agentsclimarketplace
Sign in

Growth radar

Skill inflowave/skills/skills/growth-radar

A cross-domain correlation engine for an Inflowave account — pulls engagement, forms, workflows, pipeline, and revenue together to find what actually drives outcomes (and what's silently leaking money), then ranks concrete opportunities with the exact next action for each. Use when the user says "where's my biggest opportunity", "what should I focus on", "find growth", "what's leaking", or wants prioritized suggestions rather than a report.From its SKILL.md

Install
npx -y skills add inflowave/skills --skill growth-radar

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

3 things to look at

  • 23 days oldThe repository was created 23 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.

SKILL.md

3.2 KB, 682 tokens by cl100k_base, as published. Nobody here has run it

Growth Radar

The suggestion engine. A weekly recap tells you what happened; Growth Radar tells you what to do next and why, by correlating across domains that are normally looked at in isolation.

Method

  1. Scope. check_connection; confirm workspace via list_sub_accounts.

  2. Gather signals across all domains (reads, parallel):

    • Audience/reach: get_engagement_analytics, get_follower_analytics, get_account_insights.
    • Capture: list_forms + get_form_submissions; list_leads / search_leads by source.
    • Automation: list_workflows, get_workflow_performance, workflow_health_audit, get_workflow_failure_stats.
    • Conversion: get_pipeline_analytics, get_pipeline_board, list_pipeline_opportunities.
    • Money: get_finances_summary; attribution via get_lead_journey on a sample.
    • Reach amplifiers: get_link_analytics (which links/CTAs actually get clicked).

  3. Correlate — this is the whole point. Look for relationships, not totals:

    • Source → revenue. Which lead source (form, DM, campaign, link) produces the highest won value per lead, not just the most leads? Fund the winner.
    • Workflow → revenue. Which active workflow's contacts convert best? Which "busy" workflow drives lots of activity but no wins?
    • Leak points. Biggest drop between stages: submitted→lead, lead→no-follow-up, stage→stage. Quantify each in lost $ (volume × downstream win value).
    • Underused wins. A high-converting workflow that only runs on a fraction of eligible leads; a high-click link buried where few see it.
    • Silent failures. A source that dried up, an automation that stalled, an integration that disconnected.

  4. Rank opportunities by estimated_value × confidence ÷ effort. Estimate the $ upside for each from the pipeline's own average won value and win rate — and be honest about confidence.

Output

A ranked Opportunity Radar — 3 to 5 items, biggest first. Each item:

  • The opportunity (one line, in money terms where possible): "~$4k/mo left on the table: 120 form leads/mo get no follow-up."
  • Why (the correlation you found).
  • Do this (the exact next action — often "build workflow X" or "shift budget to source Y"), with an offer to do it now (hand off to build-workflow or workflow-doctor).

Guardrails

  • Read-only analysis; any action is offered, never taken automatically.
  • Every suggestion must trace to a correlation you actually observed — no generic advice ("post more"). If the data is too thin to correlate, say so and name what to instrument first.
  • Money estimates are clearly labeled estimates with their assumption stated.
  • Plain language, ranked, skimmable. Lead with the single biggest lever.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most product growth skills give in 682 tokens

Counted across 728 of the 1,010 authors here whose files we hold, read 2026-08-07

  • Read product marketing context before asking questionsin 24 of 728, across 18 files
  • Define the ideal customer profilein 21 of 728, across 3 files
  • Document a rollback plan before deploymentin 21 of 728, across 12 files
  • Analyze the codebase to understand the productin 19 of 728, across 1 file
  • Ask clarifying questions about the value propositionin 19 of 728, across 1 file
  • Search for companies matching the criteriain 19 of 728, across 1 file
  • Look for signals of immediate needin 19 of 728, across 1 file
  • Assign a fit score from one to tenin 19 of 728, across 1 file
  • Identify the target decision-maker rolein 19 of 728, across 1 file
  • Suggest a personalized contact strategyin 19 of 728, across 1 file
  • Provide conversation starters for outreachin 19 of 728, across 1 file
  • Format results in a scannable markdown templatein 19 of 728, across 1 file

Said here and by no other author read

  • confirm workspace via list_sub_accounts
  • gather signals across all domains
  • correlate data to find relationships
  • quantify leak points in lost dollars
  • rank opportunities by estimated value
  • produce an opportunity radar

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,834. 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.