Skip to content
SkillModel-led1,198 tokens in use

growth-loops

Compare the five growth loop types, choose the one that fits your product, and get its conversion chain and a first measurable test.

680 stars on the repository MIT Licensephuryn/product-engineering · product/skills/growth-loops
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 growth-loops costs

27tokens idle
1,198tokens 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
  • Frontmatter8/15
  • Structure17/25
  • Examples6/15
  • 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 activity100
  • Maintenance100
  • Community44
  • Maturity4
  • Momentum40

growth-loops guides an agent through designing one growth loop that compounds user acquisition through the product itself. It weighs five mechanisms (viral, usage, collaboration, user-generated and referral) for fit and picks the most promising.

The output names who acts, what their action produces and how that brings the next user, plus the first test. Estimates are marked as assumptions, and projections or a 30-60-90 day roadmap come only when the inputs support them.

What You Get

  • One chosen loop with the reasoning for choosing it
  • The conversion chain: who acts, what the action produces, how it brings the next user
  • Loop mechanics covering trigger, incentive, ease of sharing and invite-to-activation rate
  • A first measurable test that targets the step most likely to break

Common Use Cases

  • Designing product-led growth for a new product
  • Reducing reliance on paid acquisition
  • Judging whether a referral reward fits the unit economics
  • Analyzing how a competitor grows

What Makes It Unique

The skill asks for one loop mastered before others are added, and it separates measured inputs from assumptions before any projection is made. Rewards must come with their unit economics. It is the growth step in the product pack, updated beside a differently worded version in the pm-skills collection.

Under The Hood

The skill is one SKILL.md of instructions, with a table of the five loop types and their examples. It has no scripts and no linked files. The agent reasons from the product context you pass in. 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