Skip to content
SkillModel-led2,209 tokens in use

referrals

Design referral and affiliate programs and word-of-mouth loops: check viral fit, pick rewards, size incentives, launch with a checklist and run review campaigns.

61,715 stars on the repository MIT Licensecoreyhaines31/marketingskills · skills/referrals
npx skills add coreyhaines31/marketingskills --skill referrals
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing referrals costs

74tokens idle
2,209tokens in use
9,963tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure25/25
  • Examples15/15
  • Output10/15
  • Size15/15
  • Resources12/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity100
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

The referrals skill helps an agent design and tune programs that turn customers and partners into a growth channel. It gathers program type, lifetime value, acquisition cost and product fit, then checks whether virality can be built into the product before a reward program is added.

It covers the referral loop from trigger moment to reward, single-sided and double-sided incentives, affiliate programs, launch and nurture emails, metrics, and review request programs, with reference files for each area.

What You Get

  • A referral loop design with trigger moments, share mechanisms ranked by effectiveness and an incentive structure
  • A viral fit diagnosis and product-embedded mechanisms such as badges, embeds and watermarks
  • Launch, nurture and reminder email drafts for the program
  • A launch checklist covering tracking, fraud rules and terms
  • Metrics for program health and business impact, plus A/B test ideas

Common Use Cases

  • Deciding whether a B2B tool should run a referral program or an affiliate program
  • Sizing a double-sided reward against customer lifetime value
  • Adding a Powered By badge or share flow to a product with natural exposure
  • Setting up review request campaigns on G2, Capterra or app stores within platform rules

What Makes It Unique

It starts by asking whether to run a reward program at all, using a viral potential spectrum that sends backend and infrastructure products toward content and partnerships. Affiliate operations, review platform rules and power-law partner mechanics sit in separate reference files, so the main file stays short while the detail is one link away.

Under The Hood

The skill is an instruction file with seven reference documents on viral mechanisms, affiliate programs and operations, program examples and review programs. It has no scripts. The agent reads the product marketing context file if present and writes its design in chat. It links to tool guides on the web, such as affiliate and link tracking tools, but does not fetch pages, call APIs, run commands or write files itself.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers