Skip to content

Product & Design Blueprint

Safety checked

Run Product Decisions End to End With PM Frameworks

0phurynMay 2026

68 structured PM skills and 42 chained workflows across 9 plugins covering discovery, strategy, execution, research, analytics, go-to-market, marketing, utilities, and AI shipping.

Product DiscoveryProduct StrategyExecutionMarket ResearchData AnalyticsGo-to-MarketProduct Marketing & GrowthPM ToolkitAI Shipping

Install Prompt

Copy this prompt and paste it into your AI agent to install.

What problem does this solve?

Runs product decisions through proven frameworks instead of relying on generic AI responses. Each skill encodes a domain framework (Opportunity Solution Tree, Lean Canvas, RICE prioritization, Jobs to Be Done, pre-mortem, etc.), and commands chain multiple skills into end-to-end workflows. You get the rigor of Teresa Torres, Marty Cagan, and Alberto Savoia built into your daily work, not as reference material you forget to use.

How does it work?

Install once (9 plugins for Claude Cowork, Claude Code, or Codex). Then use commands or skills as you work: /discover for ideation and assumption testing, /strategy for business models and vision, /write-prd for PRDs, /plan-launch for go-to-market, /north-star for metrics. Commands suggest the next relevant command after completing, so workflows flow naturally. Output: structured decisions (roadmaps, strategy docs, launch plans, personas, positioning) rather than open-ended text.

Included Skill Groups

What's the biggest win?

Product decisions improve because every decision point invokes a named framework (not ad-hoc thinking), frameworks surface risky assumptions cheaply (not late), and context flows between stages (discovery informs strategy informs execution).

What's required to run this?

Requires Claude Cowork, Claude Code (CLI), Codex CLI, or another AI assistant supporting plugin marketplaces. Claude Code needs Node.js and git. Non-CLI tools copy skills to local .gemini/skills, .cursor/skills, etc. All 68 skills work across platforms; only /slash commands are Claude-specific.

What should I watch out for?

Slash commands (/discover, /write-prd, etc.) run natively on Claude Cowork and Code only. Codex users install plugins but invoke workflows as skill references (no /slash syntax). Commands can be converted to Codex skills with effort. Some Windows versions of Claude Cowork may require a CoworkVMService restart.

Key Features

9 PM Domains

Discovery, Strategy, Execution, Market Research, Data Analytics, Go-to-Market, Product Marketing, Toolkit, and AI Shipping.

Framework-Driven Skills

Each skill encodes a proven PM method (Opportunity Solution Tree, Lean Canvas, RICE, Jobs to Be Done, pre-mortem, Porter's Five Forces, etc.).

Chained Commands

Workflows chain 2-4 skills together (e.g., /discover chains brainstorm-ideas → identify-assumptions → prioritize-assumptions → brainstorm-experiments).

Multi-AI Compatible

Full support for Claude Cowork and Code with slash commands. Codex and other AI assistants use skills directly (no slash command support).

PM-Specific Documentation

AI Shipping Kit documents vibe-coded apps, audits security/performance, and maps test coverage for code reviewability.

Tools in this Blueprint

Claude logo
4.4(68 reviews)
Cowork
Claude logo
4.6(456 reviews)
Gemini logo
4.4(604 reviews)

About This Blueprint

License
MIT
Industry
Technology
Skills
9 workflows, 68 sub-skills, 0 standalone
Sales

ICP-Filtered Outreach Lists from G2 Buyer Intent

Stop wasting rep time on weak intent signals and mismatched accounts. The workflow ranks ICP-fit buyers by readiness, finds the right contact, and supplies tailored outreach angles for the strongest opportunities.

ID

Ishani D.

Account Manager

Customer Experience

Answer pre-purchase questions to convert hesitant shoppers with AI

Shoppers get accurate answers about fit, compatibility, ingredients, and delivery even when your team is offline, so fewer leave before checkout. Conversation insights also reveal which product-page details could prevent the next unanswered question.

UB

Urska B.

GTM Lead

Customer Experience

Find the root cause behind repeat support tickets with AI

Catch a few unusual tickets before a product or fulfillment issue turns into hundreds of refunds, chargebacks, and bad reviews. Cluster transcript evidence by SKU, order date, location, and carrier so operations can trace the cause and support can reach affected customers early.

UB

Urska B.

GTM Lead