carte blanche preview

skills / business

prioritization-frameworks

what it does

Reference guide to 9 prioritization frameworks with formulas, when-to-use guidance, and templates — RICE, ICE, Kano, MoSCoW, Opportunity Score, and more. Use when selecting a prioritization method, comparing frameworks like RICE vs ICE, or learning how different prioritization approaches work.

by Pawel Huryn · Pawel Huryn, MIT · version 1 · license MIT

Verified Before and after: 2 models 1 try per case View source Download .zip

Compare the answers

Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1

Same request, same model, once with the skill and once without. Read both and judge for yourself.

“Rank these by our usual score: reach × impact × confidence ÷ effort. Show the scores.”

Source material given with the request

We plan effort in person-months. 1 person-month = 4 person-weeks. Item Reach (users/qtr) Impact Confidence Effort Bulk edit 4,000 1 80% 2 person-months Slack integration 1,500 2 50% 6 person-weeks SSO 600 3 100% 1 person-month Mobile offline 2,500 2 50% 4 person-months Onboarding checklist 5,000 0.5 80% 8 person-weeks
with the skill
Using **Score = Reach × Impact × Confidence ÷ Effort**, with confidence as a decimal and all effort in **person-months**: | Rank | Item | Effort (person-months) | Calculation | Score | |---:|---|---:|---|---:| | 1 | SSO | 1 | 600 × 3 × 1.00 ÷ 1 | **1,800** | | 2 | Bulk edit | 2 | 4,000 × 1 × 0.80 ÷ 2 | **1,600** | | 3 | Slack integration | 1.5 | 1,500 × 2 × 0.50 ÷ 1.5 | **1,000** | | 3 | Onboarding checklist | 2 | 5,000 × 0.5 × 0.80 ÷ 2 | **1,000** | | 5 | Mobile offline | 4 | 2,500 × 2 × 0.50 ÷ 4 | **625** | Conversions: 6 person-weeks = 1.5 person-months; 8 person-weeks = 2 person-months.
without
Using **reach × impact × confidence ÷ effort**, with effort converted to **person-months**: | Rank | Item | Effort (person-months) | Calculation | Score | |---|---|---:|---|---:| | 1 | SSO | 1 | 600 × 3 × 1.00 ÷ 1 | **1,800** | | 2 | Bulk edit | 2 | 4,000 × 1 × 0.80 ÷ 2 | **1,600** | | 3 (tie) | Slack integration | 1.5 | 1,500 × 2 × 0.50 ÷ 1.5 | **1,000** | | 3 (tie) | Onboarding checklist | 2 | 5,000 × 0.5 × 0.80 ÷ 2 | **1,000** | | 5 | Mobile offline | 4 | 2,500 × 2 × 0.50 ÷ 4 | **625** | *Conversions: 6 person-weeks = 1.5 person-months; 8 person-weeks = 2 person-months.*

Answers are shown exactly as the model wrote them, from the first try, and nothing is picked by hand.

The models

2 models

Claude Sonnet 5.5

made by Anthropic

claude-sonnet-5-5 · revision not reported by the provider

1 try per case · tested 3 Nov 2026

GPT-6.1 Sol

made by OpenAI

gpt-6.1-sol · revision not reported by the provider

1 try per case · tested 3 Nov 2026

The tasks

written by Carte Blanche
request-count-list

“Sales gave me the most requested features with counts. Can I just build them in order of request count?”

score-with-mixed-units

“Rank these by our usual score: reach × impact × confidence ÷ effort. Show the scores.”

startup-method-choice

“We're a 4-person startup with about 30 feature ideas in a spreadsheet and a planning meeting on Friday. We have almost no usage data. What's a sensible way to prioritize?”

survey-ranking

“Which of these customer problems should we work on first? We surveyed 200 customers; ratings are averages on a 1-10 scale.”

weighted-matrix

“Leadership has to pick one of these three initiatives. Which should we pick? Show the math.”

Install

Download the .zip and unzip it. Put its files, in a folder named prioritization-frameworks, here:

Claude Code~/.claude/skills/Every project. For one project only, use .claude/skills/ inside it.
Codex~/.agents/skills/Every project. For one repository only, use .agents/skills/ inside it.
Cursor~/.cursor/skills/Cursor also reads the Claude Code and Codex folders above.

Then start a new session and ask for what the skill does. Other agents that read SKILL.md have their own skills folder; check their docs.

Coming after launch: get skills from inside your agent, no download needed.