problem-decomposer

Decomposes large ambiguous problems into work packages, dependencies, and acceptance criteria.

Updated Aug 22, 2026
One-click install
npx skills add https://github.com/JustinChangTW/ai-skills-core --skill problem-decomposer-justinchangtw
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: problem-decomposer
Source: https://github.com/JustinChangTW/ai-skills-core/tree/main/skills/09-software-problem-solving/problem-decomposer
Command: npx skills add https://github.com/JustinChangTW/ai-skills-core --skill problem-decomposer-justinchangtw

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and assets (resource) components.

What problem does it solve? Large, messy, or high-uncertainty problems often stall because teams cannot tell symptoms from root causes or turn analysis into schedulable work. This Skill converts such problems into an executable decomposition report with success criteria, work packages, dependencies, risks, and tracking metrics. ## Core Features & Use Cases - Problem framing and issue trees: Separates symptoms, target gaps, root-cause hypotheses, and countermeasures, then builds issue trees with a consistent classification basis per level. - Framework selection: Chooses among MECE, WBS, systems thinking, OKR, CPM/PERT, and Kanban based on the problem type, with explicit reasoning for the choice. - Execution-ready output: Produces work packages with acceptance criteria, estimates, dependencies, critical path, parallelization strategy, RACI, and PDCA feedback loops. - Use Case: A cross-department data platform project is chaotic and blocked. The Skill classifies it as a delivery-scope problem, applies WBS, and outputs work packages with acceptance criteria, dependencies, critical path, and a weekly tracking cadence. ## Quick Start Ask the assistant to decompose your messy project or recurring problem into an executable report with work packages, dependencies, acceptance criteria, and the first three actions to take.

Frequently Asked Questions about problem-decomposer

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

FAQPage Schema
How do I break down a large messy project into executable tasks?▼

Describe the problem, goal gap, constraints, and deadline, and the Skill classifies the problem type, selects a decomposition framework such as WBS, and outputs work packages with acceptance criteria, dependencies, critical path, and tracking metrics.

What is the difference between an issue tree and a WBS?▼

An issue tree decomposes why a problem occurs, focusing on complete classification and hypothesis validation. A WBS decomposes what must be delivered and by whom, focusing on outputs, dependencies, and acceptance. The Skill keeps these trees separate and only converts validated branches into work packages.

How do I handle a problem that keeps recurring despite fixes?▼

Recurring problems are treated as systemic issues. The Skill maps feedback loops, delays, and leverage points using systems thinking, then converts leverage points into concrete work items with monitoring indicators rather than a linear to-do list.

When should I not use problem decomposition?▼

Skip full decomposition for single bug fixes, straightforward spec writing, simple to-do lists, concept explanations, or diagram-only requests. The Skill explicitly routes those cases to neighboring skills or declines to over-apply heavy frameworks.

How do I plan a research project with high uncertainty?▼

The Skill structures research problems around a Baseline, a proof of concept, evaluation criteria, and Go/No-Go decision gates. It uses three-point estimation to handle uncertainty instead of committing to a single fixed timeline.