返回提示词目录第 1401 页

辨析消息语气并拟定核实回复

区分消息字面含义与个人推测,梳理多种可能语气及证据,起草中性回复以减少误会。

完整提示词

<context>
Text strips out tone, so readers fill it in, and anxious or tired readers fill it in negatively. Short replies, a full stop at the end, no emoji, "Can we talk?", "Fine.", "Per my last email" or a slow reply are weak signals: they mean different things from different people, generations, cultures and moods. The most reliable evidence is the difference from how this person usually writes, plus what the message literally asks or states. A good read separates what is said from what is inferred, lists the plausible readings with the cues for and against each, and ends with a cheap way to check before reacting, rather than a verdict on someone else's feelings.
</context>

<task>
Help me read this message before I react.

<message>
{{message}}
</message>
{{#relationship_context}}
<relationship_context>
{{relationship_context}}
</relationship_context>
{{/relationship_context}}
{{#your_reading}}
<your_reading>
{{your_reading}}
</your_reading>
{{/your_reading}}

1. If the message is empty, ask for it and stop.
2. If the message is plainly hostile, threatening, abusive or harassing, say so directly; do not offer charitable readings of a threat. Give practical next steps (do not engage in kind, keep a record, tell someone, report or block, and contact emergency services if I feel in danger) and stop there.
3. State what the message literally says or asks, with no interpretation.
4. List what I might be inferring that the words do not say.
5. Give two to four plausible readings of the tone and intent, from most to least likely given the context. For each: the cues that support it, the cues against it, and a rough likelihood (likely, possible, unlikely). Base likelihood on how this person usually writes if I told you; otherwise say that you lack a baseline.
6. If I gave my reading, say honestly whether the evidence supports it, partly supports it or does not. Do not simply reassure me, and do not confirm a fear that the words do not support.
7. Suggest how to check: a neutral reply or question that works under every plausible reading, or waiting for a conversation that is already planned. Draft one or two such replies in my voice.
8. Name what not to do yet (reply defensively, ask a third person to interpret it in a group chat, over-apologise for something not yet raised).
</task>

<constraints>
- Do not claim to know what the sender feels or intends. Use "may", "could", "one reading is".
- Keep it proportionate; a two-word message does not need an essay.
- Do not invent context about the sender. Generalisations about texting styles must be framed as general tendencies, not facts about this person.
</constraints>

<output_format>
If step 2 applies, give only `## This is a threat` (one or two lines saying so plainly, and why it is not ambiguous) and `## What to do now` (the next steps as bullets), and nothing else.

Otherwise:
## What it actually says
One or two lines.
## Plausible readings
A table: Reading | Cues for | Cues against | Likelihood.
## About your reading
One to three lines, or "You didn't share one."
## How to check
One or two neutral replies in quote blocks, or advice to wait, with why.
## Not yet
One to three bullets.
</output_format>

可替换内容

  • {{message}}
  • {{#relationship_context}}
  • {{relationship_context}}
  • {{/relationship_context}}
  • {{#your_reading}}
  • {{your_reading}}
  • {{/your_reading}}

分类与标签

情感社交、语气解读、消息回复、误会澄清、人际沟通

前往 AI 图片创作