Define the operational guardrails that stop end customers from gaming a refer-a-friend program - reward caps, velocity limits and cooldowns, reward-hold windows tied to the refund window, eligibility rules, identity-verification gates, a published enforcement ladder, and abuse-monitoring signals. Produces a guardrail spec for B2C and B2B SaaS referral program managers.
安装
npx skills add mbfinotti/partnerships-skills --skill referral-abuse-guardrailsnpx skills add mbfinotti/partnerships-skills --skill referral-abuse-guardrails -a claude-code -gnpx skills add mbfinotti/partnerships-skills --skill referral-abuse-guardrails -a codex -ggemini skills install https://github.com/mbfinotti/partnerships-skills.git --path skills/referral-abuse-guardrailsgh skill install mbfinotti/partnerships-skills referral-abuse-guardrailsgit clone --depth 1 https://github.com/mbfinotti/partnerships-skills /tmp/mbfinotti__partnerships-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/mbfinotti__partnerships-skills/skills/referral-abuse-guardrails ~/.claude/skills/referral-abuse-guardrails # Claude Code
cp -R /tmp/mbfinotti__partnerships-skills/skills/referral-abuse-guardrails ~/.agents/skills/referral-abuse-guardrails # Codex, Cursor, Gemini CLI, Copilot, OpenCode