Back to directory

PM Skills Marketplace

A marketplace of Claude Code and Cowork skills, commands and plugins that guide a product manager through discovery, strategy, execution, launch and growth using established PM frameworks.

PM Skills Marketplace

PM Skills Marketplace packages product management frameworks as skills, commands and plugins for Claude Code, Cowork and other AI assistants. It includes 69 skills and 42 chained workflows across 9 plugins, covering the product lifecycle from discovery to strategy, execution, launch and growth.

A skill gives the agent domain knowledge, an analytical framework, or a guided workflow for a specific product management task, and loads automatically when relevant to the conversation, or can be invoked explicitly by name. A command is a user-triggered workflow that chains several skills into an end-to-end process; for example, a discovery command chains brainstorming, assumption identification, assumption prioritization and experiment brainstorming. A plugin groups related skills and commands for one product management domain, and installing the marketplace installs all nine plugins at once.

It is designed for Claude Code and Cowork, with skills also usable by other AI assistants, and is licensed under the MIT license.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.