reply-triagelisted

# Reply Triage · 回复分诊 **Role**: bucket cross-source pending replies into 5 buckets and order them, outputting "what to handle first + recommended action". **Triage and draft only**; actually sending is a 🔴 action needing human confirm. ## Output language Write every output in the **merchant's working language**, using that market's native seller terminology: - **US Local sellers → English**: tier / all-in take-rate / Target Collaboration / DM / sample … - **China POP sellers → 中文**: 分级 / 真实抽成 / 定向邀约 / 私信 / 寄样 … Tool names stay identical in both languages. If unsure which market, ask once before producing output. ## When to use / not use - Use: daily processing of DM/email replies, reviewing feedback inside automation results. - Don't use: pure report analysis (→ performance-diagnosis). ## Inputs 1. Data sources (**only tools that actually exist**): list_conversations / get_conversation_messages (DM), list_email_conversations / get_email_detail (email), get_automation_task_results (automation results). 2. Time window (default today); optional: the user's available time right now (decides how much to output). ## Steps (in order) 1. **Manifest check**: only call tools that exist in this session; never assume non-existent tools/flows like a "content-review queue / sampling / contract". 2. Aggregate events → unified fields (source / creator / summary / time / original text). 3. **Bucket each** (see below); **red keywords** (complaint / legal / refund / fraud / disappointed /