Feature Prioritisation Matrix skill for Claude and Codex
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.
Install it once and Claude or Codex runs it for you. When your request matches, your AI loads the skill, asks for anything it is missing, and works through the template itself. Prefer to fill it in by hand? See the full prompt template.
Download the skill (.zip) · View SKILL.md
When it is used
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.
What it will ask you for
- 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)
How it works
- List each candidate with its requester, evidence, and effort, and fix the committed items first.
- Score reach, impact, confidence, and effort for each item and write down the reasoning for every score.
- Mark low-confidence items and name the cheapest evidence that would raise confidence.
- Pull out quick wins that cost little enough to do now.
- Fit the ranked list to capacity and sort into commit, investigate, and decline with a sayable reason for each.
What you get
A scoring table with the working, then three lists (commit, investigate, decline) each with a one-sentence reason, plus a quick-wins list.
What it watches out for
- 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.
How to install
Claude.ai and the Claude desktop app
- Download the skill .zip.
- Open Settings, then Capabilities, and find Skills.
- Choose Upload skill and select the .zip.
- Ask Claude for help with the task. It loads the skill when your request matches.
Claude Code
- Download the skill .zip.
- Unzip it into ~/.claude/skills/ (or .claude/skills/ inside a project).
- Start a new session. Claude Code loads the skill when your request matches.
Codex
- Download the skill .zip.
- Unzip it into ~/.agents/skills/ (or .agents/skills/ inside a project).
- Codex picks it up on its own. Type $ and the skill name to use it, or just ask for the task.
Cursor
- Download the Cursor rule (.mdc).
- Save it in .cursor/rules/ inside your project.
- Cursor's agent applies the rule when your request matches its description.
AGENTS.md (Codex, Cursor, and other coding agents)
- Copy the AGENTS.md section.
- Paste it into AGENTS.md at the root of your repository, creating the file if needed.
- Coding agents that read AGENTS.md follow it when your request fits.