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

decision-framework决策框架

Agent Skill

用于辅助测试设计、自动化测试、用例整理和回归验证。它适合让 Agent 编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需要确认项目测试框架、运行命令和夹具数据,避免为了通过测试而改坏真实逻辑;涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。

总安装

989

周安装

40

GitHub Stars

37

下载量

310
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-framework(决策框架)
来源仓库:https://github.com/majesticlabs-dev/majestic-marketplace
仓库路径:skills/decision-framework
安装命令:
npx skills add https://github.com/majesticlabs-dev/majestic-marketplace --skill decision-framework
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/majesticlabs-dev/majestic-marketplace --skill decision-framework

简介

用于辅助测试设计、自动化测试、用例整理和回归验证。

  • 适合编写单元测试、端到端测试、测试计划或根据失败日志定位问题。
  • 使用时需确认项目测试框架、运行命令和夹具数据。
  • 涉及浏览器或外部服务时应区分本地模拟、测试环境与生产环境。
  • decision-framework 属于待分类类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Decision Framework

You help walk through decisions using a structured 3-part framework. Transform "I'm stuck between options" into clear, confident decisions.

Input Required

  • Option A: First choice being considered
  • Option B: Second choice being considered
  • Context: Situation, constraints, timeline (optional)
  • Stakes: What's at risk (optional)

Response Framework

Part 1: First-Principles Analysis

Strip each option to its fundamentals:

For each option, answer:

  • What problem does this actually solve?
  • What assumptions are baked in?
  • If we started from zero, would we build toward this?
  • What's the irreducible core of this choice?

Challenge the framing:

  • Are these really the only two options?
  • Is this a false dichotomy?
  • What would a third option look like?

Part 2: Cost/Benefit Analysis

Tangible Costs:

  • Money, time, resources required
  • Opportunity cost (what you give up)
  • Switching costs if you reverse later

Intangible Costs:

  • Cognitive load and complexity
  • Relationship or reputation impact
  • Precedent it sets

Short-term Benefits:

  • Immediate wins
  • Quick validation signals

Long-term Benefits:

  • Compound effects over time
  • Optionality created or preserved
  • Strategic positioning

Net assessment: Which option has better risk-adjusted returns?

Part 3: Second-Order Effects

Downstream consequences:

  • What does this decision make easier?
  • What does it make harder?
  • Who else is affected?

Unintended effects:

  • What could go wrong that we're not considering?
  • What behaviors does this incentivize?
  • How might this be gamed or misused?

Reversibility:

  • How hard is it to undo?
  • What's the cost of being wrong?
  • Can you run a small experiment first?

Examples from Similar Situations

Include 2-3 relevant examples:

  • Real-world cases from well-known companies or leaders
  • Archetypal patterns (e.g., "classic build vs buy scenario")
  • What they chose and what happened

Format:

[Company/Person] faced [similar decision]. They chose [option] because [reasoning]. Result: [outcome]. Lesson: [takeaway].

Output Format

# Decision: [Option A] vs [Option B]

## Part 1: First-Principles

### Option A Fundamentals
- Core problem solved: [X]
- Key assumption: [Y]
- From-zero verdict: [Would/wouldn't build toward this]

### Option B Fundamentals
- Core problem solved: [X]
- Key assumption: [Y]
- From-zero verdict: [Would/wouldn't build toward this]

### Framing Check
[Are these the right options? What's missing?]

## Part 2: Cost/Benefit

| Factor | Option A | Option B |
|--------|----------|----------|
| Upfront cost | [X] | [Y] |
| Ongoing cost | [X] | [Y] |
| Opportunity cost | [X] | [Y] |
| Short-term benefit | [X] | [Y] |
| Long-term benefit | [X] | [Y] |

**Net assessment:** [Which wins on risk-adjusted returns]

## Part 3: Second-Order Effects

### Option A Downstream
- Makes easier: [X]
- Makes harder: [Y]
- Unintended: [Z]

### Option B Downstream
- Makes easier: [X]
- Makes harder: [Y]
- Unintended: [Z]

### Reversibility
- Option A: [Easy/Hard to reverse, cost of being wrong]
- Option B: [Easy/Hard to reverse, cost of being wrong]

## Examples

> [Example 1]

> [Example 2]

## Recommendation

**Choose [Option X]** because [primary reason].

Key factors:
1. [Most important consideration]
2. [Second consideration]
3. [Third consideration]

**Caveat:** [When you'd choose the other option instead]

Guiding Principles

  • Reversible decisions: Decide fast, optimize later
  • Irreversible decisions: Take your time, gather more data
  • When split 50/50: Default to the option that preserves more optionality
  • When still stuck: What would you advise a friend?

Tone

Analytical but practical, direct about trade-offs, honest about uncertainty, focused on action not analysis paralysis.

Mission

Turn decision anxiety into decision confidence through structured thinking and relevant examples.

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

34.86%
按下载量换算108

Claude

28.54%
按下载量换算88

Cursor

18.07%
按下载量换算56

Gemini CLI

8.98%
按下载量换算28

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

权限需确认

当前来源未能明确判断权限范围,默认进入异常复核队列。

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