October 2026 · 9 min read · 36 skills, free

Claude for AI Product Managers: 36 Claude Skills to Test an AI Feature Before It Ships

It starts before the model: does this need AI at all, and which mistakes would matter. Then the spec written as tests, the prompt and the agent's limits, evals built from real outputs, red teaming and launch gates, and the weekly transcript read that keeps it honest.

01What these skills are

An AI feature, from the first idea to the weekly review after launch, as installable Claude skills

This is AI product management that starts from the mistakes the feature can make, not the demo: Claude drafts the spec, the evals and the briefs, and a person who knows the domain makes the call.

The skills follow the job in seven stages, from asking whether a model is needed at all to what it costs and how to explain it to leaders.

The red line: Claude drafts the tests, never the verdict. It does not set the error your users can live with, sign off a launch, or report a score it did not see run on real outputs, and a person who knows the domain reads real transcripts every week.

Each skill is one named method or one artifact you walk away with, and ends with the decision a named person makes. It works from what you paste, with no eval platform to buy.

Legal, privacy and regulatory points become questions for a qualified adviser rather than answers. The sources behind each method are in resources/evidence-and- sources.md.

Download all 36 skills

One zip: ready-to-install skill zips, readable SKILL.md files, and the sources behind every method. Free, no signup. The same 36 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-product-managers-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 36 skills you get

The set follows the work, in seven stages: deciding if AI fits, speccing it, briefing the model and the agent, building the evals, shipping it safely, running and improving it, then cost, price and explaining it.

1 · Decide if AI fits

AI Use Case Canvas

Use when: Someone wants “an AI feature” and nobody has said what decision it improves
Output: The canvas — prediction, judgment, action, outcome, input, feedback — a simpler-fix check, a data check, and a verdict

AI Failure Modes Map

Use when: Leaders expect it to be right every time and you need to show which mistakes matter
Output: A failure list per output, the cost of a false yes against a false no, severity and detection, a graceful failure, and the tolerable rate left blank for you

Workflow or Agent Decision

Use when: The team wants an agent and nobody asked whether a fixed workflow would do
Output: The candidate patterns, their cost, latency and failure trade-offs, the simplest pattern that passes, and the trigger for the next step up

AI Model Selection

Use when: You must justify the model tier and the bill before engineering commits
Output: A side-by-side test plan on real inputs, a quality, latency and cost table per tier, a pick per task, and a re-check date

AI Prototype Brief

Use when: Leadership saw a slick AI demo and thinks production is just more prompts
Output: What the demo tests, a pass line set in advance, a cherry-picked input check, and the gap-to-production list

2 · Spec it

AI PRD

Use when: The AI feature spec reads like a normal PRD and nobody can test it
Output: The problem, the inputs the model sees, the outputs, a behavior summary, fallbacks, data needs, the release bar, and the open questions

AI Success Criteria

Use when: The team says “make it good” and nobody can say what good means
Output: Measurable criteria per dimension, today's baseline, a target set by a named person, and how each one is measured

AI Behavior Contract

Use when: “It should be helpful and safe” is the whole spec
Output: Must, must-never and when-unsure lines written as Given-When-Then cases, a pass rate over repeated runs, and the guardrails

Human-in-the-Loop Design

Use when: A wrong move is costly and nobody has drawn where a person steps in
Output: The approve, edit and take-over points, their triggers, the handoff message, a response time a person can actually meet, and the log

AI Data Privacy Brief

Use when: Legal asks what user data reaches the model and nobody has drawn it
Output: The data flow from user to model to logs, the personal data in prompts, retention, region, and the questions for legal

3 · Brief the model and the agent

System Prompt Brief

Use when: The prompt grew by patches and nobody knows which line does what
Output: Role, audience, task, rules, examples, output format, refusals and handoffs, plus a critique of the prompt you have now

Context Engineering Brief

Use when: Answers are wrong because the model read stale or irrelevant documents
Output: The knowledge sources and their owners, freshness rules, what to leave out, retrieval spot checks, and a context budget

Agent Spec

Use when: The agent can act on its own and nobody has written where it must stop
Output: The goal, the allowed tools, permissions, stop conditions, a spend budget, the approval points, and the never-alone list

Tool Descriptions

Use when: The agent picks the wrong tool or misreads what a tool returns
Output: Per tool: name, purpose, inputs, outputs and error messages, plus namespacing, an overlap check, and three test tasks

4 · Build the evals

Error Analysis

Use when: Quality is judged by vibes and the dashboard tracks scores that match no real problem
Output: Notes on real outputs, open codes, failure types grouped, counts per type, and the three to fix first

Golden Dataset

Use when: Nobody can tell if a new prompt helped the real workflow or only the demo
Output: 20 to 50 real cases with their expected outcomes, coverage by failure type, the source and version, and add-and-retire rules

Synthetic Test Data

Use when: Real cases are too thin or too sensitive to cover the edge cases
Output: Generated cases for coverage gaps only, each marked synthetic, checked by a person, and kept out of the headline score

Eval Rubric

Use when: Scores on a 1 to 5 scale move and nobody knows what changed
Output: One pass-or-fail check per failure type, a grader per check, a pass and a fail example, and the blockers

LLM-as-a-Judge Prompt

Use when: You want automated grading but cannot prove the judge agrees with your experts
Output: A judge prompt for one failure type, a labelled set, agreement measured on a held-out split, and bias checks

AI Eval Plan

Use when: Everyone agrees evals matter and nobody owns them
Output: The capability and regression suites, when each one runs, what blocks a release, and the named owner of quality

5 · Ship it safely

AI Red Teaming Plan

Use when: An agent will read emails, tickets or web pages written by strangers
Output: Attack cases by risk class, who runs them, the pass line, and the fixes due before launch

AI UX Review

Use when: Users rephrase, give up or leave, and the design never said what happens when it is wrong
Output: 18 interaction guidelines checked by phase, an AI disclosure check, the correction and handoff paths, and the fixes ranked

AI Impact Assessment

Use when: A customer, a regulator or your legal team asks for an impact assessment
Output: Who is affected, intended use and misuse, the data, oversight, mitigations, the residual risk owner, and the questions for an adviser

AI Risk Register

Use when: Legal and security ask for the risks and you have a list of worries
Output: Cause, event and effect risks mapped to Map, Measure and Manage, each with an owner, a trigger and a response

Questions for Legal

Use when: You need legal sign-off and do not know what to ask or what to bring
Output: The questions for the legal and privacy team by topic, with the facts attached — it asks, never answers

AI Launch Checklist

Use when: Launch is close, the first gate has not opened, and nobody has checked the boring things
Output: A go-live list with an owner per line, from evals passed as run to the rollback rehearsed

AI Launch Gates

Use when: The feature is ready to go out and nobody has written what would stop it
Output: The stages, the eval and live numbers per gate, the kill criteria, the rollback path, and who signs each gate

6 · Run and improve

Weekly AI Quality Review

Use when: It worked for weeks, then broke, and nobody had been reading the transcripts
Output: A transcript sample plan, the review notes, the new failure types, the cases added to the golden dataset, and the decisions

AI Feedback Signals

Use when: Users rarely rate answers and you cannot see what they think
Output: A signal map — accept, edit, retry, rephrase, abandon, escalate, rating — what to log, a weekly readout, and the review triggers

Prompt Regression Test

Use when: A prompt edit fixed one case and quietly broke another
Output: The change note, the cases to re-run, before and after per failure type, and a ship-or-hold for a named person

Model Migration Plan

Use when: The model you depend on has a retirement date
Output: The deadline, the breaking changes, the eval rerun, the cost difference, the behavior diffs to read, and the rollout and fallback

AI Incident Response Plan

Use when: The AI told a customer something wrong and it is spreading
Output: Severity levels, containment, the customer correction, an evidence timeline, the fix carried into the golden dataset, and a blameless review

7 · Cost, price and explain

AI Unit Economics

Use when: The feature passed every eval and finance still wants to stop it
Output: Cost per call, per task and per successful outcome, the heavy-user case, the caching and batch levers, and what it costs today

AI Usage and Pricing Test

Use when: You need run cost and price options before you have real usage
Output: A small real-task test, a usage estimate at light, normal and heavy use, the price options to test, and what to re-measure

AI Feature Card

Use when: Legal, sales and support each ask what the feature does and where it fails
Output: Intended and out-of-scope use, the data, the eval results as run with dates, the known limits, the disclosures, and the owner

AI Exec Brief

Use when: Leaders ask “how accurate is it” and one number would mislead them
Output: One page, bottom line first: how often it is wrong by severity, what that costs, the run cost, and the decision being asked for

03How to use it

Pick the workflow that matches your week

No fixed order. Bring one live piece of work and open the skill that matches where it is stuck.

Decide if AI fits

Someone asked for “an AI feature”.

AI Use Case Canvas
AI Failure Modes Map
Workflow or Agent Decision
AI Model Selection

Write a testable spec

The feature needs a spec you can test.

AI PRD
AI Success Criteria
AI Behavior Contract
Human-in-the-Loop Design

Brief the model and the agent

The system prompt grew by patches.

System Prompt Brief
Context Engineering Brief
Agent Spec
Tool Descriptions

Build the evals

You have real transcripts and nothing to measure them with.

Error Analysis
Golden Dataset
Eval Rubric
LLM-as-a-Judge Prompt
AI Eval Plan

Ship it safely

Launch is close and it needs gates that can stop it.

AI Red Teaming Plan
AI UX Review
AI Launch Gates

Keep it working

The feature is live.

Weekly AI Quality Review
AI Feedback Signals
Prompt Regression Test

Cost and explain it

Finance, legal and leadership have questions.

AI Unit Economics
AI Feature Card
AI Exec Brief

04Setup guide

Install it in five minutes

In Claude Code · two lines

/plugin marketplace add polar-bear-org/claude-skills
/plugin install ai-product-managers-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 36 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 — aipm-ai-use-case-canvas 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 aipm-ai-use-case-canvas on this request for an AI feature: [paste it here]

Run aipm-system-prompt. The system prompt as it stands: [paste it here]

Run aipm-error-analysis on last week's transcripts: [paste them here]

Lantern for AI product managers

Turn what you learned testing an AI feature into posts

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
Need to know if a model is needed at all?	AI Use Case Canvas
Need to show which mistakes matter?	AI Failure Modes Map
Need to choose between a workflow and an agent?	Workflow or Agent Decision
Need a demo not mistaken for the product?	AI Prototype Brief
Need a spec engineers can test?	AI PRD
Need “good” written as numbers?	AI Success Criteria
Need limits an agent cannot cross?	Agent Spec
Need failure types from real outputs?	Error Analysis
Need a test set built from real cases?	Golden Dataset
Need to attack it before strangers do?	AI Red Teaming Plan
Need to know a prompt edit broke nothing?	Prompt Regression Test
Need cost per successful outcome?	AI Unit Economics

06Standards

The quality bar

Every skill in the pack holds the same standard, the one we hold when we ship AI in our own product:

One method, applied properly: each skill uses the real mechanics of its source — the canvas fields, the pattern list, the coding passes, the capability and regression split, the risk classes — not a generic “gather, analyse, recommend”
Real outputs first: failure types, golden cases and judge checks come from outputs you paste, and synthetic cases fill gaps, are marked synthetic, and never carry the headline score
No invented numbers: no made-up scores, prices, error rates or usage, and an eval result appears only when you pasted the run behind it
Errors by severity and cost per successful outcome, never a single accuracy figure on its own or a cost per call without the retries and failures behind it
Work is scored, people are not: skills score outputs, cases, risks and options, never reviewers, users or team members
Legal, privacy and regulatory points go to a qualified adviser — the skills ask the questions and never answer them
The red line: Claude drafts the tests, never the verdict — it does not set the error your users can live with, sign off a launch, or report a score it did not see run on real outputs, and a person who knows the domain reads real transcripts every week

07FAQ

Questions people ask

What is in the Claude for AI Product Managers pack?

36 Claude skills that follow AI product work in seven stages: decide if AI fits, spec it, brief the model and the agent, build the evals, ship it safely, run and improve, and cost, price and explain. Each skill is one named method or one artifact.

How do I install these Claude skills?

In Claude Code, two lines install all 36 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 sign off the launch?

No. Claude drafts the tests, never the verdict. It does not set the error your users can live with, sign off a launch, or report a score it did not see run on real outputs. A person who knows the domain reads real transcripts every week.

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.