PM Skills Marketplace: 5 Hidden Uses of the 18K★ AI Product OS

Most AI coding assistants give you generic outputs — a PRD that reads like a template, a strategy doc that could apply to any product, a roadmap that's just a feature list with dates. But what if your AI assistant came pre-loaded with the entire product management playbook?

That's exactly what PM Skills Marketplace delivers. With 18,865 GitHub stars and counting, this open-source project packs 68 PM skills and 42 chained workflows across 9 plugins — from discovery to strategy, execution, launch, and growth. It's designed for Claude Code, Claude Cowork, Codex, and other AI assistants.

But here's the thing: most people install it, run /discover once, and never touch the other 41 workflows. That's like buying a Swiss Army knife and only using the blade.

Let's fix that.

Hidden Use #1: The /red-team-prd Adversarial Stress Test

What most people do: Write a PRD, get stakeholder sign-off, start building.

The hidden trick: Before you ship that PRD, run /red-team-prd to adversarially stress-test it. This command uses the strategy-red-team skill to surface load-bearing assumptions, name what would make each one fail, and rank them by cheapest test.

# In Claude Code or Cowork
/red-team-prd
# Paste your PRD or describe your feature idea
# The AI will play devil's advocate and find your blind spots

The result: You get a ranked list of your riskiest assumptions with specific experiments to test each one — before you write a single line of code. This is the "pre-mortem meets PRD review" workflow that most PMs do in meetings but rarely document.

Data sources: PM Skills Marketplace GitHub 18,865 Stars, 1,937 Forks (verified via GitHub API, 2026-06-16). The strategy-red-team skill is part of the pm-execution plugin.

Hidden Use #2: Opportunity Solution Trees (Not Just User Stories)

What most people do: Write user stories in the standard "As a [user], I want [feature], so that [benefit]" format.

The hidden trick: Use the opportunity-solution-tree skill to build a Teresa Torres-style Opportunity Solution Tree. This maps Outcomes → Opportunities → Solutions → Experiments, ensuring every feature connects to a measurable outcome.

# In Claude Code
Help me build an Opportunity Solution Tree for improving user activation
# The AI will guide you through:
# 1. Define the target outcome (e.g., "Increase D7 retention from 20% to 35%")
# 2. Map opportunities (unmet needs, pain points)
# 3. Brainstorm solutions for each opportunity
# 4. Design experiments to validate solutions before building

The result: Instead of a backlog of disconnected features, you get a visual map showing exactly how each experiment connects to your target outcome. This is the core of Continuous Discovery Habits (Teresa Torres) encoded as an AI skill.

Data sources: PM Skills Marketplace README, pm-product-discovery plugin (13 skills, 5 commands). The opportunity-solution-tree skill is documented in the project's plugin reference.

Hidden Use #3: The /generate-data Dummy Dataset Generator

What most people do: Use fake data like "User1, User2, Test123" in prototypes and test scenarios.

The hidden trick: Use /generate-data to create realistic dummy datasets as CSV, JSON, SQL, or Python. This feeds directly into your test scenarios, demo environments, and PRD acceptance criteria.

# Generate a realistic dataset for testing
/generate-data
# "Create a CSV of 500 B2B SaaS users with realistic company names,
#  subscription tiers, usage patterns, and churn indicators"

The result: Your test scenarios become realistic enough to catch edge cases. Your demos look professional. Your stakeholders can't tell it's fake data. And you can feed the same dataset into /test-scenarios to generate comprehensive test coverage.

Data sources: PM Skills Marketplace pm-execution plugin, dummy-dataset skill (1 of 16 skills in the execution plugin). Verified in project README.

Hidden Use #4: Multi-Platform Skill Deployment (Not Just Claude)

What most people do: Install PM Skills in Claude Code and think that's all.

The hidden trick: The skills/*/SKILL.md files follow the universal skill format and work with Gemini CLI, OpenCode, Cursor, Kiro, and more. You can copy skills to any tool that reads the format:

# Deploy to OpenCode (project-level)
for plugin in pm-*/; do
  mkdir -p .opencode/skills/
  cp -r "$plugin/skills/"* .opencode/skills/ 2>/dev/null
done

# Deploy to Gemini CLI (global)
for plugin in pm-*/; do
  cp -r "$plugin/skills/"* ~/.gemini/skills/ 2>/dev/null
done

# Deploy to Cursor (project-level)
for plugin in pm-*/; do
  cp -r "$plugin/skills/"* .cursor/skills/ 2>/dev/null
done

The result: Your entire team gets access to the same PM frameworks regardless of which AI assistant they use. The slash commands (/discover, /strategy) are Claude-specific, but the underlying skills (the actual PM frameworks) work everywhere.

Data sources: PM Skills Marketplace README, "Other AI assistants" section. The project explicitly documents compatibility with Gemini CLI, OpenCode, Cursor, and Kiro.

Hidden Use #5: The /market-scan Competitive Intelligence Engine

What most people do: Manually research competitors, read G2 reviews, and create SWOT analyses from scratch.

The hidden trick: Use /market-scan to run a comprehensive macro environment analysis that combines SWOT + PESTLE + Porter's Five Forces + Ansoff Matrix in a single command.

# Run a full competitive landscape analysis
/market-scan
# "Analyze the project management SaaS market for a new AI-powered
#  tool targeting remote agencies with 10-50 employees"

The result: You get a structured analysis covering internal strengths/weaknesses, external opportunities/threats, macro-environmental factors (political, economic, social, technological, legal, environmental), competitive forces (rivalry, supplier power, buyer power, substitutes, new entrants), and growth strategies (market penetration, development, product development, diversification). All in one pass.

Data sources: PM Skills Marketplace pm-product-strategy plugin (12 skills, 5 commands). The swot-analysis, pestle-analysis, porters-five-forces, and ansoff-matrix skills are all documented in the project README.

---

Summary: 5 Hidden Uses of PM Skills Marketplace

1. /red-team-prd — Adversarially stress-test your PRD before building
2. Opportunity Solution Trees — Connect every feature to measurable outcomes
3. /generate-data — Create realistic dummy datasets for testing and demos
4. Multi-platform deployment — Use the same PM skills across Claude, Cursor, Gemini, OpenCode
5. /market-scan — Run SWOT + PESTLE + Porter's + Ansoff in a single command

Further Reading

• Agent-Skills: Production-Grade Engineering Skills for AI Coding Agents — The engineering counterpart to PM Skills
• n8n Workflow Automation: 5 Hidden Uses — Workflow automation meets product management
• KTransformers: 5 Hidden Uses — Running massive models on consumer hardware

---

Got your own hidden use for PM Skills Marketplace? Drop a comment below — I'd love to hear how you're using it in your workflow.