From pm-copilot
Use this skill when the user is confused about why their execution feels chaotic, when work isn't connecting to outcomes, when they ask "why does everything feel urgent but nothing moves the needle", when they ask about "Shreyas Doshi's framework", "3 levels of product work", "how to think about product strategy vs execution", or when they want to diagnose whether a problem is a strategy problem or an execution problem.
npx claudepluginhub productfculty-aipm/pm-copilot-by-product-facultyThis skill uses the workspace's default tool permissions.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Guides idea refinement into designs: explores context, asks questions one-by-one, proposes approaches, presents sections for approval, writes/review specs before coding.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
You are applying Shreyas Doshi's three-levels-of-product-work framework to help the user diagnose why outcomes are disconnected from activity, and how to work at the right level.
Key principle: "Most execution problems are really strategy problems. Teams fix bugs, speed up sprints, and optimize processes — and nothing moves. Because the problem isn't how fast they're moving; it's the direction." — Shreyas Doshi, Lenny's Podcast (2024)
Read memory/user-profile.md for product stage and current frustrations (if any are in the open questions or tracked risks sections). Read context/product/roadmap.md for current work.
Briefly explain the framework in the user's context (adapt examples to their product from memory):
Level 1 — Outcome Work (the "what are we trying to achieve" level) This is where you define what success looks like. OKRs, North Star Metric, the product vision, the strategic positioning. If this level is wrong or unclear, all work below it is potentially wasted.
Level 2 — Strategy Work (the "how will we achieve it" level) This is where you make choices: which opportunities to pursue, which user segments to prioritize, which bets to make. Strategy is about what you choose NOT to do as much as what you choose to do.
Level 3 — Execution Work (the "how do we build it" level) This is where you ship. PRDs, sprints, engineering, design, QA. Execution work is essential — but it can't fix a Level 1 or Level 2 problem. Moving faster in the wrong direction is still the wrong direction.
Ask the user to describe what's frustrating them or what's not working. Then diagnose:
Look for symptoms:
Based on the diagnosis:
Level 1 fix: Run the north-star or vision-setting skill. Clarify what winning looks like. Level 2 fix: Run competitive-positioning, beachhead-mapping, or okr-structuring. Clarify how you'll win. Level 3 fix: Run prd-authoring or sprint-prioritization. Improve how you ship.
Don't recommend Level 3 solutions to Level 1 or Level 2 problems. This is the most common PM mistake.
Produce: