referrals

PurposeHelps design, optimize, and analyze customer referral, affiliate, and word-of-mouth programs. Uses a referral loop framework, incentive design, and optimization diagnostics. Outputs program specs, launch checklists, and metrics that turn existing users into low-CAC growth engines.

Domains

Marketing

Forms

Workflow

Required Tools

—None

Languages

—No strong dependency

Package Manager

—N/A

Mechanism

When It Triggers · How It Works · What It Produces

Breaks down how the skill works and what it produces, so you can quickly judge whether it fits your scenario and value.

Trigger Timing

When a user wants to build, optimize, or analyze a referral/affiliate/word-of-mouth program, or mentions terms like 'referral', 'affiliate', 'refer a friend'.

Working Mechanism

Reads product-marketing context if present, then gathers program type, LTV, CAC, current state.
Distinguishes referral vs affiliate, designs loop (trigger → share → convert → reward), picks incentives and share mechanics.
Uses reference files for examples, runs optimization checks, defines metrics and launch checklist.

Outcome

A structured referral/affiliate program design with incentives, share flow, metrics, and launch plan that turns users into acquisition channels.

Use Cases

Two Typical Use Cases

Scenario 01

B2C SaaS builds first referral program

A B2C SaaS founder has no referral program and wants to acquire users cheaper. They use this skill to identify trigger moments (post-aha), pick double-sided rewards, and build an in-product share flow. The skill outputs a launch checklist and email sequence, helping them launch a program that lowers CAC by turning happy users into referrers.

Scenario 02

B2B optimizes low-converting affiliate program

A B2B company runs an affiliate program with low conversion. They use this skill to review commission structure, recruitment, and fraud rules via the affiliate reference, then A/B test incentive types and placement. The skill helps optimize the funnel, raising referred-signup rate and ROI from partner channels.

Skill File

SKILL.md

Open in GitHub ↗

SKILL.mdLoading from GitHub…

Skill Composition

Open in GitHub ↗

SKILL.md25.0%
references50.0%
other25.0%

▸skills/referrals/
▸root
- ·SKILL.md
- ▸evals
  - ·evals.json
- ▸references
  - ·affiliate-programs.md
  - ·program-examples.md

Per the Agent Skills spec, SKILL.md is the only required file. The colored bars classify the rest into the three spec-aligned optional directories (scripts / references / assets) and an 'other' bucket. The full directory tree is below.

When It Triggers · How It Works · What It Produces

Trigger Timing

Working Mechanism

Outcome

Two Typical Use Cases

B2C SaaS builds first referral program

B2B optimizes low-converting affiliate program

SKILL.md

Skill Composition

/referrals

Two Typical Use Cases

B2C SaaS builds first referral program

B2B optimizes low-converting affiliate program

SKILL.md

Skill Composition

When It Triggers · How It Works · What It Produces

Trigger Timing

Working Mechanism

Outcome