Skip to content
SkillModel-led395 tokens in use

identify-assumptions-existing

Stress-test a feature idea for an existing product by listing risky assumptions across value, usability, viability and feasibility.

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

59tokens idle
395tokens 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
  • Examples0/15
  • Output0/15
  • 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 runs a devil’s advocate review of a feature idea for a product that already exists. It looks at the idea from the product manager, designer and engineer points of view and lists what could go wrong in four risk areas: value, usability, viability and feasibility.

For each assumption it notes what could fail, how confident the team is (high, medium or low) and a way to test it. The aim is to strengthen the idea before work starts.

What You Get

  • A list of risky assumptions grouped by value, usability, viability and feasibility
  • A confidence rating of high, medium or low for each assumption
  • A suggested way to test each assumption
  • Input that feeds directly into assumption prioritization

Common Use Cases

  • Stress-testing a feature idea before it enters the roadmap
  • Preparing assumptions for an assumption-mapping workshop
  • Running a quick risk assessment on a PRD or design the team already has

What Makes It Unique

It is scoped to features in an existing product, so it uses the four classic product risks and a three-perspective devil’s advocate pass. Its sibling skill for new products widens the list to eight categories. The tone is constructive: the goal is to strengthen the idea.

Under The Hood

The skill is a prompt only. It ships no scripts and runs no commands. It tells the agent to read any files the user supplies (designs, PRDs, research) and then reason step by step. It does not call web services, fetch pages or write files of its own.

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