JasonColapietro/suede-creator-skills / skills/suede-referrals
suede-referrals
VerifiedDesign a referral and affiliate program with incentives, commission and payout rules, fraud controls, disclosure, attribution, and cohort measurement. Use when asked to "design our referral program" or repair customer, ambassador, or partner incentives. Returns a program spec, economics, tooling options, and launch checklist. NOT FOR: payouts or billing changes, brand partnerships (use suede-co-marketing), launch packaging (use suede-launch-packaging), or lifecycle messages (use suede-emails).
| File | Kind | Size |
|---|---|---|
| CARD.md | markdown | 4.3 KB |
| SKILL.md | skill md | 9.5 KB |
| agents/openai.yaml | config | 589 B |
| evals/evals.json | config | 6.3 KB |
| references/affiliate-programs.md | markdown | 4.3 KB |
| references/program-examples.md | markdown | 3.9 KB |
| references/worked-handoff.md | markdown | 1.6 KB |
references/worked-handoff.md
View on GitHub# Suede Referral Skills: Worked Handoff
## Inputs
Request: “Design a referral pilot for a subscription service.” Synthetic business
inputs: $40 monthly revenue, $16 monthly variable delivery cost, a $10 reward to
each side, paid only after the referred customer's second paid month. No observed
referral conversion or retention data is supplied. Returns and fraud can reverse
eligibility; the business owner has not yet approved final terms.
## Expected output
Write the program spec with qualifying event, attribution window, deduplication,
self-referral rule, reward type, review owner, dispute path, disclosure language,
and rollout checklist. Show the illustrative contribution calculation:
`2 × ($40 − $16) − $20 = $28` before acquisition, fixed, tax, refund, or fraud
costs. Label those exclusions. Do not turn that example into LTV or expected
profit. Propose a capped pilot, with its cap left for the owner's real budget,
and report referral activation, paid conversion, net contribution, reversals,
and retention by cohort.
## Failure case
If variable costs, reward funding, or refund terms are unknown, return an
economics worksheet and unresolved decision rather than calling the incentive
sustainable. If referral evidence is incomplete, queue the reward for review;
do not issue a payout or create accounts while drafting a program.
## Validation
Recalculate the example from the supplied values. Trace every payout condition
to a named event and owner. Verify negative cases: self-referral, duplicate
customer, cancellation before month two, refund after eligibility, and disputed
attribution. The spec should state what each does to eligibility and appeal.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 323k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |