Running growth experiments
Skill Giving-Back-Studio/growth-agent/skills/running-growth-experiments
Growth Agent — open-source skills that turn the AI you already use into a growth partner for your business, powered by Earth Care Network
npx -y skills add Giving-Back-Studio/growth-agent --skill running-growth-experimentsAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
3 things to look at
- 12 days oldThe repository was created 12 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 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.
- 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.
What its author says it does
Copied from the file, not written here
Reviews an Earth Care Network Growth Plan and turns its recommendations into armed, running automations. Use when someone wants a growth-plan checkup, asks what is confirmed versus open, wants to know what to work on next, or wants to automate their sales follow-up.
SKILL.md
2.9 KB, as published. Nobody here has run it
Running growth experiments
The Growth Plan is the living deliverable: story → offer → icp → signals → prospects → moves → automation_plan. This skill audits it and closes the gaps.
Audit
get_growth_plan returns the plan plus real metrics. Report plainly which
modules are confirmed, which are drafted but unconfirmed, and which are empty.
Do not describe an empty plan as a start — say it's empty.
The metrics block is the honest read on whether anything is working. Content created but never approved is not content shipped; say that when it's true.
Close gaps in order
Modules compound — an automation_plan is only as good as the icp under it.
Work the earliest open one first.
update_growth_plan_module— draft or revise. Only some modules are draftable here, and the parameter differs:content(a string) forstory/icp,payloadfortargets/channel_bets/challenges/agentic_solutions.offer,signals,prospects,moves, andautomation_planare confirm-only. There is novalueparameter — sending one writes nothing.confirm_growth_plan_module— after the owner approves it. Accepts all seven.
If icp is thin, stop and use refining-your-icp rather than drafting a weak
one inline.
Arm the automations
Confirming automation_plan returns 2-3 recommendations computed from that
business's own confirmed ICP, watchlists, and leads. These are computed, not
authored — narrate what comes back, don't invent additions.
create_workflow_from_template instantiates one as a draft. Templates
include daily-lead-digest, signal-inbox-digest, daily-gtm-followups,
sales-inquiry-pipeline, sales-follow-up-3day.
Say clearly: it is a draft, it does not run until they publish it, and nothing sends without their approval. A person who believes automation is live when it isn't will miss real leads.
Don't arm a template the plan didn't recommend. If they ask for one anyway, that's their call — just say it isn't grounded in their data.
Choosing what's next
When someone asks "what should I do?", answer from their data, not best practice in general:
- No confirmed ICP → that, before anything else.
- ICP confirmed, no watchlist → arm monitoring; it compounds while they sleep.
- Signals arriving, none triaged → triage; unread signals are worth nothing.
- Leads with no follow-up → drafts; the pipeline leaks here.
- All of the above healthy → then automate the repeated motion.
Name the one next action, not five. A person with five priorities has none.