無料GitHub で公開

opportunity-solution-tree

Build Opportunity Solution Trees using Teresa Torres' framework for structured product discovery. Use this skill when: - You need to map a desired outcome to opportunities, solutions, and experiments - You want to decide WHAT to build next based on user research and discovery data - You have workshop findings, pilot feedback, or user research to structure into actionable options - You need a visual tree diagram showing the path from outcome to testable experiments

qa-aman/claude-skills

インストール方法を見る

含まれるファイル（1）

SKILL.md4.0 KB

SKILL.md（原文）

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Opportunity Solution Tree

Interactive skill that builds an OST (Teresa Torres' framework). Maps: Desired Outcome -> Opportunities -> Solutions -> Experiments.

Workflow

Define outcome — Ask user, or read from spec success metrics / roadmap goals
Read input data — Workshop findings, pilot feedback, user research, feedback files
Identify opportunities — Unmet needs and pain points from the data
Brainstorm solutions — 2-3 solutions per opportunity
Define experiments — 1-2 validation experiments per solution
Build tree — Mermaid diagram + detailed breakdown
Output — Print to conversation or write to file

The 4 Levels

Level 1: Desired Outcome

The measurable business/product outcome.

Must be specific and measurable: "Increase WAU/MAU ratio by 15%"
Pull from spec success metrics or roadmap goals
One tree per outcome

Level 2: Opportunities

Unmet needs, pain points, desires — NOT solutions.

Frame as user needs: "Users lose motivation after breaks"
Or as "How might we..." questions
Pull from: workshops, feedback, pilot data, persona pain points
3-5 opportunities per outcome

Level 3: Solutions

Feature ideas that address specific opportunities.

Each solution addresses ONE opportunity
2-3 solutions per opportunity (avoid fixating on one idea)
Can include features already on the roadmap
Name concretely: "Recovery Mechanic" not "engagement improvement"

Level 4: Experiments

How to validate each solution before building.

Types: prototype test, A/B test, user interview, pilot, data analysis, fake door test
Each experiment has: hypothesis, method, success criteria, effort level
1-2 experiments per solution

Output Format

# Opportunity Solution Tree — {Outcome}

**Date:** {DD-MM-YYYY}
**Desired Outcome:** {specific measurable outcome}

## Tree Diagram

```mermaid
graph TD
  O["Outcome: Increase retention by 15%"]
  O --> OP1["Users lose motivation after breaks"]
  O --> OP2["Parents unaware of progress"]
  OP1 --> S1["Recovery mechanic"]
  OP1 --> S2["Progress protection"]
  OP2 --> S3["Parent dashboard"]
  S1 --> E1["Pilot with 50 users"]
  S2 --> E2["User interviews"]
  S3 --> E3["Parent survey"]

Detailed Breakdown

Opportunity 1: {description}

Source: {workshop/feedback/pilot} Evidence: {supporting data}

Solution 1a: {name}

Description: {brief}
Effort: Low/Medium/High
Experiment:
- Hypothesis: If we {action}, then {expected result}
- Method: {prototype/interview/pilot/data analysis}
- Success Criteria: {measurable threshold}
- Effort: {days/weeks}

Priority Matrix

Solution	Opportunity	Confidence	Effort	Priority
{name}	{which}	H/M/L	H/M/L	{1-N}

Recommended Next Steps

{highest priority experiment to run first}
{second priority}
{third priority}


## Anti-Patterns

- Don't jump to solutions without defining opportunities first
- Don't have only one solution per opportunity — that's not discovery, that's a feature request
- Don't skip experiments — untested solutions are guesses
- Don't define vague outcomes — "improve engagement" is not measurable

## Quality Checklist

- [ ] Outcome is specific and measurable
- [ ] Opportunities are user needs, not solutions in disguise
- [ ] Each opportunity has 2-3 solutions
- [ ] Each solution has at least 1 experiment
- [ ] Mermaid tree diagram is included
- [ ] Priority matrix ranks solutions

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

ログインしてレビューを書く

同じリポジトリのスキル

概要と使いどころ

11-star-framework

無料

Rate any product, feature, or experience on the 11-star scale (Brian Chesky's Airbnb thought experiment). Use when user says "rate this experience", "11-star", "star rating", "experience audit", "how good is this", "experience rating", "product audit", "quality assessment", or wants to evaluate product quality and identify improvement paths. Also trigger when user wants to benchmark a feature, assess where a product stands, or map out what "great" looks like - even if they don't explicitly say "11-star".

日本語の概要は準備中です。原文の説明を表示しています。