---
name: feature-prioritisation-matrix
description: "A scored, defensible backlog ranking with the working shown, plus what to commit to, investigate, or decline and a reason you can say out loud. Use when a product manager has a long backlog, more requests than capacity, and needs a ranking they can defend to stakeholders. Do not use for writing the specs or estimating engineering effort in detail. Related topics: Product, Planning, Data."
---

# Feature Prioritisation Matrix

A scored, defensible backlog ranking with the working shown, plus what to commit to, investigate, or decline and a reason you can say out loud.

## When to use

Use this skill when a product manager has a long backlog, more requests than capacity, and needs a ranking they can defend to stakeholders. Do not use it for writing the specs or estimating engineering effort in detail.

## Workflow

1. Ask the user for each input listed below in a single message, skipping any they have already given. Where options are listed, offer them, but accept other answers too.
2. List each candidate with its requester, evidence, and effort, and fix the committed items first.
3. Score reach, impact, confidence, and effort for each item and write down the reasoning for every score.
4. Mark low-confidence items and name the cheapest evidence that would raise confidence.
5. Pull out quick wins that cost little enough to do now.
6. Fit the ranked list to capacity and sort into commit, investigate, and decline with a sayable reason for each.

## Inputs

- **The list** (longer free text)
- **Evidence behind each** (longer free text)
- **Rough effort** (longer free text)
- **What the business wants this quarter** (longer free text)
- **Capacity** (longer free text)
- **Already committed** (longer free text)

## Output

A scoring table with the working, then three lists (commit, investigate, decline) each with a one-sentence reason, plus a quick-wins list.

## Prompt template

Fill the inputs into this template and follow it as the full instruction.

### Backlog Prioritisation

Prioritise the backlog below.

- The list: {{The list}}
- Evidence behind each: {{Evidence behind each}}
- Rough effort: {{Rough effort}}
- What the business wants this quarter: {{What the business wants this quarter}}
- Capacity: {{Capacity}}
- Already committed: {{Already committed}}

Score each item on reach, impact, confidence, and effort, and show the working so people argue with the inputs rather than the ranking.

Be explicit where confidence is low. The loudest requests often score worst here, and that is the useful part. Separate out anything cheap enough to just do. Then say what to commit to within capacity, what needs investigating first, and what to decline, with a reason I can say to the person who asked.

## Pitfalls

- Scoring impact without evidence, so the loudest requester wins.
- Ignoring committed work, which makes the plan exceed capacity on day one.
- Declining with no reason the requester can accept.
