官方 Official 需审批 Needs approval 例行 Routine Skill Skill
退款追回经理：找到索赔、提交并跟到底 Refunds Manager
Refunds Manager
找到该追的索赔，提交并跟到退款或折扣回来。 Finds the claim, files it, and follows it until a refund or discount comes back.
详细介绍Details
官方扩容帖「Refunds manager」：找到索赔、提交并跟进，带着追回的退款或折扣回来。这是你作为消费者/采购方去追钱，不是客服给用户办政策内退款。 Official expansion-post Refunds manager: finds the claim, files it, and follows it through, coming back with the refund or discount it recovered. This is you claiming money back—not in-policy customer refunds.
为什么推荐Why we recommend it 官方「Jobs Bots are doing today」新角色。已有 support-in-policy-refunds 是客服给用户退款；这里方向相反：替你追索赔。 New official “Jobs Bots are doing today” role. Existing support-in-policy-refunds issues refunds to customers; this files claims on your behalf.
上手路径How to start
审批边界Approval boundary
不提交索赔、不接受和解、不改支付方式；只返回可追索清单、草稿材料与跟进状态。 Do not file a claim, accept a settlement, or change payment methods; return the recoverable list, draft packets, and follow-up status.
- 先跑一次安全范围Run a safe first pass
先在可撤回、不外发的范围内试跑。本条未批准前：不提交索赔、不接受和解、不改支付方式；只返回可追索清单、草稿材料与跟进状态。。 Try it first in a reversible, non-outbound scope. Until approved: Do not file a claim, accept a settlement, or change payment methods; return the recoverable list, draft packets, and follow-up status..
- 存 SkillSave a Skill
这条用法已包含可复用 Skill。跑通安全范围后，立刻把步骤固化下来。 This use already includes a reusable Skill. After the safe pass, lock the steps in.
- 再上 RoutineThen add a Routine
输出稳定后再打开例行 / 定时。本条已有例行形态，不要一上来就无人值守外发。 Turn on the routine / schedule only after output is stable. This item already has a routine shape — do not start unattended outbound.
