Product Strategy SessionSAFE

Product Management skills framework built on battle-tested methods for Claude Code, Cowork, Codex, and AI agents.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: product-strategy-session
argument-hint: "[product or strategic question]"
description: Run an end-to-end product strategy session across positioning, discovery, and roadmap planning. Use when a team needs validated direction before committing to execution.
intent: >-
  Guide product managers through a comprehensive product strategy session by orchestrating positioning, problem framing, customer discovery, and roadmap planning skills into a cohesive end-to-end process. Use this to move from vague strategic direction to concrete, validated product strategy with clear positioning, target customers, problem statements, and prioritized roadmap—ensuring alignment across stakeholders before committing to execution.
type: workflow
theme: strategy-positioning
best_for:
  - "Running a full strategy arc from positioning through roadmap"
  - "Giving a team validated direction instead of a feature list"
  - "Aligning leadership on where the product is going and why"
scenarios:
  - "Our team has a backlog but no direction and leadership wants a strategy"
  - "We need to go from positioning through discovery to a roadmap people believe"
estimated_time: "2-4 weeks"
---


## Purpose
Guide product managers through a comprehensive product strategy session by orchestrating positioning, problem framing, customer discovery, and roadmap planning skills into a cohesive end-to-end process. Use this to move from vague strategic direction to concrete, validated product strategy with clear positioning, target customers, problem statements, and prioritized roadmap—ensuring alignment across stakeholders before committing to execution.

This is not a one-time workshop—it's a repeatable process for establishing or refreshing product strategy, typically spanning 2-4 weeks with multiple touchpoints.

## Input

**Works best with:** The product (or product line) and the strategic question forcing the session.
**Also useful:** Existing positioning, discovery artifacts, roadmap drafts, and who needs to align on the outcome.

Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended `ARGUMENTS:` line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.

**Arriving empty-handed? That works too.** The workflow starts at positioning and orchestrates the phases from there — supplied artifacts let it skip ahead.

**Example invocation:** `Run a strategy session for our analytics add-on: flat adoption, two competing roadmap visions, exec review in 4 weeks.`

## Key Concepts

### What is a Product Strategy Session?

A product strategy session is a structured, multi-phase process that takes a product from strategic ambiguity to validated direction. It orchestrates:

1. **Positioning & Market Context** — Define who you serve, what problem you solve, and how you're differentiated
2. **Problem Discovery & Validation** — Frame and validate customer problems through research
3. **Solution Exploration** — Generate opportunity solutions and prioritize based on impact
4. **Roadmap Planning** — Sequence epics and releases based on strategy

### Why This Works
- **Structured discovery:** Prevents jumping to solutions before understanding problems
- **Stakeholder alignment:** Creates shared mental model across exec, product, design, engineering
- **Validated strategy:** Tests assumptions before committing resources
- **Executable roadmap:** Connects high-level strategy to concrete work

### Anti-Patterns (What This Is NOT)
- **Not a feature brainstorm:** Strategy sessions frame problems, not just list features
- **Not waterfall planning:** Builds in feedback loops and iteration
- **Not a solo PM exercise:** Requires cross-functional participation

### When to Use This
- Launching a new product or major initiative
- Annual/quarterly strategic planning cycles
- Repositioning an existing product
- Onboarding new product leaders (align on strategy)

### When NOT to Use This
- When strategy is already clear and validated
- For tactical feature additions (no strategic shift needed)
- When you lack executive sponsorship (strategy won't stick)

---

### Facilitation Source of Truth

When running this workflow as a guided conversation, use [`workshop-facilitation`](../workshop-facilitation/SKILL.md) as the interaction protocol.

It defines:
- session heads-up + entry mode (Guided, Context dump, Best guess)
- one-question turns with plain-language prompts
- progress labels (for example, Context Qx/8 and Scoring Qx/5)
- interruption handling and pause/resume behavior
- numbered recommendations at decision points
- quick-select numbered response options for regular questions (include `Other (specify)` when useful)

This file defines the workflow sequence and domain-specific outputs. If there is a conflict, follow this file's workflow logic.

## Application

Use `template.md` for the full fill-in structure.

This workflow orchestrates **6 phases** over **2-4 weeks**, using multiple component and interactive skills.

---

## Phase 1: Positioning & Market Context (Week 1, Days 1-2)

**Goal:** Define target customer, problem space, and differentiation.

### Activities

**1. Run Positioning Workshop**
- **Use:** `skills/positioning-workshop/SKILL.md` (interactive)
- **Participants:** PM, product leadership, marketing, sales
- **Duration:** 90 minutes
- **Output:** Draft positioning statement

**2. Define Proto-Personas**
- **Use:** `skills/proto-persona/SKILL.md` (component)
- **Participants:** PM, design, customer-facing teams
- **Duration:** 60 minutes
- **Output:** 1-3 proto-personas (hypothesis-driven)

**3. Map Jobs-to-be-Done**
- **Use:** `skills/jobs-to-be-done/SKILL.md` (component)
- **Participants:** PM, design
- **Duration:** 60 minutes
- **Output:** JTBD statements for each persona

### Decision Point 1: Do we have enough customer context?

**If YES:** Proceed to Phase 2 (Problem Framing)

**If NO:** Run additional discovery:
- **Use:** `skills/discovery-in

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

pinned

Secrets in source

none-found

Findings (0)

No findings outside the package's declared scope.

Gates applied: no_behavioural_pass.