prioritization

Rank product features, research experiments, and release scope using RICE-A, ICE, and MoSCoW frameworks.

1|Updated May 6, 2026
One-click install
npx skills add https://github.com/jacob-balslev/skill-graph --skill prioritization-jacob-balslev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: prioritization
Source: https://github.com/jacob-balslev/skill-graph/tree/main/marketplace/skills/prioritization
Command: npx skills add https://github.com/jacob-balslev/skill-graph --skill prioritization-jacob-balslev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It prevents AI engineering teams from picking the wrong work by giving practical frameworks to rank backlog items, experiments, and release scope—especially when research uncertainty would otherwise distort decisions.

Core Features & Use Cases

  • RICE-A product feature scoring: prioritizes user-facing work while explicitly penalizing high ambiguity so experimental ideas do not outrank proven value too early (e.g., deciding what feature to build next when multiple candidates exist).
  • ICE research prioritization: ranks discovery-phase experiments using impact, confidence, and ease to identify the fastest path to a working approach (e.g., choosing which 10 experiments to run first).
  • MoSCoW MVP/Release scoping: defines what must ship versus what can wait to reduce accuracy creep and scope drift (e.g., setting Must-Have quality thresholds for a milestone).

Quick Start

Use prioritization to decide which backlog features to fund next by scoring candidates with RICE-A for product work and switching to ICE when you are still validating uncertain research.

Frequently Asked Questions about prioritization

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

FAQPage Schema
How do I prioritize backlog features when unsure about their value?

Prioritize backlog features by scoring them with the RICE-A framework, which evaluates reach, impact, confidence, and effort while explicitly penalizing high ambiguity so uncertain ideas do not outrank proven value.

What is the best way to rank research experiments during model discovery?

Rank research experiments using the ICE framework, which scores discovery-phase ideas based on impact, confidence, and ease to identify the fastest path to a working approach.

How do I set MVP scope and prevent accuracy creep in milestones?

Set MVP scope using MoSCoW-based release scoping to define Must-Have quality thresholds, distinguishing what must ship from what can wait to reduce scope drift and accuracy creep.

When should I switch from ICE to RICE-A for backlog triage?

Switch from ICE to RICE-A when transitioning from validating uncertain research experiments to prioritizing user-facing product features, ensuring ambiguity-aware scoring protects proven value.

Does prioritization work for defining release boundaries across engineering workflows?

Yes, prioritization applies to defining MVP and milestone Must-Have boundaries across engineering workflows, using phase-appropriate framework selection and MoSCoW-based accuracy threshold protection.

What distinguishes RICE-A scoring from standard RICE for product features?

RICE-A distinguishes itself by explicitly penalizing high ambiguity during product feature scoring, preventing experimental ideas from outranking proven value too early in the backlog triage process.