Marketing ReferralGrowthAffiliate

Referral Program

Design, launch, and optimize referral and affiliate programs.

$skillfish add ~skills/referral-program

Real Conversations

See how the Referral Program skill responds to actual requests. These are representative examples of what your AI agent will produce.

You

We run a project management SaaS for agencies, $49/seat/month. We want to launch a referral program. Our NPS is 52, we have 1,200 active users across 180 accounts. What mechanics actually work for B2B?

Agent

Referral Program Design: Agency PM SaaS

Recommended mechanic: Account credit, not cash Cash feels transactional for B2B. Account credits ($50–$100/successful referral) reduce your CAC and give the referrer skin in the game — they want the referred account to succeed.

Two-sided incentive structure:

  • Referrer: $75 account credit when referred account pays first invoice
  • Referee: First month free (removes friction, no upfront cost)

Who to target first: Your 180 account admins, not individual users. Admins have budget authority and agency networks. Filter by: accounts with 3+ seats AND NPS ≥ 8.

Launch sequence:

  1. Email top 40 accounts (highest seat count) with personal outreach from your CSM
  2. In-app prompt in dashboard after 3rd login of month
  3. Post-payment confirmation email with referral link

Tracking setup:

  • Unique referral link per account (not per user)
  • UTM: ref=acct-{account_id} for attribution
  • Track: click → signup → paid invoice → credit issued

Realistic expectations at your scale: 15–25% of contacted accounts will share at least once; expect 8–15 qualified referrals in first 90 days.

Get Started

How to install and use this skill in your preferred environment.

Skills are designed for AI coding agents (Claude Code, Cursor, Windsurf) and IDE-based workflows where the agent can read files, run scripts, and act on your codebase. Web-based AI can use the knowledge and frameworks, but won't have tool access.

Models & Context

Which AI models and context windows work best with this skill.

Recommended Models

Best
Claude Opus 4 Claude Sonnet 4 GPT-4.1 Gemini 2.5 Pro Grok 3 Kimi K2
Good
Claude Haiku 4.5 GPT-4.1 mini Gemini 2.5 Flash Grok 3 mini

Larger models produce more detailed, production-ready outputs.

Context Window

This skill's SKILL.md is typically 3–10 KB — fits in any modern context window.

8K Skill only
32K+ Skill + conversation
100K+ Skill + references + codebase

All current frontier models (Claude, GPT, Gemini) support 100K+ context. Use the full window for complex multi-service work.

Pro tips for best results

1

Be specific

Include numbers — users, budget, RPS — so the skill can size the architecture.

2

Share constraints

Compliance needs, team size, and existing stack all improve the output.

3

Iterate

Start with a high-level design, then ask follow-ups for IaC, cost analysis, or security review.

4

Combine skills

Pair with companion skills below for end-to-end coverage.

Ready to try Referral Program?

Install the skill and start getting expert-level guidance in your workflow — any agent, any IDE.

$skillfish add ~skills/referral-program
← Browse all 169 skills