整理与导出对话归档
文本 · 通用对话模型
整理并导出对话要点
将对话中的任务、偏好和上下文按类别与日期整理成便于复制的完整导出文本。
Prompt
总结并导出本次聊天中交流的所有重要要点、指示和上下文信息,并按你的要求进行组织。
- 为每个主要类别使用章节标题(例如:任务指示、偏好、系统指南等)。
- 在每个类别中,每条内容单独占一行,格式为:[YYYY-MM-DD] - 此处填写内容。
- 在每个类别内按日期从早到晚排序。
- 如果条目日期未知,请使用 [unknown] 代替日期。
- 保留用户内容时,尽可能使用原文措辞,尤其是直接指示、要求或偏好。
- 将整个导出内容放在单个代码块中(反引号,语言不限),以便轻松复制。
- 在代码块后,明确说明这是完整内容,还是仍有更多条目。
请继续检查此前的所有对话轮次,确保完整收录所有相关上下文。请逐步思考,避免遗漏任何类别或细节。
## 输出格式:
- 导出内容必须放在单个代码块中。
- 在代码块内使用 Markdown 章节标题划分各类别。
- 每个类别中的每条内容必须单独占一行,格式为:[YYYY-MM-DD] - 此处填写内容。
- 如有需要,如果无法确定条目的日期,请使用 [unknown]。
- 在代码块后添加纯文本说明:“这是完整内容。”或“仍有更多条目。”(视情况而定)。
## 示例
```
# Task Instructions
[2024-06-13] - I will move this chant to another AI agent to also support my projects. I want you to prepare detailed list of important points which were discussed in this chat. Please preapare.
# Format Specifications
[2024-06-13] - Use section headers for each category. Within each category, list one entry per line, sorted by oldest date first. Format each line as: [YYYY-MM-DD] - Entry content here.
[2024-06-13] - If no date is known, use [unknown] instead.
# Output Instructions
[2024-06-13] - Wrap the entire export in a single code block for easy copying.
[2024-06-13] - After the code block, state whether this is the complete set or if more remain.
```
(实际导出内容可能更长,也可能包含更多类别或条目。)
---
**提醒:**请仔细检查此前的所有对话轮次,确保没有遗漏任何内容,并逐字保留用户要求和指示。请严格按照上述要求生成导出内容,包括最后的完整性说明。Summarize and export all important points, instructions, and contextual information exchanged in this chat, structured per your requirements.
- Use section headers for each major category (e.g., Task Instructions, Preferences, System Guidelines, etc.).
- For each entry within a category, list one entry per line, formatted as: [YYYY-MM-DD] - Entry content here.
- Sort entries by oldest date first within each category.
- If no date is known for an entry, use [unknown] instead of a date.
- When preserving user content, use the original wording verbatim where possible, particularly for direct instructions, requirements, or preferences.
- Wrap the entire export in a single code block (backticks, language unspecified) for easy copying.
- After the code block, clearly state whether this is the complete set or if more entries remain.
Persist in checking all prior conversation turns to ensure all relevant context is captured exhaustively. Think step-by-step to avoid missing any category or detail.
## Output Format:
- The export must be wrapped in a single code block.
- Use markdown section headers within the code block for each category.
- Each entry in a category must be a single line, formatted as: [YYYY-MM-DD] - Entry content here.
- If needed, use [unknown] if the date for an entry cannot be determined.
- After the code block, add a plain text statement: "This is the complete set." or "More entries remain." (as appropriate).
## Example
```
# Task Instructions
[2024-06-13] - I will move this chant to another AI agent to also support my projects. I want you to prepare detailed list of important points which were discussed in this chat. Please preapare.
# Format Specifications
[2024-06-13] - Use section headers for each category. Within each category, list one entry per line, sorted by oldest date first. Format each line as: [YYYY-MM-DD] - Entry content here.
[2024-06-13] - If no date is known, use [unknown] instead.
# Output Instructions
[2024-06-13] - Wrap the entire export in a single code block for easy copying.
[2024-06-13] - After the code block, state whether this is the complete set or if more remain.
```
(Real exports may be longer and contain more categories/entries as appropriate.)
---
**Reminder:** Carefully review all prior turns to ensure nothing is missed, using verbatim wording for user requirements and instructions. Produce the export exactly as described above, including the final completeness statement.
使用建议
使用建议:在需要交接项目或保存讨论记录时使用,先确认可访问的对话范围,再按类别整理条目;无法确定日期时标记为 [unknown],导出后核对完整性声明。
信息
- 类型
- 文本
- 模型
- 通用对话模型
- 许可
- CC0-1.0