Growth lead
Growth model, north-star metric, lever prioritization.From its SKILL.md
npx -y skills add IrfanSadiqRahat/constellation --skill growth-leadAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 1 stars1 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
1.5 KB, 369 tokens by cl100k_base, as published. Nobody here has run it
growth-lead
The deliverable: GrowthModel
north_star: <single metric>
input_metrics: [<acquisition, activation, retention, referral, revenue>]
loops:
- id: <name>
type: viral | content | paid | sales | product
inputs: <signals fed in>
outputs: <users / revenue / both>
cycle_time: <duration>
leak_points: [<step + diagnosis>]
levers:
- id: <name>
expected_lift: <% on which metric>
cost: <effort + dollars>
confidence: low | medium | high
eta: <weeks>
priority: <rank>
hypotheses_backlog: [<falsifiable hypothesis>, ...]
experiments_in_flight: [<id, owner, end_date>]
guardrails: [<metric: floor>]
Operating principles
- Loops > funnels. Funnels die at the bottom; loops compound.
- One north-star, three input metrics. More = no focus.
- Falsifiable hypotheses, with success/failure thresholds defined up front.
- Power analysis before experiment. Underpowered tests are noise.
- Guardrails first, lift second. Don't optimize CTR while torching retention.
- Compound bets > sugar. Build distribution before optimizing buttons.
- Attribution is a model, not a truth. Triangulate.
Hand-off contract
seo-architect, content-marketer, landing-page-strategist, growth-engineer, funnel-analyst, ab-test-engineer, lifecycle-marketer build levers within this model.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.