Opportunity Solution TreeSAFE

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: opportunity-solution-tree
argument-hint: "[stakeholder request or outcome]"
description: Build an Opportunity Solution Tree from outcomes to opportunities, solutions, and tests. Use when a stakeholder request needs problem framing before you decide what to build.
intent: >-
  Guide product managers through creating an Opportunity Solution Tree (OST) by extracting target outcomes from stakeholder requests, generating opportunity options (problems to solve), mapping potential solutions, and selecting the best proof-of-concept (POC) based on feasibility, impact, and market fit. Use this to move from vague product requests to structured discovery, ensuring teams solve the right problems before jumping to solutions—avoiding "feature factory" syndrome and premature convergence on ideas.
type: interactive
theme: discovery-research
best_for:
  - "Turning a stakeholder feature request back into a problem worth solving"
  - "Connecting a desired outcome to opportunities, solutions, and tests"
  - "Showing why one solution was chosen over the alternatives"
scenarios:
  - "A stakeholder asked for a specific feature and I want to reframe it as a problem first"
  - "I need to show leadership why we picked this solution over the three alternatives"
estimated_time: "30-45 min"
---


## Purpose
Guide product managers through creating an Opportunity Solution Tree (OST) by extracting target outcomes from stakeholder requests, generating opportunity options (problems to solve), mapping potential solutions, and selecting the best proof-of-concept (POC) based on feasibility, impact, and market fit. Use this to move from vague product requests to structured discovery, ensuring teams solve the right problems before jumping to solutions—avoiding "feature factory" syndrome and premature convergence on ideas.

This is not a roadmap generator—it's a structured discovery process that outputs validated opportunities with testable solution hypotheses.

## Input

**Works best with:** The stakeholder request or the target outcome you're starting from.
**Also useful:** Customer evidence you already have, constraints, and solutions already being pushed.

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 skill opens by asking for the request or desired outcome, then extracts the measurable target outcome from it.

**Example invocation:** `Build an OST from this request: 'Sales says we need a mobile app because competitors have one.'`

## Key Concepts

### What is an Opportunity Solution Tree (OST)?

An OST is a visual framework (Teresa Torres, *Continuous Discovery Habits*) that connects:
1. **Desired Outcome** (business goal or product metric)
2. **Opportunities** (customer problems, needs, pain points, or desires that could drive the outcome)
3. **Solutions** (ways to address each opportunity)
4. **Experiments** (tests to validate solutions)

**Structure:**
```
         Desired Outcome (1)
                |
    +-----------+-----------+
    |           |           |
Opportunity  Opportunity  Opportunity (3)
    |           |           |
  +-+-+       +-+-+       +-+-+
  | | |       | | |       | | |
 S1 S2 S3    S1 S2 S3    S1 S2 S3 (9 total solutions)
```

### Why This Works
- **Outcome-driven:** Starts with business goal, not feature requests
- **Divergent before convergent:** Explores multiple opportunities before picking solutions
- **Problem-focused:** Opportunities are problems, not solutions disguised as problems
- **Testable:** Each solution maps to experiments, not just "build it and ship"
- **POC selection:** Evaluates feasibility, impact, market fit before committing resources

### Anti-Patterns (What This Is NOT)
- **Not a feature list:** Opportunities are problems customers face, not "we need dark mode"
- **Not solution-first:** Don't start with "we should build X"—start with "customers struggle with Y"
- **Not waterfall planning:** OST is a discovery tool, not a project plan
- **Not a one-time exercise:** OSTs evolve as you learn from experiments

### When to Use This
- Stakeholder requests a feature or product initiative
- Starting discovery for a new product area
- Clarifying vague OKRs or strategic goals
- Prioritizing which problems to solve first
- Aligning team on what outcomes you're driving

### When NOT to Use This
- When the problem is already validated (move to solution testing)
- For tactical bug fixes or technical debt (no discovery needed)
- When stakeholders demand a specific solution (address alignment issues first)

---

### Facilitation Source of Truth

Use [`workshop-facilitation`](../workshop-facilitation/SKILL.md) as the default interaction protocol for this skill.

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 domain-specific assessment content. If there is a conflict, follow this file's domain logic.

## Application

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

This interactive skill follows a **two-phase process**:

**Phase 1:** Generate OST (extract outcome, identify opportunities, map solutions)
**Phase 2:** Select POC (evaluate solutions, recommend best starting point)

---

### Step 0: Gather Context (Before Questions)

**Agent suggests:**

Before we create your Opportunity Solution Tree, let's gather context:

**Stakeholder Request or Product Initiative:**
- What did the stakeholder ask for? (Feature request, product idea, strategic goal)
- Any existing materials: PRD drafts, OKR documents, str

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.