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

decision-synthesis决策综合

Agent Skill

decision-synthesis 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

465

周安装

19

GitHub Stars

6

下载量

149
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-synthesis(决策综合)
来源仓库:https://github.com/andurilcode/skills
仓库路径:skills/decision-synthesis
安装命令:
npx skills add https://github.com/andurilcode/skills --skill decision-synthesis
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/andurilcode/skills --skill decision-synthesis

简介

在分析完成后收敛生成可辩护且可追溯的最终决策。

  • 整合系统思维、根因分析等多框架前期成果形成选择。
  • 最大化给定信息下的推理质量,保持透明以便学习改进。
  • 适用于已完成可能性探索阶段,需做出明确取舍的情形。
  • decision-synthesis 属于开发类 Skill,可作为该场景下的辅助能力补充。

SKILL.md

Decision Synthesis

Core principle: Analysis produces options and criteria. Synthesis produces a decision. Most frameworks diverge — generate possibilities, map complexity. This skill converges: makes a defensible, traceable choice. A good decision process maximizes reasoning quality given available information and is transparent enough to learn from.


When to Use

After other frameworks have done their work — Systems Thinking mapped structure, 5 Whys found root causes, Scenario Planning produced futures, Red Teaming attacked options, Stakeholder Mapping identified alignment needs. Now: a rich picture, multiple options, time to land.


The Core Process

Step 1: Clarify What's Being Decided

  • Exact choice?
  • Decision horizon (reversible 3 months? irreversible?)?
  • Final authority?
  • Cost of delay?

Many processes fail because people are evaluating different questions without realizing it.

Step 2: Surface All Options

List every viable option, including:

  • Status quo (always an option)
  • Hybrid approaches
  • Sequenced approaches (do A now, revisit B in 6 months)
  • Options dismissed early but worth a formal look

Step 3: Define Criteria

  • Must-haves (binary — failing = eliminated)
  • Want-to-haves (graded — options compared)

Good criteria: specific enough to score ("error rate < 1%"), independent (no double-counting), tied to actual goal not proxies.

Step 4: Weight the Criteria

Distribute 100 points. The allocation is the conversation — exposes hidden disagreements between stakeholders.

Step 5: Score the Options

Score each option × criterion 1–5 (or 1–10) with explicit reasoning. Scores without reasoning can't be challenged.

Step 6: Compute and Challenge

Weighted scores = signal, not verdict:

  • Top scorer match intuition? If not, why?
  • Which criteria drive the result? Right ones?
  • Swap top-two weights — does the answer change?
  • Comfortable defending this to a critic?

Output Format

Decision Statement

  • Decision: [Exact choice]
  • Horizon: [Reversible / Partially / Irreversible]
  • Decider: [Authority]
  • Deadline: [When resolved]

Options

#OptionBrief description
1[Name][One line]

Criteria & Weights

CriterionTypeWeightRationale
[C1]Must-have[Why binary]
[C2]Want-to-have35[Why this weight]
[C3]Want-to-have25
100

Scoring Matrix

OptionC1C2 (×35)C3 (×25)Weighted Total
APass4 → 1403 → 75X
BPass2 → 705 → 125Y
CFailEliminated

Recommendation

  • Recommended: [Name]
  • Primary reason: [1–2 criteria driving result]
  • Main trade-off: [What it sacrifices]
  • Confidence: [High/Med/Low — based on info quality, not preference strength]

Sensitivity Check

  • If [top criterion] changes weight, does answer change?
  • Which assumption, if wrong, most undermines this?
  • What new info would re-open the decision?

Reversibility & Regret

  • Can it be undone? At what cost?
  • Regret minimization: which choice produces least regret if situation shifts?
  • Low confidence + irreversible → flag explicitly before committing.

Decision Traps

  • False consensus: Everyone nods but criteria weights were never explicit — different people solving different things.
  • Analysis paralysis: More analysis rarely resolves value disagreements. Name the disagreement and call it.
  • Criteria inflation: More criteria adds noise, not signal. Keep the list short and honest.
  • Anchoring on first option: Evaluate all options in parallel, not sequentially.
  • Score laundering: Working backwards from a preferred conclusion. The matrix is a thinking tool, not a legitimacy machine.

Thinking Triggers

  • *"If I decided alone, no politics, what would I choose?"*
  • *"Are we weighting what matters or what's easy to measure?"*
  • *"Is there a hybrid we haven't named?"*
  • *"What would a regret minimizer choose? A risk minimizer? A maximizer?"*
  • *"Are we delaying because we need information, or because we don't want to own the decision?"*

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

35.06%
按下载量换算52

Claude

28.7%
按下载量换算43

Cursor

18.56%
按下载量换算28

Gemini CLI

9.31%
按下载量换算14

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