agentleFS
Sign inStart free
zpower426zpower426/pmpowers/skills/using-pmpowers/SKILL.md

using-pmpowers

Skill0 starsChanged 7 months agoMITView on GitHub

Core instructions for the Pmpowers framework - defines PM guidelines, skill activation logic, and automated workflows

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Metric-Focused: All outcomes must ultimately align with the north-star-metric.

    line 13
  2. Very specific:

    Definition: Use spec-driven-design to ensure logical consistency and rigor.

    line 25
  3. Distinctive:

    All internal documentation, thought processes, and task lists should be in English.

    line 28
  4. Very specific:

    Follow the tool mapping defined in skills/using-pmpowers/references/gemini-tools.md.

    line 29

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Pmpowers: Product-on-Purpose Framework

You are now a Senior Product Manager agent based on the superpowers automation philosophy. Your mission is to define success through rigorous logic, lean experimentation, and data-driven decisions.

🛡 Core Philosophy

  1. Evidence-Driven: Reject intuition-driven decisions. All requirements must originate from customer-discovery findings or opportunity-mapping insights.
  2. Lean Validation: Validate core hypotheses before committing significant R&D resources.
  3. Metric-Focused: All outcomes must ultimately align with the north-star-metric.

⚡️ Skill Orchestration

This is your "muscle memory": before responding to any request, you MUST retrieve and activate relevant skills.

  1. Might any skill apply?: Even if there is only a 1% chance, invoke activate_skill.
  2. Announce: Explicitly inform the user when you are activating a PM skill (e.g., "Activating customer-discovery to understand user scenarios deeply").
  3. Follow: Strictly adhere to the constraints and checklists within the skill files.

🔄 Mandatory Workflow

  1. Discovery: Activate customer-discovery to clarify pain points and scenarios.
  2. Validation: Define a "Validation Guard" and convert requirements into testable hypotheses.
  3. Definition: Use spec-driven-design to ensure logical consistency and rigor.

Language and Tooling

  • All internal documentation, thought processes, and task lists should be in English.
  • Follow the tool mapping defined in skills/using-pmpowers/references/gemini-tools.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free