decision-synthesis

Convert competing analyses and mapped options into a defensible choice using weighted criteria.

7|2|Updated Mar 5, 2026
One-click install
npx skills add https://github.com/AndurilCode/craftwork --skill decision-synthesis
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: decision-synthesis
Source: https://github.com/AndurilCode/craftwork/tree/main/skills/decision-synthesis
Command: npx skills add https://github.com/AndurilCode/craftwork --skill decision-synthesis

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decision-making stalls when analysis produces many plausible options but no clear, defensible choice; this skill converts criteria and scores into a transparent decision you can act on.

Core Features & Use Cases

  • Clarifies the exact decision by separating what is being decided from how people are evaluating it (horizon, authority, reversibility, and delay costs).
  • Surfaces and compares all options including status quo, hybrids, sequenced plans, and options that were prematurely dismissed.
  • Builds a weighted decision matrix with must-haves and graded want-to-haves, then challenges the result through sensitivity and reasoning checks.
  • Produces an actionable decision output including recommendation, confidence (based on information quality), and regret/minimization guidance for irreversibility.

Quick Start

Use the decision-synthesis skill after your analysis to pick between competing options by weighing explicit criteria and producing a traceable recommendation for the final decision.

Frequently Asked Questions about decision-synthesis

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I make a defensible choice when analysis leaves too many plausible options?

Decision synthesis converts competing analyses into a defensible choice by applying a weighted decision matrix that scores options against must-have and want-to-have criteria, yielding a single traceable recommendation.

What is the best way to handle multi-stakeholder disagreement on decision priorities?

Multi-stakeholder disagreement is resolved by specifying weighted criteria with explicit rationales, allowing stakeholders to score options transparently and validating the outcome through sensitivity and regret minimization checks.

How do I perform a sensitivity analysis on a weighted decision matrix?

Sensitivity analysis validates a weighted decision matrix by challenging the scores and weights to ensure the recommendation holds up, checking if altering priority weights changes the final choice.

When should I use regret minimization checks in decision-making?

Regret minimization checks are used in decision-making when facing irreversibility, helping to evaluate the potential downside of a choice and providing guidance to minimize regret for high-stakes commitments.

How do I separate what is being decided from how people are evaluating it?

You separate what is being decided from evaluation methods by defining the decision scope explicitly, mapping the horizon, authority, reversibility, and delay costs before enumerating and scoring options.

Can I use decision synthesis for scenarios where a rich diagnostic phase produced no winner?

Decision synthesis is specifically suitable for scenarios where a rich diagnostic phase produced no winner, converting mapped options and competing analyses into an actionable, structured recommendation.