Skip to content
SkillModel-led1,374 tokens in use

value-curve

Score your product and its alternatives on one segment's top needs plus price, and draw a value curve that shows where you must be far ahead.

680 stars on the repository MIT Licensephuryn/product-engineering · product/skills/value-curve
claude plugin install product@product-engineering
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing value-curve costs

31tokens idle
1,374tokens in use
1,483tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. 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
  • Frontmatter8/15
  • Structure25/25
  • Examples3/15
  • Output10/15
  • Size15/15
  • Resources15/15

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 activity100
  • Maintenance100
  • Community44
  • Maturity4
  • Momentum40

value-curve compares offerings on the factors one customer segment values. It comes from Blue Ocean Strategy by W. Chan Kim and Renée Mauborgne, and asks whether your offering meets this segment’s needs far better than anything else they can use.

The agent scores needs with Dan Olsen’s opportunity formula, picks five to seven factors, scores each offering from 0 to 100, draws the curve and writes what it means. Where no interviews exist, every score is labelled an assumption.

What You Get

  • A table of factors by offerings, each score with its source
  • A chart with one line per offering and a legend
  • A reading that says where to be far ahead, where parity is enough and what to leave out on purpose
  • The weakest assumptions behind the curve, as what to test next

Common Use Cases

  • Comparing a product with competitors on one segment’s needs
  • Choosing what to be best at
  • Supplying the Alternatives part of a value proposition
  • Finding out what to test with customers when no interviews exist yet

What Makes It Unique

The skill scores needs and not features, caps the curve at seven factors, keeps one segment per curve, and requires every score to cite a source or say it is an assumption. It treats must-haves as parity factors, so a low opportunity score does not remove them. A worked streaming example shows the table and reading. It feeds the value-proposition skill.

Under The Hood

The skill is a SKILL.md of instructions, plus a receipts.md file recording where each rule came from. It has no scripts. The agent reasons from what customers said, reviews and websites you give it, and draws the chart in whatever way the agent can. The skill does not tell the agent to fetch pages, call services, run commands or write files.

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