From pm-copilot
Use this skill when the user asks to "scope this to the happy path", "what's the minimum I need to prototype", "help me cut scope for prototyping", "what should I include in the prototype", "how do I decide what to prototype", or needs help deciding which parts of a feature to include in a prototype vs. which to defer. Also use at the start of any prototyping session to right-size the prototype scope.
npx claudepluginhub productfculty-aipm/pm-copilot-by-product-facultyThis skill uses the workspace's default tool permissions.
Dispatches parallel agents to independently tackle 2+ tasks like separate test failures or subsystems without shared state or dependencies.
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.
You are helping the user scope a prototype to the minimum needed for its purpose. Prototypes fail most often because they're over-scoped — too many screens, too many states, too much detail — which makes them slow to build, hard to iterate, and confusing to test.
Framework: Colin Matthews (prototype scope discipline), Shape Up (appetite-based scoping applied to prototypes).
Key principle: A prototype should contain only what's needed to answer the question it's designed to answer. Every screen and state beyond that is waste.
Before scoping, ask: what is this prototype for?
User testing: The prototype needs to be realistic enough that users can complete the task without confusion. Prioritize: realistic content, working flow, correct information architecture. De-prioritize: visual polish, error states, edge cases.
Stakeholder demo / alignment: The prototype needs to communicate the vision. Prioritize: key screens, the "wow moment", one complete flow. De-prioritize: completeness, all edge cases, mobile version.
Engineering spec / handoff: The prototype needs to demonstrate the interaction mechanics. Prioritize: interactive states, transitions, behavior on action. De-prioritize: visual perfection, backend-dependent behavior.
Team alignment / discussion: The prototype needs to ground a conversation. Prioritize: the two or three screens in dispute. De-prioritize: everything else.
The happy path is the sequence of steps where:
Map the happy path for the feature being prototyped:
This becomes the spine of the prototype. Everything else is a branch — don't prototype branches.
For each of the following, decide: In prototype or Out of prototype
| Element | Include? | Why |
|---|---|---|
| Auth / login flow | OUT | Start logged in. Auth is a solved problem. |
| Empty states | OUT | Use mock data instead. |
| Error messages / validation | OUT | Happy path only. |
| Loading states | OUT | Mock instant load. |
| Settings / configuration | OUT | Not in the happy path. |
| Admin / internal views | OUT | Not the user's journey. |
| Mobile responsive | OUT | Unless this IS a mobile test. |
| [Feature-specific element] | [In/Out] | [Reason] |
Force a minimum screen count:
For user testing: You need at least 3 screens (start state, mid-flow, success state). You rarely need more than 7.
For stakeholder demo: You need the "before" (the problem state) and the "after" (the solution working). 2–4 screens is typical.
For engineering spec: You need every unique interaction state. Count the number of distinct interactions, not screens.
If the prototype has more than 8 screens, scope it down until it fits. Prototype one flow completely rather than two flows partially.
Define the mock data needed to make the prototype feel real:
Produce:
This scope statement should be shared whenever the prototype is shared, to prevent misunderstanding about what's implemented.