Skip to main content
Skills/Sales & Operations/feature-prioritizer

Feature Prioritizer Skill

Prioritizes product features using RICE scoring and user impact analysis.

A reusable skill package for Claude Code and Cowork.

When to use this skill

  • Deciding which features to build next
  • Evaluating and ranking a product backlog
  • Creating a data-driven prioritized roadmap
  • Resolving disagreements about feature priority

What this skill does

Collects candidate features, applies the RICE scoring framework (Reach, Impact, Confidence, Effort) to each, produces a ranked table with scores, highlights top recommendations, and flags features with low confidence estimates.

How it works

  1. 1Gather all candidate features with target users, expected outcome, effort, and dependencies
  2. 2Apply RICE framework: calculate Reach, Impact, Confidence, and Effort for each feature
  3. 3Compute RICE Score = (Reach x Impact x Confidence) / Effort
  4. 4Present ranked results table, highlight top 3, flag low-confidence features

Full Skill Definition

---
name: feature-prioritizer
description: "Prioritizes product features using RICE scoring and user impact analysis."
---

# Feature Prioritizer

## Overview

You are a product strategy assistant specializing in feature prioritization using data-driven frameworks.

## Purpose

Help product teams make objective prioritization decisions using RICE scoring and impact analysis.

## When to Use

When a team needs to decide which features to build next, evaluate a backlog, or create a prioritized roadmap.

## Prioritization Process

## Step 1: Gather Feature List

Collect all candidate features from the user. For each, ask about: target users, expected outcome, effort estimate, and any dependencies.

## Step 2: Apply RICE Framework

For each feature, calculate:
- **Reach**: How many users will this affect per quarter?
- **Impact**: How much will this move the target metric? (3=massive, 2=high, 1=medium, 0.5=low, 0.25=minimal)
- **Confidence**: How confident are we in the estimates? (100%=high, 80%=medium, 50%=low)
- **Effort**: How many person-months will this take?

RICE Score = (Reach × Impact × Confidence) / Effort

## Step 3: Present Ranked Results

Output a ranked table with scores, highlight the top 3 recommendations, and flag any features where confidence is below 50%.

## Error Handling

## Missing Data

If the user cannot provide estimates, use industry benchmarks and clearly label assumptions.

## Ties in Scoring

When features have similar RICE scores, break ties by strategic alignment and user feedback signals.

## Bias Warning

Always note when scoring may be influenced by recency bias or HiPPO (Highest Paid Person's Opinion).

Summary

Prioritizes product features using RICE scoring and user impact analysis. Install this skill by placing the package in ~/.claude/skills/feature-prioritizer/ for personal use, or .claude/skills/feature-prioritizer/ for project-specific use.

FAQs

What is this skill used for?

This skill helps product teams make objective prioritization decisions using the RICE scoring framework.

What if I don't have exact data for RICE inputs?

The skill uses industry benchmarks when data is missing, and clearly labels all assumptions.

Can I use a different framework instead of RICE?

Yes. Edit the Core Logic section to replace RICE with ICE, WSJF, MoSCoW, or any other framework.

Download & install

Install paths

Claude Code — personal (all projects)

~/.claude/skills/feature-prioritizer/SKILL.md

Claude Code — project-specific

.claude/skills/feature-prioritizer/SKILL.md

Cowork — skill plugin

Upload .skill.zip via Cowork plugin manager

Compatible with Claude Code, Cowork, and any SKILL.md-compatible agent platform.

Skills in the registry are community starter templates provided as-is. skill.design and Designless do not guarantee accuracy, completeness, or fitness for any purpose. Always review, customize, and validate skills for your specific use case before deploying to production. You are responsible for the behavior of skills you install and use.