agentsclimarketplace

Genpark campaign autopilot

Skill alphaparkinc/genpark-campaign-autopilot

GenPark skill: genpark-campaign-autopilot based on GrowthGPT research

Install
npx -y skills add alphaparkinc/genpark-campaign-autopilot

Assembled 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.
  • 9 stars9 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

An autonomous agent skill that continuously monitors campaign performance, scales winning ad campaigns, and reverts based on custom guardrails.

SKILL.md

1.5 KB, 292 tokens by cl100k_base, as published. Nobody here has run it

GenPark Campaign Autopilot Skill

Overview

This skill allows GenPark agents to act as an autonomous campaign manager, mirroring the capabilities of GrowthGPT's "Autopilot". It continuously evaluates active campaigns across platforms (Meta, Google, TikTok), applying deterministic guardrails and logic to either scale budgets for winning campaigns or pause/revert campaigns that exceed target CPA.

Capabilities

  • Real-Time Monitoring: Fetches campaign data on a recurring cadence (e.g., last 72h window) to evaluate signals against targets.
  • Autonomous Scaling: Adjusts daily budgets dynamically (e.g., +20%) when ROAS and CPA signals are green and frequency is safe.
  • Safety Guardrails & Revert Triggers: Monitors performance post-scale. If CPA/CPP exceeds targets or CTR drops > 15%, the agent autonomously reverts the budget to the previous safe baseline.
  • Explainable Actions: Generates an auditable "Reasoning" report for every action (Context -> Reasoning -> Action -> Next Check).

Usage Instructions

  1. Provide the agent with connection credentials to the relevant ad platform APIs (Meta Ads, Google Ads).
  2. Define the exact targets (target_cpa, target_roas) and safety limits (max_daily_budget, revert_trigger_cpa).
  3. Set the evaluation frequency (e.g., every 6 hours).

What ships with it

Read from the repository

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

Gives 0 of the 12 instructions most marketing audience skills give in 292 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

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 328,083. 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.