September 2026 · 9 min read · 31 skills, free

AI for Product Managers: 31 Claude Skills to Decide What to Build

First this week's requests: the log, the question behind each ask, the no that holds. Then direction — vision, strategy, north star, OKRs, roadmap. Then customers, the written spec, the decision that sticks, launch, and the review two weeks after.

01What these skills are

The whole product manager's job, from roadmap to launch, as installable Claude skills

This is AI for product management, built for the product managers who carry it: Claude drafts the prioritisation, the roadmap, the PRD and the review, and the customer conversations and the call stay yours.

The pack follows the product job in seven stages, from this week's requests to the review after launch.

The red line: real customers are not optional. Claude drafts the documents, the team talks to users, and a named person makes the call.

Each skill is one method or one artifact, with a fixed output template and the next skill to run. It works from what you paste, with no connector to install.

Nothing here scores, ranks or profiles people. The skills score requests, options, risks and assumptions.

Download all 31 skills

One zip: ready-to-install skill zips, readable SKILL.md files, and the evidence notes behind every method. Free, no signup. The same 31 skills live in our open repo, if you would rather read them before you install them.

Download the zip Browse on GitHub

Install in Claude Code

Two lines, and every skill in the pack loads at once.

/plugin marketplace add polar-bear-org/claude-skills
/plugin install ai-for-product-management-pack@polar-bear-skills

Using Claude on the web instead? Download the zip above and upload each skill from its install folder under Customize → Skills.

02The catalog

The 31 skills you get

The set follows the product job, in seven stages: prioritise and say no, set direction, discover, define, decide and align, launch, and measure and learn.

1 · Prioritise and say no

Feature Request Triage

Use when: Sales promised it, a big client wants it, the CEO forwarded it, all this week
Output: Request log, why-behind-it questions, build / later / no sort, reply drafts

Cost of Delay

Use when: Everything is urgent and you need a no that holds
Output: Urgency profiles, CD3 order, “yes, if” options, reply to the asker

RICE Prioritization

Use when: 40 requests, room for 5, and the loudest voice keeps winning
Output: Scored backlog, confidence notes, out-of-order exceptions, cut list

MoSCoW Prioritization

Use when: The date is fixed and scope has to give
Output: Must / Should / Could / Won't list, Must budget check, Won't-this-time list

Kano Model

Use when: You need to know which features customers expect and which delight
Output: Paired survey questions, category table per feature, build-first list

2 · Set direction

Product Vision

Use when: The team cannot say in one sentence what it is building toward
Output: Vision statement, vision board (target group, needs, product, business goals)

Product Strategy

Use when: Everything is high priority and leaders set the roadmap by preference
Output: Diagnosis, guiding policy, coherent actions, “we will not” list

North Star Metric

Use when: The team ships a lot and cannot say which number it is moving
Output: North star, 3 to 5 named inputs with definitions, counter-metrics

Product OKRs

Use when: The quarter starts and the goals are a list of features
Output: Quarterly objectives, measurable key results, key-result grading notes

Product Roadmap

Use when: The roadmap is yours until it is run from the CEO's inbox
Output: Now-next-later board, confidence notes, what is not on it, executive version

3 · Discover

Customer Interview Guide

Use when: You have 30 minutes with a customer and cannot waste it on opinions
Output: Screener lines, story-based questions, probes, consent note, notes template

Interview Synthesis

Use when: Five interview transcripts and a PRD due Friday
Output: Affinity clusters, need statements with sources, contradictions, open questions

Jobs to Be Done

Use when: A request arrives with no known job behind it
Output: Job statements, circumstances, forces for and against switching, alternatives

Opportunity Solution Tree

Use when: Discovery keeps getting squeezed and has to fit between sprints
Output: Outcome, opportunity tree, target opportunity, three solution ideas, assumption tests

Assumption Mapping

Use when: The team is about to build on beliefs nobody has checked
Output: Desirability, viability and feasibility assumptions, evidence map, riskiest three

4 · Define

Working Backwards PR/FAQ

Use when: A prototype is already built and nobody wrote down why
Output: One-page press release, customer FAQ, internal FAQ

Prototype Brief

Use when: Leadership saw the AI demo and thinks it ships next week
Output: What it tests, pass line set in advance, what it does not prove, gap-to-production list

PRD Template

Use when: The last spec was read five different ways
Output: Problem, goals, non-goals, requirements, open questions, success measures

Story Mapping

Use when: The backlog is 200 tickets and nobody can see the whole product
Output: User activity backbone, walking skeleton, release slices

User Stories

Use when: Engineers say the requirements are thin but not what is missing
Output: Stories, Given / When / Then criteria, INVEST check, refinement questions

5 · Decide and align

Product Role Charter

Use when: You ship story points, not software, and the week is meetings and tickets
Output: What product owns, what others own, stop-doing list, meeting audit

DACI Decision

Use when: Sign-off never comes, or comes and is reversed next week
Output: Driver, approver, contributors, informed, inputs, decision date

Decision Log

Use when: Settled calls keep coming back as if nobody decided
Output: Dated records (context, decision, status, consequences), reopening rule

Pre-Mortem Analysis

Use when: The launch date was promised before anyone asked what could go wrong
Output: Failure story, reasons list, top risks with owners and signals, go / adjust / stop

6 · Launch

Competitive Analysis

Use when: Sales keeps saying “the competitor has it”
Output: Landscape table, win / loss themes, where you differ, what not to copy

Value Proposition Canvas

Use when: Marketing, sales and product each describe the product differently
Output: Customer profile, value map, fit notes, one message all teams use

Go-to-Market Plan

Use when: The product is ready and sales, support and marketing are not
Output: Launch tier, audiences, positioning line, readiness by team, enablement brief

Release Notes

Use when: Support hears about changes from customers
Output: Customer notes by change type, internal version for support, who is affected

7 · Measure and learn

Success Metrics

Use when: You celebrated a release and still cannot say whether it worked
Output: HEART table (goals, signals, metrics), baseline, target, guardrail

Experiment Design

Use when: Two options, a strong opinion on each side, and enough users to test
Output: Hypothesis, variants, primary metric, guardrails, sample check, decision rule

Post-Launch Review

Use when: Two weeks after launch customers still use the old workflow
Output: Intended versus actual, why, keep / change list, keep, fix or remove call

03How to use it

Pick the workflow that matches your week

No fixed order. Bring one real thing from the week and open the skill that matches what hurts. When one skill finishes, it names the next.

Prioritise the week

Sales, support and the CEO all want something, this week.

Feature Request Triage
RICE Prioritization
Product Roadmap

Set direction

A no only holds when there is a direction to say it against.

Product Vision
Product Strategy
North Star Metric
Product OKRs

Hear customers

You have interviews to run, or transcripts nobody has read.

Customer Interview Guide
Interview Synthesis
Jobs to Be Done

Test the riskiest assumption

An idea everyone likes and nobody has checked.

Opportunity Solution Tree
Assumption Mapping
Prototype Brief

Write it down

Before anything is promised to anyone.

Working Backwards PR/FAQ
PRD Template
Story Mapping
User Stories
Pre-Mortem Analysis

Decide, and keep it decided

A call that keeps getting reopened.

DACI Decision
Decision Log

Launch and learn

A release is going out, and you want to know what it changed.

Go-to-Market Plan
Release Notes
Success Metrics
Experiment Design
Post-Launch Review

04Setup guide

Install it in five minutes

In Claude Code · two lines

/plugin marketplace add polar-bear-org/claude-skills
/plugin install ai-for-product-management-pack@polar-bear-skills

In Claude.ai or Claude Desktop · seven clicks

Download the pack, then open Settings
Unzip the pack: its skills folder holds all 31 skills. In Claude, click your name at the bottom left, then Settings.
Download the zip
Open Skills and click Add
Under Customize, choose Skills. Click Add, then Upload a skill.
Drop in a skill file
Drag the skill's file into the box, or click to browse. You can add several at once.
Pick the skill from the pack
In the pack folder, open skills, then the skill you want, and select its SKILL.md — pm-feature-request-triage is a good first one.
Check the preview and upload
Claude shows the skill's name and what it does. Click Upload.
Make sure it is switched on
The skill opens on its own page. Its toggle should be on.
Try it in a new chat
Type / and the skill's name, then say what you need.

Then try one

Run pm-feature-request-triage on this week's requests: [paste them here]

Run pm-prd for [feature]. My discovery notes: [paste them here]

Run pm-post-launch-review. Usage export from the launch: [paste it here]

Keep customer names and personal data out: the skills summarise what customers need, they never profile who they are.

Lantern for product managers

Turn your discovery calls into posts about what you're building

Lantern drafts a week of posts from your notes and call transcripts, in your voice. You review them and publish the ones you like.

100 free credits, about ten posts. No card needed.

Try for free

05Quick reference

Where to start

Your situation	Skill to run
Sales promised it, a big client wants it, the CEO forwarded it, all this week	Feature Request Triage
Everything is urgent and you need a no that holds	Cost of Delay
40 requests, room for 5, and the loudest voice keeps winning	RICE Prioritization
The date is fixed and scope has to give	MoSCoW Prioritization
Everything is high priority and leaders set the roadmap by preference	Product Strategy
The roadmap is yours until it is run from the CEO's inbox	Product Roadmap
You have 30 minutes with a customer and cannot waste it on opinions	Customer Interview Guide
Five interview transcripts and a PRD due Friday	Interview Synthesis
Leadership saw the AI demo and thinks it ships next week	Prototype Brief
The last spec was read five different ways	PRD Template
You ship story points, not software, and the week is meetings and tickets	Product Role Charter
Settled calls keep coming back as if nobody decided	Decision Log
Two weeks after launch customers still use the old workflow	Post-Launch Review

06Standards

The quality bar

Every skill in the pack holds the same standard, the one we hold when we run product ourselves:

One method, applied properly: each skill uses the real mechanics of its method — the scales, the grid, the formula, the order of the pass — not a generic “gather, analyse, recommend”
It tells you where it breaks: every skill says when not to use it and what fits instead
Same shape every time: a fixed output template and a short “done when” check before handover
No invented facts: no made-up quotes, customers, numbers or findings — missing data becomes a bracketed placeholder or an open question
Work is scored, people are not: the skills score requests, options, risks and assumptions, never team members or individual users, and customer material is summarised as needs rather than profiled
Every output ends with the decision a named person makes, and by when: nothing sends a reply, a no or a launch message on its own
The red line: real customers are not optional — Claude drafts the documents, the team talks to users, and a named person makes the call

07FAQ

Questions people ask

What is in the AI for Product Managers pack?

31 Claude skills that follow the product job in seven stages: prioritise, set direction, discover, define, decide, launch, and measure. Each skill is one named method or one artifact, with a fixed output template and the next skill to run.

How do I install these Claude skills?

In Claude Code, two lines install all 31 at once. In Claude.ai or Claude Desktop, download the zip, open Settings, Skills, Add, and upload the skills you want. Either way it takes about five minutes.

Do I need Claude Code to use them?

No. The skills work in Claude.ai, Claude Desktop and Claude Code. In the app you upload them yourself; in Claude Code one command installs the whole pack.

Do the skills work with ChatGPT or other assistants?

They are built as Claude Skills, and installing them is a Claude feature. Each one is a plain Markdown file, so you can read it and reuse the method elsewhere, but it will not load and trigger by itself outside Claude.

Will Claude decide what we build?

No. Claude drafts the documents and the analysis. The team talks to real customers, and a named person makes the call. Nothing in the pack scores, ranks or profiles people.

Is the pack free?

Yes. It is free to use inside your company and in client work, and not for resale. There is no signup: the download and the install command are on this page.

08Who made this

Lantern, by Polar Bear

These skills were written by Polar Bear, a people ops consultancy that runs its own company on Claude. The pack is free, and the same skills are open on GitHub.

Lantern is Polar Bear's content workspace. It turns your notes, documents and call transcripts into drafts for LinkedIn and other networks. You review them and publish the ones you like.