Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
A product-management library organized across discovery, definition, delivery, measurement, and iteration. Templates and sample outputs give agents a concrete quality reference, while workflows connect individual skills into larger pieces of work.
WHO IT'S FOR
AI agent / automation builders
implementing product management capabilities in AI agents
Product Managers
standardizing AI-driven product discovery and delivery
Technical leads / architects
designing AI agent workflows with strict output contracts
AI agent power users
enhancing Claude or Codex with PM-specific skillsets
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Installs: All 68 PM-Skills skills, installed from the repository's skills directory into the agent's default skills directory. · Claude Code, Cursor, GitHub Copilot, Cline
Before you start
An environment capable of running npx
An agent supporting the skills ecosystem
Run this command in a terminal to install the full skill library using the skills CLI.
Notes describing one initiative and its affected user segment
Available research, support tickets, or behavioral data
Business context, metric baselines and targets, and known constraints
Use define-problem-statement to turn my notes into a concise problem statement for one initiative. Identify the affected user segment, pain points, business impact, success metrics with baselines and targets, constraints, and open questions. Keep the framing focused on the problem rather than prescribing a solution, and ask about missing evidence.
An agreed problem statement or concise problem summary
The proposed solution and essential capabilities
Success targets, scope limits, alternatives considered, risks, and potential owners
Use develop-solution-brief to draft a one-page brief for my proposed solution to an agreed problem. Include a short problem recap, the proposed solution, 3–5 essential features, measurable success criteria, trade-offs, risks and mitigations, and 3–5 immediate next steps. Use clear language suitable for stakeholder review.
A changelog, completed tickets, or pull request descriptions for one release with user-visible changes
Known issues or limitations
Product and audience context
Use deliver-release-notes to draft customer-facing release notes for this release from my changelog. Select 1–3 highlights, translate technical changes into user benefits, and group the remaining items into New Features, Improvements, and Bug Fixes. Keep each item to 1–2 sentences and acknowledge supplied known issues. Return a draft for review.