Skip to content

Opportunity Solution Tree

Structure product discovery by mapping an outcome to opportunities, solutions and experiments

Stars
27,616
Licence
MIT
Files
1 file

What it does

When installed, the agent helps a product team lay out an Opportunity Solution Tree, a visual framework from Teresa Torres' Continuous Discovery Habits. It starts from one measurable desired outcome, groups customer problems (opportunities) beneath it, ranks them with an Opportunity Score, and proposes several solutions and quick experiments for the top ones. The result is a hierarchical map that helps a team decide what to build next instead of jumping straight to features.

Great for

  • Product managers running continuous discovery
  • Product trios (PM, designer, engineer) planning what to build next
  • Students or teams learning the Opportunity Solution Tree method

Skip it if

  • Teams with no customer research data, since the framework depends on real opportunities, and the output would be guesswork
  • Projects needing a finished product spec or code, because the skill only structures discovery thinking

Try asking

  • “Build an opportunity solution tree for increasing 7-day retention to 40%”
  • “Map my customer interview notes into opportunities and rank them”
  • “Generate three solutions and two experiments for the top onboarding pain point”
Step-by-step guide: how to use Opportunity Solution TreeInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    opportunity-solution-tree.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip opportunity-solution-tree.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip opportunity-solution-tree.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent a single, measurable outcome and your raw research (interview notes, survey results, analytics) so opportunities come from evidence.
  • Ask for at least three solutions per opportunity and review them with engineers and designers, as the method recommends.
  • Save the output as markdown and update the tree weekly as new learning arrives.

What's inside

  • SKILL.md

Redistributed unmodified from phuryn/pm-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.