agentleFS
Sign inStart free
gomarble-aigomarble-ai/marketing-agent/skills/affiliate-marketing/SKILL.md

affiliate-marketing

Skill15 starsChanged 38 days agoMITView on GitHub

Use for affiliate and partner marketing on impact.com: partner performance, commission spend, conversions and payouts, which partners drive profitable orders, program-level results, invoices owed, and how affiliate spend compares with paid media. Read-only through GoMarble.

4 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Check a report's accepted filters with impact_get_report_metadata before running it.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Affiliate marketing (impact.com)

Analyze affiliate and partner programs on impact.com through GoMarble. The connector reads impact.com; it can't change partners, contracts or payouts.

Setup

  1. impact_list_accounts first. Every other impact.com tool needs the account_id.
  2. impact_list_programs early. impact.com calls programs "campaigns", and most reports need a program_id.

Tools

NeedTool
Commission spend and conversions for a program or partner, with breakdownsimpact_get_partner_spend (needs program_id and dates)
Individual conversions: order ID, payout, status, clearing datesimpact_get_conversion_details (needs program_id and dates)
Partners and their relationship statusimpact_list_partners
Any impact.com report: clicks, actions, revenue, costimpact_list_reports to find it, impact_get_report_metadata to see its filters and columns, then impact_run_report
What the brand owes partnersimpact_list_invoices, and impact_get_invoice for line items

Check a report's accepted filters with impact_get_report_metadata before running it; impact.com silently ignores filters it doesn't accept. An empty result means no data, not an error.

How to analyze

  • Spend vs revenue. ActionCost / action_cost is what the brand pays (commission), not revenue. Report cost per order and commission as a share of revenue.
  • Partner quality. Rank partners by profitable orders, not clicks. Watch for partners with high reversal or rejection rates, coupon and cashback partners claiming orders that would have happened anyway, and last-click partners taking credit for paid media's work.
  • Clearing. Recent conversions may still be pending or reversed. Say how much of the period has cleared.
  • Against paid media. Compare affiliate cost per order with paid media CPA from the same period, and reconcile orders with Shopify (shopify-order-discipline) so the same order isn't counted twice.

Output

Program and partner performance (orders, revenue, commission, cost per order), the partners worth growing or reviewing, what's still pending, and recommendations written as impact.com steps.

For a cross-channel view, use build-reports.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free