referral-program

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization.

Install with Tessl CLI

npx tessl i github:coreyhaines31/marketingskills --skill referral-program

What are skills?

Overall
score

90%

Review — 88%

Does it follow best practices?

If you maintain this skill, you can automatically optimize it using the tessl CLI to improve its score:

npx tessl skill review --optimize ./path/to/skill

Learn more

Evaluation — 87%

↑ 1.16x

Agent success when using this skill

Validation — 11 / 11 Passed

Validation for skill structure

SKILL.md

Review

Evals

Evaluation results

93%

16%

FitPath: Launch Our First Referral Program

Referral program design from scratch

Criteria

Without context

With context

Referral loop stages

100%

High-intent trigger

100%

In-product sharing primary

100%

38%

Incentive sizing formula

75%

100%

Double-sided framing

100%

75%

Tracking and attribution

100%

Fraud prevention included

100%

Terms and conditions

100%

Post-launch review steps

100%

Incentive type fit

100%

Referred customer stats

25%

100%

Referral tool mentioned

100%

Without context: $0.3165 · 2m 23s · 11 turns · 11 in / 6,151 out tokens

With context: $0.5924 · 3m 3s · 24 turns · 317 in / 8,146 out tokens

80%

-14%

NourishBox: Build an Affiliate Program with Content Creators

Affiliate program commission and enablement

Criteria

Without context

With context

Recurring commission type

100%

Commission rate range

100%

SaaS cookie duration

50%

100%

Affiliate source diversity

100%

Enablement package breadth

100%

Technical fraud prevention

100%

Structural fraud prevention

100%

Rewardful recommendation

100%

Outreach template elements

100%

Unique tracking links

100%

Performance metrics defined

100%

Without context: $0.3287 · 2m 26s · 12 turns · 11 in / 6,057 out tokens

With context: $0.5106 · 2m 46s · 19 turns · 1,609 in / 6,771 out tokens

89%

34%

FlowDesk: Diagnose and Fix an Underperforming Referral Program

Referral program optimization and metrics

Criteria

Without context

With context

K-factor calculation

100%

K-factor interpretation

100%

Referral rate benchmark

30%

50%

Problem-fix mapping

90%

100%

Incentive A/B tests

88%

100%

Messaging A/B tests

88%

75%

Placement A/B tests

100%

Program health metrics

25%

50%

ROI formula applied

100%

LTV/churn impact cited

100%

Business impact metrics

88%

100%

Without context: $0.2009 · 1m 33s · 7 turns · 7 in / 4,110 out tokens

With context: $0.4705 · 2m 42s · 18 turns · 65 in / 6,936 out tokens

Evaluated: about 16 hours ago
Agent: Claude Code

Table of Contents

FitPath: Launch Our First Referral Program NourishBox: Build an Affiliate Program with Content Creators FlowDesk: Diagnose and Fix an Underperforming Referral Program

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.