • frameworks/ooda-loop.md
  • frameworks/cynefin-framework.md
  • frameworks/confidence-determines-speed-vs-quality.md

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

35.58%
按下载量换算23

Claude

30.15%
按下载量换算20

Cursor

19.7%
按下载量换算13

Gemini CLI

10.6%
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

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。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