原文核对：2026-10-13 · 中文正文 · 英文提示词与演示
场景定位
结合 Slack 和实际工作工具识别直接请求、隐含跟进、已解决事项和高影响行动，再起草回复或交接。
- 难度
- 入门
- 时间跨度
- 30 分钟
适合用于
- 需要区分未完成请求和已处理讨论的人。
- 背景分散在私信、频道和会话的上线、社区、客服、产品与运营工作。
- 起草回复、交接、文档修改或任务前需要排序清单的团队。
相关工具
搜索私信、频道、回复和提及。
Slack ↗邮件涉及外联、介绍或已发送跟进时交叉核对。
Gmail ↗读取关联文档、幻灯片、表格和材料。
Google Drive ↗检查会议、上线、网络研讨会或截止时间。
Google Calendar ↗起步提示词
英文原文 · 可复制后按实际材料修改
Can you check @slack for messages to me about [workstream] from [time window] and return a ranked action queue?
Look across DMs, group DMs, channel mentions, and threads.
For each item, include:
- source link or thread
- what is being asked
- whether it needs my reply, a person or lead, a docs or code change, or just a decision
- why it matters
- the recommended next step
Before calling anything unresolved, read the latest thread replies and skip items that were already handled.
Do not post messages directly but suggest drafts for my review.找出消息里的工作
请求可能始于私信，在会话中澄清，在频道附文档，又在后续被解决而没有再次提及你。
要求读完整背景、确认仍待处理，再返回少数需回复、决策、联系、更新文档或交接的事项，并排序。
执行分诊
- 指定时间窗口、工作流、人员、频道或主题。
- 搜索私信、群私信、频道提及和相关回复。
- 判为未解决前先读会话最新尾部。
- 按紧急度和影响排序。
- 起草回复、交接或后续任务。
试用并调整后，可在同一对话安排定时执行。
要求正确输出
说明每项为何仍待处理，排除后来已有人回答的旧请求。
结果可类似：
Codex首要事项：Priya 需要具体客户案例，而不只是更多想法。
重要性：上线更新需要本周能联系的真实人员。
证据：原消息询问场景，后续明确说有线索请私信。
下一步：回复两个具名线索，或表示自己可以作为案例。
区分想法和线索、待办和知会；已经回复的请求不应继续留在清单。
噪声过多或行动太少时调整提示词，必要时指定重点频道。
起草后续
清单准确后，在同一对话利用已收集证据起草回复或交接：
官方提示词
英文原文 · 可复制后按实际材料修改
Draft the Slack reply for each of these action items, using evidence from the triage pass.
Do not post it directly, but suggest drafts for my review.展开英文原文对照
Use ChatGPT with Slack and the tools where work happens to find direct asks, implicit follow-ups, resolved items, and the highest-impact next actions before drafting replies or handoffs.
Find the work hidden in Slack
Slack is often where a request starts, but not where the full context lives. A teammate might ask for a reply in a DM, clarify the real action in a thread, link a doc in a channel, and resolve the issue later without mentioning you again.
Use this workflow when you want ChatGPT to read the Slack context, check whether the ask is still live, and return the few items that actually need your attention. The goal is to get a ranked action queue: what needs a reply, a decision, a person to contact, a doc update, or a handoff.
Run the triage pass
- Give ChatGPT a time window, workstream, person, channel, or topic.
- Ask it to search DMs, group DMs, channel mentions, and relevant thread replies.
- Have ChatGPT read the latest thread tail before calling an item unresolved.
- Ask for a ranked queue sorted by urgency and impact.
- Ask ChatGPT to draft the reply, handoff, or follow-up task.
After trying this and tweaking the flow to match your needs, you can schedule a task for the work from the chat by asking ChatGPT to do the same thing on a schedule.
Ask for the right output
A useful triage result should explain why each item is still live. It should also skip old asks that someone answered later in the thread.
You should expect to see something like this:
CodexTop action item: Priya is asking for concrete customer examples, not just more ideas.
Why it matters: the launch update needs real people the team can contact this week.
Evidence: the original channel message asked for use cases, but the thread later says “please DM me if you have leads.”
Next step: reply with two named leads, or say you can be the example if that is more useful.
Good output makes the distinction explicit: an idea is different from a lead, a live ask is different from an FYI, and a request you already answered shouldn’t stay in the queue.
If you get too much noise or too few actionable items, tweak the prompt and if needed, mention specific slack channels you want ChatGPT to pay attention to.
Draft the follow-up
Once the queue is right, keep the action in the same chat. Ask ChatGPT to draft a reply or handoff from the evidence it already gathered:
官方提示词
英文原文 · 可复制后按实际材料修改
Draft the Slack reply for each of these action items, using evidence from the triage pass.
Do not post it directly, but suggest drafts for my review.