Skip to content
SkillModel-led843 tokens in use

opportunity-solution-tree

Build an Opportunity Solution Tree that links one desired outcome to customer opportunities, candidate solutions and fast experiments.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-product-discovery/skills/opportunity-solution-tree
claude plugin install pm-product-discovery@pm-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing opportunity-solution-tree costs

60tokens idle
843tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure25/25
  • Examples0/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Good
  • Development activity80
  • Maintenance76
  • Community60
  • Maturity32
  • Momentum40

This skill structures product discovery with Teresa Torres’ Opportunity Solution Tree. It starts from a single measurable outcome, maps three to seven customer opportunities from the research provided, ranks them with an Opportunity Score, generates at least three solutions for each top opportunity and designs experiments to test the best ones.

The tree is presented as a clear hierarchy and saved as markdown when it is large.

What You Get

  • A four-level tree: outcome, opportunities, solutions and experiments
  • Opportunities ranked by Opportunity Score or a qualitative assessment
  • At least three solution ideas for each prioritized opportunity
  • One or two experiments per promising solution, each with a success threshold

Common Use Cases

  • Turning interview and survey findings into a map of customer needs
  • Choosing what to build next for a retention or activation goal
  • Reviewing a roadmap that jumps straight to solutions

What Makes It Unique

It carries the principles of continuous discovery in the prompt: one outcome at a time, opportunities and not features, at least three solutions before choosing, and weekly updates. The README lists it as a standalone reference that Claude draws on whenever relevant, so no command is needed.

Under The Hood

The skill is a prompt only, with no scripts. It tells the agent to use the outcome and any research data the user provides, such as interviews, surveys or analytics exports, and to save the tree as markdown if it is large. It makes no web or API calls and runs no commands.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers