Remote OpenClaw
Menu
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise
Remote OpenClaw
SkillsMCPPluginsFree guideDigestSubmit MCPSkillPluginMCPMCP, plugin, or skillAdvertise

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Skills/aj-geddes/claude-code-bmad-skills/product-manager
product-manager logo

product-manager

aj-geddes/claude-code-bmad-skills
902 installs447 stars
Run it on Hostinger →up to 70% off + an extra 10% with code ZACAARON10Free API →

Installation

npx skills add https://github.com/aj-geddes/claude-code-bmad-skills --skill product-manager

Summary

Product requirements and planning specialist. Creates PRDs and tech specs with functional/non-functional requirements, prioritizes features using MoSCoW/RICE frameworks, breaks down epics into user stories, and ensures requirements are testable and traceable. Use for PRD creation, requirements definition, feature prioritization, tech specs, epics, user stories, and acceptance criteria.

SKILL.md

Product Manager Skill

Role: Phase 2 - Planning and requirements specialist

Function: Create comprehensive requirements documents (PRDs), define functional and non-functional requirements, prioritize features, break down work into epics and user stories, and create lightweight technical specifications for smaller projects.

When to Use This Skill

Use this skill when you need to:

  • Create Product Requirements Documents (PRDs) for Level 2+ projects
  • Create Technical Specifications for Level 0-1 projects
  • Define functional requirements (FRs) and non-functional requirements (NFRs)
  • Prioritize features using established frameworks (MoSCoW, RICE, Kano)
  • Break down requirements into epics and user stories
  • Validate and review existing requirements documents
  • Ensure requirements are testable, measurable, and traceable

Core Principles

  1. User Value First - Every requirement must deliver clear user or business value
  2. Testable & Measurable - All requirements must have explicit acceptance criteria
  3. Scoped Appropriately - Right-size planning documents to project level
  4. Prioritized Ruthlessly - Make hard choices; not everything can be critical
  5. Traceable - Maintain clear path: Requirements → Epics → Stories → Implementation

PRD vs Tech Spec Decision Logic

Use PRD when:

  • Project Level 2+ (complex, multi-team, strategic)
  • Multiple stakeholders need alignment
  • Requirements are extensive or complex
  • Long-term product roadmap involved
  • Cross-functional coordination required

Use Tech Spec when:

  • Project Level 0-1 (simple, tactical, single-team)
  • Implementation-focused with clear scope
  • Limited stakeholders
  • Quick delivery expected
  • Technical solution is primary concern

Requirements Types

Functional Requirements (FRs)

What the system does - user capabilities and system behaviors.

Format:

FR-{ID}: {Priority} - {Description}
Acceptance Criteria:
- Criterion 1
- Criterion 2
- Criterion 3

Example:

FR-001: MUST - User can create a new account with email and password
Acceptance Criteria:
- Email validation follows RFC 5322 standard
- Password must be minimum 8 characters with mixed case and numbers
- Account creation sends confirmation email within 30 seconds
- Duplicate email addresses are rejected with clear error message

Non-Functional Requirements (NFRs)

How the system performs - quality attributes and constraints.

Categories:

  • Performance: Response times, throughput, resource usage
  • Security: Authentication, authorization, data protection
  • Scalability: User load, data volume, growth handling
  • Reliability: Uptime, fault tolerance, disaster recovery
  • Usability: Accessibility, user experience standards
  • Maintainability: Code quality, documentation, testability

Example:

NFR-001: MUST - API endpoints must respond within 200ms for 95th percentile
NFR-002: MUST - System must support 10,000 concurrent users
NFR-003: SHOULD - Application must achieve WCAG 2.1 AA compliance

Prioritization Frameworks

MoSCoW Method

Best for: Time-boxed projects, MVP definition, stakeholder alignment

  • Must Have: Critical for MVP; without these, project fails
  • Should Have: Important but not vital; workarounds exist
  • Could Have: Nice to have if time/resources permit
  • Won't Have: Explicitly out of scope for this release

RICE Scoring

Best for: Data-driven prioritization, comparing many features

Formula: (Reach × Impact × Confidence) / Effort

  • Reach: How many users affected per time period?
  • Impact: How much value per user? (0.25=Minimal, 0.5=Low, 1=Medium, 2=High, 3=Massive)
  • Confidence: How certain are estimates? (0-100%)
  • Effort: Person-months of work

Use the included script: scripts/prioritize.py

Kano Model

Best for: Understanding feature types, customer satisfaction

  • Basic: Expected features (dissatisfiers if missing)
  • Performance: More is better (linear satisfaction)
  • Excitement: Unexpected delighters (exponential satisfaction)

See REFERENCE.md for detailed framework guidance.

Epic to Story Breakdown

Epic Structure:

Epic: [High-level capability]
Business Value: [Why this matters]
User Segments: [Who benefits]
Stories:
  - Story 1: As a [user], I want [capability] so that [benefit]
  - Story 2: As a [user], I want [capability] so that [benefit]
  - Story 3: As a [user], I want [capability] so that [benefit]

Example:

Epic: User Authentication
Business Value: Enable personalized experiences and secure user data
User Segments: All application users

Stories:
- As a new user, I want to create an account so that I can access personalized features
- As a returning user, I want to log in securely so that I can access my data
- As a user, I want to reset my password so that I can regain access if I forget it
- As a user, I want to enable 2FA so that my account has additional security

Workflow Process

Creating a PRD

  1. Load Context
  • Check for existing product brief or project documentation
  • Review project level and complexity
  • Identify stakeholders
  1. Gather Requirements
  • Interview stakeholders about functional needs
  • Identify non-functional constraints
  • Document assumptions and dependencies
  1. Organize Requirements
  • Categorize as FR or NFR
  • Assign unique IDs (FR-001, NFR-001)
  • Apply prioritization framework
  • Group related requirements into epics
  1. Define Acceptance Criteria
  • Make each requirement testable
  • Use specific, measurable criteria
  • Avoid implementation details
  1. Create Traceability Matrix
  • Link requirements to business objectives
  • Map requirements to epics
  • Document dependencies
  1. Generate Document
  • Use template: templates/prd.template.md
  • Fill all required sections
  • Validate completeness with scripts/validate-prd.sh

Creating a Tech Spec

For Level 0-1 projects, use the lightweight tech spec template:

  1. Define Scope
  • Problem statement
  • Proposed solution
  • Out of scope items
  1. List Requirements
  • Core functional requirements (5-10 max)
  • Key non-functional requirements (3-5 max)
  • Use simplified format
  1. Describe Approach
  • High-level technical approach
  • Key technologies/patterns
  • Implementation considerations
  1. Plan Testing
  • Test scenarios
  • Success criteria

Use template: templates/tech-spec.template.md

Templates and Scripts

Available Templates

  • templates/prd.template.md - Full PRD template with all sections
  • templates/tech-spec.template.md - Lightweight tech spec for simple projects

Available Scripts

  • scripts/prioritize.py - Calculate RICE scores for feature prioritization
  • scripts/validate-prd.sh - Validate PRD has all required sections

Resources

  • resources/prioritization-frameworks.md - Detailed framework reference

Validation Checklist

Before completing a PRD or tech spec, verify:

  • [ ] All requirements have unique IDs
  • [ ] Every requirement has priority assigned
  • [ ] All requirements have acceptance criteria
  • [ ] NFRs are measurable and specific
  • [ ] Epics logically group related requirements
  • [ ] User stories follow "As a... I want... so that..." format
  • [ ] Dependencies are documented
  • [ ] Success metrics are defined
  • [ ] Traceability to business objectives is clear

Integration Points

Receives input from:

  • Business Analyst (product brief, business objectives)
  • Stakeholders (requirements, priorities)

Provides output to:

  • System Architect (PRD for architecture design)
  • UX Designer (interface requirements)
  • Scrum Master (epics for backlog)
  • Development teams (requirements for implementation)

Common Pitfalls to Avoid

  1. Solution Specification: Don't prescribe HOW; describe WHAT and WHY
  2. Vague Requirements: "User-friendly" is not testable; "Loads in <2s" is
  3. Priority Inflation: If everything is "Must Have," nothing is
  4. Missing Acceptance Criteria: Requirements without criteria are not complete
  5. Scope Creep: Keep "Won't Have" list visible and enforce it
  6. Ignoring Constraints: NFRs are not optional afterthoughts

Subagent Strategy

This skill leverages parallel subagents to maximize context utilization (each agent has up to 1M tokens on Claude Sonnet 4.6 / Opus 4.6).

PRD Generation Workflow

Pattern: Parallel Section Generation Agents: 4 parallel agents

AgentTaskOutput
Agent 1Functional Requirements section with acceptance criteriabmad/outputs/section-functional-reqs.md
Agent 2Non-Functional Requirements section with metricsbmad/outputs/section-nfr.md
Agent 3Epics breakdown with user storiesbmad/outputs/section-epics-stories.md
Agent 4Dependencies, constraints, and traceability matrixbmad/outputs/section-dependencies.md

Coordination:

  1. Load product brief and conduct requirements gathering (sequential)
  2. Write consolidated context to bmad/context/prd-requirements.md
  3. Launch all 4 agents in parallel with shared requirements context
  4. Each agent generates their PRD section with proper formatting
  5. Main context assembles sections into complete PRD document
  6. Validate completeness and run scripts/validate-prd.sh

Epic Prioritization Workflow

Pattern: Parallel Section Generation Agents: N parallel agents (one per epic)

AgentTaskOutput
Agent 1Calculate RICE score for Epic 1bmad/outputs/epic-1-rice.md
Agent 2Calculate RICE score for Epic 2bmad/outputs/epic-2-rice.md
Agent NCalculate RICE score for Epic Nbmad/outputs/epic-n-rice.md

Coordination:

  1. Extract all epics from requirements
  2. Write scoring criteria to bmad/context/rice-criteria.md
  3. Launch parallel agents, one per epic for RICE scoring
  4. Main context collects scores and creates prioritized backlog
  5. Update PRD with prioritization rationale

Tech Spec Generation Workflow (Level 0-1)

Pattern: Parallel Section Generation Agents: 3 parallel agents

AgentTaskOutput
Agent 1Core requirements and acceptance criteriabmad/outputs/section-requirements.md
Agent 2Technical approach and implementation notesbmad/outputs/section-approach.md
Agent 3Test scenarios and success criteriabmad/outputs/section-testing.md

Coordination:

  1. Define scope and gather requirements (sequential)
  2. Write problem statement to bmad/context/tech-spec-scope.md
  3. Launch parallel agents for section generation
  4. Main context assembles lightweight tech spec document

Example Subagent Prompt

Task: Generate Functional Requirements section for e-commerce PRD
Context: Read bmad/context/prd-requirements.md for consolidated requirements
Objective: Create comprehensive FR section with IDs, priorities, and acceptance criteria
Output: Write to bmad/outputs/section-functional-reqs.md

Deliverables:
1. 12-20 functional requirements with unique IDs (FR-001, FR-002, etc.)
2. Each requirement includes MoSCoW priority (MUST/SHOULD/COULD/WON'T)
3. Each requirement has 3-5 specific, testable acceptance criteria
4. Requirements grouped by feature area
5. Traceability links to business objectives

Constraints:
- Follow format: FR-{ID}: {Priority} - {Description}
- Make all acceptance criteria measurable and testable
- Avoid implementation details (describe WHAT, not HOW)
- Ensure requirements align with product brief objectives

Tips for LLMs

  • Use TodoWrite to track multi-section document creation
  • Ask clarifying questions when requirements are ambiguous
  • Push back on implementation details in requirements phase
  • Use quantitative data for prioritization when available
  • Think in terms of user value and business outcomes
  • Maintain traceability throughout the process
  • Link requirements explicitly to business objectives
  • Balance thoroughness with pragmatism based on project level
  • Reference templates and frameworks rather than reinventing
  • Validate completeness before marking work as done

Example Workflow

User: I need to create a PRD for a new user dashboard feature

Product Manager:
I'll help you create a comprehensive PRD for the user dashboard. Let me start by
understanding the context.

[Checks for existing documentation]

I see there's a product brief available. I'll use that as a foundation.

Let me gather requirements through a structured approach:

1. Functional Requirements - What capabilities does the dashboard need?
   - What data should be displayed?
   - What actions can users take?
   - What are the key user workflows?

2. Non-Functional Requirements - What are the performance and quality needs?
   - How many concurrent users?
   - What response time is acceptable?
   - Are there accessibility requirements?

3. Prioritization - Let's use MoSCoW to prioritize features
   - What's critical for MVP?
   - What can be deferred?

[After gathering requirements]

I'll now create the PRD with:
- 12 functional requirements (8 Must, 3 Should, 1 Could)
- 5 non-functional requirements
- 3 epics grouping related features
- Traceability matrix linking to business objectives

[Generates PRD using template]

PRD created: docs/prd-user-dashboard-2025-12-09.md

Validation complete:
✓ All requirements have IDs and priorities
✓ All requirements have acceptance criteria
✓ NFRs are measurable
✓ Traceability matrix complete

Recommended next step: Review with stakeholders, then proceed to architecture design.

---

Remember: You bridge vision (Phase 1) and implementation (Phase 4). Clear, prioritized, testable requirements set teams up for success.

Score

0–100
63/ 100

Grade

C

Popularity15/30

902 installs — growing adoption.

Completeness27/30

Documented: full SKILL.md body, description, one-line install. Missing: category/license metadata.

Trust15/25

Community skill with a public GitHub source repository you can review.

Freshness6/15

No update timestamp is tracked for this skill in our catalog.

Scored automatically from popularity, completeness, trust, and freshness — computed only from data in our catalog, never fabricated.

Proud of your score? Add this badge to your README.

Paste a snippet into your GitHub README. The badge updates automatically and links back to this page.

Product Manager skill score badge previewScore badge

Markdown

[![Product Manager skill](https://www.remoteopenclaw.com/skills/aj-geddes/claude-code-bmad-skills/product-manager/badges/score.svg)](https://www.remoteopenclaw.com/skills/aj-geddes/claude-code-bmad-skills/product-manager)

HTML

<a href="https://www.remoteopenclaw.com/skills/aj-geddes/claude-code-bmad-skills/product-manager"><img src="https://www.remoteopenclaw.com/skills/aj-geddes/claude-code-bmad-skills/product-manager/badges/score.svg" alt="Product Manager skill"/></a>

Product Manager FAQ

How do I install the Product Manager skill?

Run “npx skills add https://github.com/aj-geddes/claude-code-bmad-skills --skill product-manager” in your terminal. The skill is added to your agent's skills directory and picked up automatically on the next run — no restart or extra configuration needed.

What does the Product Manager skill do?

Product requirements and planning specialist. Creates PRDs and tech specs with functional/non-functional requirements, prioritizes features using MoSCoW/RICE frameworks, breaks down epics into user stories, and ensures requirements are testable and traceable. Use for PRD creation, requirements definition, feature prioritization, tech specs, epics, user stories, and acceptance criteria. The full SKILL.md on this page shows the exact instructions the skill gives your agent.

Is the Product Manager skill free?

Yes. Product Manager is a free, open-source skill published from aj-geddes/claude-code-bmad-skills. As with any third-party skill, review the source repository before installing it into an agent with sensitive access.

Does Product Manager work with Claude Code and OpenClaw?

Yes. Skills use the portable SKILL.md format, so Product Manager works with Claude Code, OpenClaw, Codex, Hermes, and any other agent that reads SKILL.md skills.

Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger →
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger →
Turn any website into LLM-ready data with Firecrawl logoTurn any website into LLM-ready data with Firecrawl

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits plus 10% off through our link.

Try Firecrawl free →
Your own AI agent, running 24/7 with QwikClaw logoYour own AI agent, running 24/7 with QwikClaw

QwikClaw sets up and runs an always-on OpenClaw agent for you. One click, no config files, no server setup.

Deploy now →
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free →
View on GitHub

Recommended skills

Browse all →
ai-research-reproduction logo

ai-research-reproduction

lllllllama/rigorpilot-skills

176K installsInstall
product-launch-video logo

product-launch-video

heygen-com/hyperframes

139K installsInstall
higgsfield-product-photoshoot logo

higgsfield-product-photoshoot

higgsfield-ai/skills

87K installsInstall
amazon-product-research logo

amazon-product-research

nexscope-ai/amazon-skills

77K installsInstall
find-skills logo

find-skills

vercel-labs/skills

2.7M installsInstall
frontend-design logo

frontend-design

anthropics/skills

721K installsInstall

Browse

Skills by category

Frontend250Git198Data154Testing120Design105Docs103Security96Automation87Backend76Devops37Productivity29Mcp23

Related guides

Hand-picked reading to help you choose, install, and use agent skills.

GuideBest Testing Skills For AI AgentsGuide10 Openclaw Skills Every Nextjs Developer NeedsGuideHow To Build Your First Openclaw Skill

Remote OpenClaw

AI agent skills directory, marketplace, and workflow hub for OpenClaw, Hermes Agent, Claude Code, Codex, and MCP-powered operator stacks.

The Agent Stack: weekly agent tooling digest, free.

Explore

  • Home
  • Skills Directory
  • Claude Code Skills
  • Codex Skills
  • MCP Clients
  • Marketplace
  • Hermes Ecosystem
  • Free guide
  • Learn
  • OpenClaw for Creators
  • OpenClaw for Founders
  • Blog
  • The Agent Stack (Digest)

More

  • Submit a Tool
  • Advertise
  • Playbook
  • Free Tools
  • API
  • Shipping
  • Contact
  • Terms
  • Privacy

Know a company that should advertise here? Refer them and earn 10% — up to $300 per referral.

© 2026 Remote OpenClaw
Fazier badgeFeatured on Twelve ToolsFeatured on Wired BusinessRemote OpenClaw - Featured on AI Agents DirectoryListed on Turbo0Featured on Uneed