Product Team Claude Skills · 2026

Claude Code for Product Managers

A structured skill system that turns Claude into a personalized PM partner — context-aware, role-specific, and tailored to your product.

10
PM Skills
6
Shared Skills
4
Architecture Layers
19
Total Commands
Context

What we observed

Pain point 1

Decisions disappear

Important product decisions — UX choices, scope trade-offs, rejected ideas — get made in meetings and Slack but never written down. Six months later, nobody knows why something was built a certain way.

Pain point 2

Silent scope trade-offs

When a manager adds a new request, PMs accept it by quietly dropping something else from the roadmap. The trade-off is never explicit and never visible to the team.

Pain point 3

Requirements miss edge cases

PMs define the happy path well. But edge cases — what happens when a payment is pending, when a user has no permissions, when a service is down — get discovered by engineering mid-implementation.

Pain point 4

No awareness of technical cost

PMs can't easily see what a feature touches in the codebase. They don't know which modules are affected, which shared services are involved, or what might break when something changes.

Design Principle

One system, two separations

The system separates what is fixed from what is personal — and separates Claude's instructions from Claude's knowledge of the product.

Policy Layer — fixed for all PMs
rules · commands · output format · skill logic
Supervisor defines · git pull to update
Interview Engine — run once per PM
structured interview → 13 personalized files
One session · generates everything
Dynamic Layer — unique per PM
CLAUDE.md · 11 context files · product agent
Output of interview · committed to repo
Personal Layer — private
CLAUDE.local.md · settings.local.json
PM only · gitignored · never shared

The key insight: When the supervisor updates a skill or rule, only the Policy Layer changes. Each PM's CLAUDE.md and context files stay untouched. No merge conflicts. No re-interview.

Layer 1

Repository structure

Every file has a defined owner and a defined purpose. Nothing is ad-hoc.

Supervisor owns
policy/
  ├── rules/            # 6 hard rules
  ├── commands/        # slash commands
  ├── output-styles/   # output format
  ├── settings.json    # team settings
  └── skills/
      ├── shared/      # 6 shared skills
      └── product-manager/ # 10 PM SKILL.md
interview/
  └── pm-interview.md
PM owns (in their product repo)
CLAUDE.md          # from interview
CLAUDE.local.md     # private, gitignored
.claude/
  ├── settings.json     # from pm-template
  ├── agents/            # from interview
  └── skills/product-manager/
      ├── problem-framing/
      │   ├── SKILL.md   # from supervisor
      │   └── context.md # from interview
      └── ... (9 more)
claude-workflow/   # this repo (git clone)
Layer 1 + Layer 3

How a skill produces personalized output

Three inputs combine at runtime. Each is maintained separately.

From supervisor

SKILL.md

Fixed logic. Defines the workflow, decision rules, output format, and quality constraints. Never changes per PM.

workflow steps
output structure
hard constraints
quality checks
+
From interview

context.md

Product-specific knowledge. Makes the skill aware of this PM's product, team, and constraints. Different per PM.

business rules
team conventions
known constraints
historical context
+
From interview

CLAUDE.md

PM profile. Defines authority, communication style, technical depth, and behavioral instructions for Claude.

PM authority limits
preferred output format
technical depth
what Claude must flag
=
Output

Personalized for this PM and this product

Same skill logic, but the output references the right modules, business rules, team conventions, and authority limits specific to this PM.

Example: The edge-case-finder skill runs identical logic for every PM. But for a fintech PM, it checks payment gateway timeouts, account verification states, and financial compliance limits — because those are in their context.md. For a content PM, it checks a completely different set of constraints.

Layer 2

The interview engine

One structured conversation generates 13 files. Every question maps to a specific output. Nothing is collected without purpose.

10 interview sections
A
Product & Business
mission, business logic, external dependencies
B
Team Structure
engineering size, design involvement, roles
C
Decision Architecture
who has authority over what
D
Feature Workflow
idea to production, artifacts, approvals
E–G
Requirements · Roadmap · Docs
handoff patterns, OKRs, documentation tools
H
Technical Context
module structure, design system, QA process
J
PM Profile
technical depth, output preferences, red flags
13 files generated
md
CLAUDE.md
PM profile + product context + instructions for Claude
root
×11
context.md
one per skill — product-specific knowledge
skills/
ag
product-agent.md
specialized agent with product persona
agents/
Interview format

Questions are in Persian. Each question includes selectable options. AI uses conversation history to skip things it already knows. Vague answers trigger one targeted follow-up before moving on.

Process · Onboarding

PM Onboarding — up and running in 15 minutes

Two commands to install, one interview to personalize. Everything runs from inside Claude Code — no manual file editing required.

Prerequisites
Claude Code CLI installed Node.js 18+ & npm Product repo on your machine
1

Install the package globally

One command. Installs the claude-pm CLI on your machine.

npm install -g claude-pm
2

Run init inside your product repo

Installs all PM skills to ~/.claude/ globally, and scaffolds the policy tree, interview file, and placeholder context files inside the repo.

cd your-product-repo
claude-pm init --role pm
3

Open Claude Code at repo root

Launch Claude Code inside the product repo. Skills and policy files are now discoverable from the session.

4

Run the PM interview

Type /start-interview to begin. The interview runs in Persian, takes 20–30 minutes, and generates all 13 context files at the end. Each question maps to a specific output file — nothing is collected without purpose.

/start-interview
5

Review the generated files

13 files appear: CLAUDE.md at repo root, 11 context.md files (one per skill), and product-agent.md in .claude/agents/. Review the key decisions and business rules captured before committing.

6

Commit to the repo

git add CLAUDE.md .claude/ .gitignore && git commit -m "feat: add PM workflow context"
7

Run your first command

Open Claude Code and describe a feature. The full context is loaded automatically on every session.

/new-feature [describe your feature]

Updating policy: When the supervisor ships new skills or rules, run claude-pm update. Your CLAUDE.md and all context files are never touched.

Personal context: Create CLAUDE.local.md at repo root for private notes. It's gitignored and loads alongside CLAUDE.md on every session.

Process

Receiving updates — one command

The separation of Policy Layer and Dynamic Layer means supervisor updates never touch PM-owned files. No merge conflicts.

When supervisor updates a skill or rule

Supervisor pushes to product-team-claude-skills repo. PM runs:

cd claude-workflow && git pull && cd ..

That is the entire update process. Nothing else required.

What changes

claude-workflow/policy/skills/product-manager/*/SKILL.md
updated
claude-workflow/policy/rules/*.md
updated
claude-workflow/policy/commands/*.md
updated

What never changes

CLAUDE.md
untouched
.claude/skills/product-manager/*/context.md
untouched
.claude/agents/product-agent.md
untouched
CLAUDE.local.md
private · gitignored

Because policy files and PM-owned files live in separate directory trees, git pull never creates a merge conflict. The separation is enforced by the repository structure, not by process.

Layer 1 · Policy

Settings and output format

Two configuration files define how Claude behaves by default for every PM in the team.

settings.json — team defaults

mode
defaultMode: plan
Claude writes a plan and waits for approval before any file change
lvl
effortLevel: high
Claude reasons at maximum precision on every task
dir
additionalDirectories
["./claude-workflow"] — Claude reads policy files
perm
permissions
read + git commands allowed · file edits require approval · no curl/rm

pm-standard output style — every response

Required sections in every feature-related output:
1 Summary — one sentence
2 Main content
3 Out of scope — explicit list
4 Open questions
Sign-off required (if applicable)
DOD
Overview

All PM Skills at a Glance

Each skill is a focused, context-loaded workflow that Claude runs on demand. Invoke by command or let chains run them in sequence.

PM-Specific Skills

problem-framing

Vague idea → engineering-ready DOD

feature-prioritization

Defensible prioritization with trade-offs

feature-dependency

Codebase-read dependency analysis

edge-case-finder

Stress-test a feature definition

scope-check

Scope creep detection and trimming

feature-spec

Full team alignment spec document

requirement-writer

Engineering-precise requirements

release-impact

Pre-release impact analysis

qa-guide

Structured test plan from codebase

decision-logger

Capture product decisions before they're lost

Shared Skills (PM + Designer)

design-system-check

Inventory existing UI components

wireframe-generator

Interactive HTML wireframe with all states

task-writer

Linear task with four-part structure

meeting-support

Agenda prep and action item extraction

presentation-style

Polished HTML slide deck generation

prompt-optimizer

Analyze and rewrite prompts for clarity

PM Skill · Discovery

problem-framing

Turn a vague feature request or product idea into a precise, engineering-ready Definition of Done — before the team wastes time building the wrong thing.

PM Skill Discovery Phase Step 1 in /new-feature
When to use

"I want to build this", "management asked us to do this", "what's the DOD for this task", or any time a feature idea needs to become a precise deliverable before engineering discussion starts.

What it outputs

A four-part Linear task structure: context, user story, DOD (the most critical part), and out-of-scope list. Preliminary edge cases and dependencies are also surfaced.

Invoke: /problem-framing [describe the feature] — or runs automatically as Step 1 in /new-feature

PM Skill · Strategy

feature-prioritization

Make prioritization decisions that are explicit, documented, and defensible — not silent trade-offs that quietly reshape the roadmap without anyone noticing.

PM Skill Strategic Decision
When to use

"Which one should we build first", "management wants this feature but it conflicts with our roadmap", "how do I justify not doing this", or any situation where a prioritization decision needs to be made and communicated.

What it outputs

A scoring analysis across strategic alignment, user impact, technical effort, and risk. Clear recommendation with reasoning, what gets deprioritized, and a handoff to decision-logger to capture the choice.

Includes automatic handoff to decision-logger — every prioritization decision gets captured before it's forgotten.

PM Skill · Technical Awareness

feature-dependency

Read the codebase directly to identify what modules, services, and components a planned feature will touch — so the PM can have informed conversations with engineering.

PM Skill Reads Repository Step 2 in /new-feature
When to use

"Engineering said it has dependencies but I don't know what", "before we start I need to know which modules are affected", or any time a PM needs technical dependency analysis before committing to a feature.

What it outputs

A dependency map of affected files/modules, complexity estimate, cross-team coordination needs, and questions the PM should ask engineering before the sprint begins.

This skill reads the repository directly — it does not ask the PM to describe the code. Requires Claude Code with repository access.

PM Skill · Quality

edge-case-finder

Stress-test a defined feature before engineering starts — finding the cases the PM hasn't thought of, before engineering finds them mid-sprint or users find them in production.

PM Skill Risk Reduction Step 3 in /new-feature
When to use

"What did I miss", "what are the edge cases for this feature", "engineering said we didn't consider this case", or any situation where a feature definition needs to be tested before implementation begins.

What it outputs

A prioritized list of edge cases with risk levels (critical/high/medium), each case's required UI state, and flags for which cases need distinct wireframe states in the next step.

Output feeds directly into wireframe-generator — all states found here must be represented as wireframe states in Step 4.

PM Skill · Scope Control

scope-check

A scope creep intervention tool for features that have grown beyond their original boundaries. Identify what was added, what's essential, and where scope can be trimmed without losing core value.

PM Skill Scope Management
When to use

"This feature keeps growing", "engineering said there's too much work", "we keep adding things mid-sprint", "management is adding requirements". Do NOT use for initial scope definition — use problem-framing for that.

What it outputs

Original scope vs. current scope comparison, categorized additions (essential / nice-to-have / out-of-scope), a trimmed MVP definition, and what to defer to a future iteration.

Use when drift has already started. For initial scope definition before implementation, use /problem-framing instead.

PM Skill · Documentation

feature-spec

Produce a single comprehensive spec document that serves as the source of truth for a feature — for engineering, design, QA, and stakeholders.

PM Skill Team Alignment Step 5 in /new-feature
When to use

"Write the spec for this feature", "I need a document for the team meeting", "the spec needs to be ready before the sprint starts". Use this for whole-team alignment. Use requirement-writer when engineering needs deeper precision.

What it outputs

Feature overview with business context, user story, design considerations, acceptance criteria for all roles (engineering + design + QA), out-of-scope section, and open questions.

Not the same as requirement-writer: feature-spec is for team alignment; requirement-writer is for engineering precision on error states and validation rules.

PM Skill · Engineering Handoff

requirement-writer

Write engineering-ready requirements that leave no ambiguity — every path, every error state, every validation rule — so developers can implement without asking follow-up questions.

PM Skill Engineering Document
When to use

"I need engineering to have all the details", "write the technical requirements", "engineering said the requirements are incomplete", "I need to specify every error state and validation rule".

What it outputs

Complete flow documentation covering: all user actions, every API call, every error response, all validation rules, business rules, and edge cases. Structured so a developer can implement without guessing.

Use after feature-spec when engineering needs implementation precision. The spec aligns the team; the requirements guide the build.

PM Skill · Release Management

release-impact

Analyze the impact of a feature or change before it goes to production — identifying what else in the system might break or be affected.

PM Skill Reads Repository Step 1 in /release-check
When to use

"We want to release this, what might break", "what else does this change affect", "what do we need to check before deploying", or any time a PM needs pre-release impact analysis.

What it outputs

Affected modules and services, downstream dependencies, regression risk assessment, suggested rollback triggers, and a list of areas that must be verified before release. Feeds directly into qa-guide.

Reads git history and the repository directly. Run as part of /release-check to automatically chain into a full test plan.

PM Skill · Quality Assurance

qa-guide

Generate a complete, prioritized testing guide from the codebase — so QA knows exactly what to test, in what order, and why.

PM Skill Reads Repository Step 2 in /release-check
When to use

"We need to test this, what do we check", "what is the test plan for this feature", "what should QA test", "we changed the payment module and need to make sure nothing broke".

What it outputs

Prioritized test cases (P0/P1/P2) with pre-conditions, steps, and expected outcomes. Regression test list for affected modules. Happy path, edge cases, and error state coverage all included.

Works best after release-impact — uses its output to focus test coverage on the right areas. Also runs standalone for any feature QA.

PM Skill · Institutional Memory

decision-logger

Capture important product decisions in a structured, retrievable format before they get lost in chat history, meeting memory, or Slack threads.

PM Skill Institutional Memory
When to use

"We need to write this decision down", "why did we choose this design", "the meeting ended and we decided something but nobody wrote it down", "we reduced scope but never documented why".

What it outputs

A structured decision record with: decision type, context, options considered, final choice, rationale, who made the call, and date. Appended to the project's decision log. Handles UX, architecture, scope, and prioritization decisions.

Called automatically by feature-prioritization at the end of every session. Also invoke directly after any meeting where an important decision was made.

Shared Skill · UI Planning

design-system-check

Inventory what UI components already exist in the design system before planning new work — so the team isn't building something that already exists.

Shared — PM & Designer Step 3.5 in /new-feature
When to use

"What components do we have", "do we need to build this UI from scratch or do we have a component", "the designer said we need a new component" — before requesting design work for UI that may already exist.

What it outputs

Available components that can be reused as-is, components that need extension, and net-new components that must be built. Feeds into wireframe planning so existing components are used wherever possible.

Invoke: /design-system-check [describe the UI needs]

Shared Skill · Visualization

wireframe-generator

Generate interactive HTML wireframes showing a feature in multiple states and multiple interaction pattern variants — not just the happy path.

Shared — PM & Designer Step 4 in /new-feature
When to use

"Show me what this looks like", "generate a wireframe", "I want to see all the states", "show me different ways to implement this", "make a visual prototype of the flow".

What it outputs

A self-contained HTML file with clickable state transitions: empty state, loading, success, error, edge cases. Multiple UX variants presented side-by-side. Uses existing design system components found by design-system-check.

Invoke: /wireframe-generator [feature description + states to show]

Shared Skill · Linear Integration

task-writer

Convert any output — a problem framing, a spec, a bug report — into a ready-to-paste Linear task with the team's standard four-part structure.

Shared — PM & Designer Linear-Ready Output
When to use

"Write a Linear task", "create a task for this", "I need to log this in Linear", or when any other skill explicitly hands off to this one. Use after problem-framing or feature-spec.

What it outputs

A formatted Linear task with four parts: (1) Context — why this matters, (2) User Story — who benefits and how, (3) DOD — precise completion criteria, (4) Out of scope — explicit exclusions. Ready to paste directly into Linear.

Invoke: /task-writer [describe what the task is about]

Shared Skill · Meetings

meeting-support

Prepare structured agendas before meetings and extract action items, decisions, and open questions after them.

Shared — PM & Designer Pre & Post Meeting
When to use

"Prepare the agenda for our sprint planning", "summarize what we decided", "extract action items from this meeting", "log the decisions from today", "what are the open questions from the meeting".

What it outputs

Pre-meeting: timed agenda with discussion points, decision goals, and prep questions. Post-meeting: structured summary with decisions made, action items with owners, and open questions that need follow-up.

Invoke: /meeting-support [meeting type + context]

Shared Skill · Communication

presentation-style

Generate polished, single-file HTML slide decks following a precise design system — no external dependencies, scroll-based, publication-ready.

Shared — PM & Designer HTML Output
When to use

"Make a presentation", "create a slide deck", "build a pitch deck", "I need to present this to the team". Trigger on any request for a presentation, deck, or slide document.

What it outputs

A self-contained HTML file saved to docs/. Title slide, content slides (cards, step rows, arch layers, code blocks), and summary slide — all following the team's flat-color, no-shadow design system.

Invoke: /presentation-style [topic and content description] — saved to docs/ for GitHub Pages publishing

Shared Skill · Prompt Engineering

prompt-optimizer

Analyze, critique, and rewrite prompts to maximize clarity, specificity, and output quality — for both claude.ai and Claude Code.

Shared — PM & Designer Prompt Engineering
When to use

"Optimize this prompt", "improve my prompt", "review my prompt", "what's wrong with this prompt", or when you paste a prompt draft and want feedback. Works for both casual claude.ai conversations and Claude Code workflows.

What it outputs

A critique identifying ambiguity, missing context, and vague instructions. A rewritten prompt with specific improvements. An explanation of what changed and why each change improves output quality.

Invoke: /prompt-optimizer [paste your prompt]

Chain Command · Full Feature Flow

/new-feature

A complete end-to-end feature development workflow — from raw idea to spec, wireframe, and Linear task — in one command.

Chain Command 6 Skills in Sequence Wait for Approval
1

problem-framing

Define the DOD, preliminary edge cases, preliminary dependencies

2

feature-dependency

Read the codebase — which modules does this touch?

3

edge-case-finder

Prioritized edge cases with risk levels and required UI states

3.5

design-system-check

Inventory available components before wireframing

4

wireframe-generator

HTML wireframe covering all states, using existing components

5

feature-spec

Complete spec consolidating all previous outputs — ready for team handoff

Invoke: /new-feature [describe the feature] — Claude waits for PM approval between each step before proceeding

Chain Command · Pre-Release

/release-check

Analyze the full impact of a release and generate a complete test plan — from codebase and git history — in one command.

Chain Command 2 Skills in Sequence Reads Repository
1

release-impact

Read git diff and codebase — what modules are affected, what could break, what are the regression risks?

2

qa-guide

Prioritized test plan (P0/P1/P2) based on the impact analysis, covering happy path, edge cases, and regressions

Invoke: /release-check [feature name or branch] — or omit arguments to use the latest git diff

Chain Command · Spec Maintenance

/sync-spec

Compare the feature spec with the current implementation — find where the spec is outdated, where the implementation deviated, and where the PM needs to make a decision.

Chain Command Reads Repository Requires PM Approval
Inputs

Reads the feature spec file from the repository, reads the current implementation source files directly, and checks git history for recent changes — no manual description needed.

What it outputs

A Spec Drift Report: (1) Spec outdated — impl is correct, update the spec. (2) Implementation deviated — spec is correct, flag for engineering. (3) PM decision needed — unclear which is right.

Never updates any file automatically. Presents proposed changes and waits for PM approval. Invoke: /sync-spec [feature name or spec file path]

Summary

What This System Delivers

A complete PM workflow system — from first idea to post-release QA — with every step documented, every decision captured, and every artifact structured for the team.

Discovery to Spec

problem-framing → feature-dependency → edge-case-finder → design-system-check → wireframe-generator → feature-spec

Precision Handoffs

requirement-writer for engineering depth, design-system-check for UI clarity, task-writer for Linear — every handoff structured.

Release Confidence

release-impact + qa-guide automatically chained in /release-check. sync-spec keeps docs aligned with what was actually built.

10
PM Skills
6
Shared Skills
3
Chain Commands
19
Total Commands