mcpField
R
referral-loop-review

referral-loop-review

github.com/sylphxaiMarketing & growth150 installsUpdated today
Repository

About referral-loop-review

A skill for designing and reviewing referral programs with attention to trust, incentives, attribution, and abuse risks. It produces a referral flow, incentive table, event schema, risk controls, and experiment plan.

Key features

  1. 01Map invitation and reward states
  2. 02Distinguish referral loop types
  3. 03Define incentives and attribution
  4. 04Identify fraud and abuse controls
  5. 05Create event schema and experiment plan

Use cases

  1. 01Design a referral flow from invite to reward
  2. 02Review incentive eligibility and reversal rules
  3. 03Plan referral tracking and experiments

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/sylphxai/skills --skill referral-loop-review

After installing, type/referral-loop-reviewin Claude Code to confirm it loaded.

Bundled filesagents/openai.yamlreferences/referral-loop-systems.md

Details

From the project README

Referral Loop Review

Use this skill to make referrals a trusted growth loop rather than a spam incentive.

Workflow

  1. Identify inviter, invitee, reward, trigger moment, channel, attribution window, and fraud risk.
  2. Read references/referral-loop-systems.md.
  3. Map invitation, acceptance, qualification, reward pending, reward grant, cancellation/reversal, and support states.
  4. Separate product-led sharing, paid incentives, team collaboration, affiliate economics, and abuse controls.
  5. Produce loop design, incentive table, event schema, risk controls, and experiment plan.

When not to use

  • Do not use for generic advice the base model already handles without this skill's specific artifact contract.

Guardrails

  • Do not reward spam, misleading claims, fake scarcity, or coerced contact upload.
  • Do not grant irreversible rewards before qualification and abuse checks.
  • Make terms, eligibility, attribution, expiration, and reversal rules visible.

Output format

Referral context:
Loop type:

Referral flow:
- trigger, channel, invite, qualification, reward, reversal

Incentive design:
- inviter reward:
- invitee reward:
- eligibility:
- caps/controls:

Risks:
- <risk> -> prevention, detection, support response

Metrics:
- invite, accept, activate, qualify, reward, fraud, retention

Comments

Markdown supported