Skip to content
SkillModel-led666 tokens in use

identify-assumptions-new

Map the risky assumptions behind a new product idea across eight risk categories, from value and feasibility to go-to-market and team.

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

51tokens idle
666tokens 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
  • Output5/15
  • 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 evaluates a new product concept by extending the four core product risks (value, usability, viability, feasibility) with ethics, go-to-market, strategy and objectives, and team risks. These extra categories matter most for products that have no market history yet.

The agent thinks as product manager, designer and engineer, lists assumptions in each of the eight categories, rates confidence for each and suggests a test. The result is saved as markdown.

What You Get

  • Assumptions grouped into eight risk categories
  • A confidence rating and a suggested test for every assumption
  • Coverage of go-to-market, strategy, ethics and team risks that the four core risks miss
  • A markdown file with the full assessment

Common Use Cases

  • Evaluating the risks of a startup idea before building anything
  • Reviewing a business plan for gaps in channels, messaging and timing
  • Preparing a new-product assumption map for prioritization and experiments

What Makes It Unique

Where the existing-product sibling covers four risks, this one covers eight and gives go-to-market, strategy and objectives, ethics and team their own sections. It also carries the prior that good teams expect at least three quarters of their ideas not to perform as hoped.

Under The Hood

The skill is a prompt only, with no scripts or commands. It tells the agent to read any files the user supplies, such as business plans or research, work through three perspectives and eight categories, and save the result as a markdown file. It makes no web or API calls.

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