From pm-copilot
Use this skill when the user asks to "escalate a risk", "write a risk escalation", "how do I tell leadership about this problem", "write a blocker update", "how do I escalate this issue", "draft a message about this risk", "communicate this blocker", or needs to surface a significant risk, blocker, or problem to leadership in a way that drives action rather than panic.
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 communicate a risk or blocker to leadership in a way that is clear, calm, and action-oriented. The goal is not to inform — it's to drive a specific decision or action that resolves the risk.
Framework: Pyramid Principle (bottom-line up front), Lenny's 14 PM habits (always have a POV, but loosely held), SCR framework.
Key principle: Never escalate a problem without a recommendation. Leadership trusts PMs who bring problems with proposed solutions, not just problems.
Read memory/user-profile.md for: the stakeholder being escalated to (their communication style, sensitivities, decision-making style), product context, and any existing tracked risks related to this escalation.
Before writing, clarify the situation:
What is the risk or blocker? (Specific, not vague — "the auth dependency won't be ready until [date]" not "there's a risk")
What is the impact if this isn't resolved? (Timeline slip? Metric miss? Customer commitment broken?)
What needs to happen for this to be resolved? (A decision? A resource? An unblocking action from a specific person?)
What are the options? (At least 2 options — including "do nothing" if that's a realistic option)
What is the recommendation? (PM's preferred option and reasoning)
When does a decision need to be made? (Be specific — if the deadline is soft, say so)
Use the SCR structure, calibrated for urgency:
For high urgency (decision needed in < 48 hours):
For medium urgency (decision needed in < 1 week):
For low urgency (FYI / heads up):
For medium/high urgency escalations, produce a clear options table:
| Option | Description | Pros | Cons | Recommendation |
|---|---|---|---|---|
| Option A | [e.g., Delay launch 2 weeks] | [Pros] | [Cons] | [Yes/No] |
| Option B | [e.g., Launch with reduced scope] | [Pros] | [Cons] | [Preferred — why] |
| Option C | [e.g., Do nothing, accept the risk] | [Pros] | [Cons] | [No — why] |
Always include "do nothing" as an option, even if to show why it's inadvisable.
From memory, apply the stakeholder's known preferences:
Produce:
memory/user-profile.md as a tracked risk