Skill · Business & Consulting

Feature Prioritizer (RICE)

Feature Prioritizer (RICE) is a Claude skill for Business & Consulting. Surface honest RICE scores by uncovering biases, anchoring impact to data, and running sensitivity analysis on roadmap assumptions. It costs $8.99 on Agensi. It runs on any paid Claude plan. Part of the StrategistKit catalog of 190+ focused Claude skills.

Category: Business & Consulting
Deliverable: 1 .skill bundle
Outputs: —
Last updated: 13 Jun 2026

$8.99 One-time · lifetime updates

Become a member to fetch

10 credits — included with a membership (30 credits/mo).

Prefer a one-time purchase, without joining?

Buy once on Agensi

StrategistKit Affiliate. One-time purchase on Agensi. Payment, delivery and refunds are handled by the marketplace — see their policy for refund terms.

Works in Claude Pro, Team, and Enterprise
Lifetime access to updates
One-time purchase on Agensi. Payment, delivery and refunds are handled by the marketplace — see their policy for refund terms.

Or get a free skill every month. Subscribers get one curated skill, free, every 1st. Pick yours →

Included in Complete Collection 195 skills for $149. View bundle →

Overview

What Feature Prioritizer (RICE) does.

This skill applies the RICE framework in a way that surfaces the advocacy problem before it locks into your roadmap. Rather than accepting numbers at face value, it asks for the reasoning behind each estimate, caps confidence scores by evidence type (anecdote, survey, usage data), and flags when a team's reach or effort estimate is inconsistent with what the data actually supports. After scoring, it runs sensitivity analysis: any ranking that flips on a single soft assumption is flagged as a research task, not a decision.

A typical session starts with a buyer supplying a list of candidate features, the product context, and whatever evidence exists — analytics exports, survey results, support ticket counts, or team gut-feel. The skill walks through scale calibration first, so impact scores mean the same thing across features, then works through reach, effort, and confidence with the buyer's actual evidence as the constraint.

Sample output excerpt for a feature ranked second after bias correction: 'CSV Export — RICE: 34. Reach adjusted from 8,000 (advocate estimate) to 5,200 (active exporters in last 90 days, analytics). Confidence capped at 70% (survey only, no behavioral data). Flip condition: if effort drops below 1.5 weeks, rank moves to #1. Recommended pre-meeting question: Who owns the effort estimate, and has it been reviewed by the engineer doing the work?'

Who it's for

Product managers and roadmap owners who need to take a scored feature list into a prioritization meeting and defend it — particularly when stakeholder advocacy tends to inflate estimates before the session starts. Also useful for PMs who inherited a RICE spreadsheet and suspect the numbers were reverse-engineered from a desired outcome.

How it works

Three steps. About two minutes.

Install

Add the .skill file to your Claude app. About 10 seconds.

Run it on your work

Invoke the skill and paste in your material.

Apply the output

Review, keep what works, and use it.

In depth

Why a Claude skill beats a prompt template.

A copy-paste prompt runs one static pass and stops. A skill is a bundled program — instructions, examples, and a workflow Claude runs as a unit: it asks for the right input, applies the same pattern every time, and returns the structured outputs above.

FAQ

Common questions.

What input do I need to bring for this to be useful?

A list of candidate features and whatever evidence exists for each — even partial evidence works. The skill calibrates confidence ceilings to your evidence type, so anecdote-only estimates are treated differently from usage data. The more context you provide about your product and team, the more accurate the calibration.

Does the skill produce a ready-to-share artifact, or is it more of a working session?

Both modes are supported. You can get a structured ranked table with assumptions and flip conditions formatted as a document you can paste into a deck, or you can run it as a live working session where it challenges your estimates in real time. Specify which you need when you start.

Will it work for my specific niche or product type?

The skill accepts your product context, team size, and available data sources at runtime and calibrates accordingly. It does not assume a particular industry or feature type — the buyer supplies that context and the scoring adapts to it.

What does the sensitivity analysis actually tell me?

For each feature in the ranked stack, it identifies which single estimate — if revised — would change that feature's position in the ranking. That tells you exactly where to spend pre-meeting research time rather than debating every number in the room.

Does this replace my existing RICE spreadsheet?

No. It works alongside whatever format you use. The skill produces scored output and a list of questions and assumptions; you carry that back into your spreadsheet or planning tool. It does not connect to external tools directly.