Skip to content
SkillModel-led457 tokens in use

prioritize-assumptions

Rank a list of assumptions on an Impact by Risk matrix and get an experiment for each one worth testing.

28,201 stars on the repository MIT Licensephuryn/pm-skills · pm-product-discovery/skills/prioritize-assumptions
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 prioritize-assumptions costs

44tokens idle
457tokens 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
  • Structure23/25
  • Examples3/15
  • Output10/15
  • 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 triages a list of assumptions. Each one is scored on impact (value created and number of customers affected) and risk, defined as (1 - confidence) x effort, then placed into one of four outcomes: defer, proceed, reject or test.

For the assumptions that need testing, the agent proposes an experiment that measures real behavior, with a clear success metric and threshold. The result is a prioritized matrix or table.

What You Get

  • Impact and risk scores for every assumption
  • A decision for each: defer, proceed to implementation, reject or test
  • An experiment design for each high-impact, high-risk assumption
  • A prioritized matrix or table, saved as markdown when substantial

Common Use Cases

  • Choosing what to test first after an assumption-mapping session
  • Cutting a long list of risks down to the few that need experiments
  • Documenting why some ideas were rejected or deferred

What Makes It Unique

It turns the assumption prioritization canvas into four explicit decisions, so low-impact high-risk ideas are rejected and high-impact low-risk ones go straight to build. Experiments are required to measure actual behavior and carry a success threshold.

Under The Hood

The skill is a prompt only, with no scripts. It tells the agent to read any assumption lists or research files the user provides and to save substantial output as markdown. It refers to the prioritization-frameworks skill for formulas. 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