agentsclimarketplace
Sign in

Analyze growth

Skill VRymarovich/product-launch-os/plugins/product-launch-os/skills/analyze-growth

Analyze product growth through acquisition, activation, engagement, retention, monetization, referral, and experiment design. Use for funnel analysis, analytics plans, KPI definitions, growth reviews, prioritizing experiments, diagnosing conversion problems, or deciding what to measure next.From its SKILL.md

Install
npx -y skills add VRymarovich/product-launch-os --skill analyze-growth

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.6 KB, 267 tokens by cl100k_base, as published. Nobody here has run it

Analyze Growth

Find the highest-leverage constraint in the product funnel and design measurable experiments.

Workflow

  1. Read docs/product/metrics.md, product events, analytics integrations, entitlements, acquisition surfaces, onboarding, and docs/product/roadmap.md.
  2. Define the funnel in user behaviors, with clear event names and identity boundaries.
  3. Audit data quality before interpretation: missing events, duplicates, anonymous/authenticated joins, time windows, and denominators.
  4. Locate the largest meaningful drop or uncertainty across acquisition, activation, engagement, retention, monetization, and referral.
  5. Segment by source, platform, cohort, use case, account state, and product version where possible.
  6. Generate experiments tied to a causal hypothesis and one primary metric.
  7. Rank experiments by impact, confidence, effort, speed of learning, and downside.
  8. Define guardrail metrics and stop conditions.
  9. Update docs/product/metrics.md and docs/product/roadmap.md.

Read references/growth-review.md for the review template.

Guardrails

  • Never infer causality from a single aggregate correlation.
  • Do not report metrics without a time window and denominator.
  • Prefer retention and repeated value over raw installs or page views.

What ships with it: 2 files

561 B alongside SKILL.md

agents/

references/

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.