在这次转换中提取关键事实。只输出符合以下类别的物项，其余全部跳过(舍弃)：
Extract key facts from this conversation. Only output items matching these categories, skip everything else:

- 用户事实：私人信息，偏好，陈述的观点，习惯
- User facts: personal info, preferences, stated opinions, habits

- 决策：做过的选择，达成的结论
- Decisions: choices made, conclusions reached

- 解决方案：通过反复试错发现的工作方法，尤其是那些在失败尝试后最终成功的非显而易见的方法
- Solutions: working approaches discovered through trial and error, especially non-obvious methods that succeeded after failed attempts

- 事件：计划，截止日期，重要事件
- Events: plans, deadlines, notable occurrences

- 偏好：社交风格，工具的偏好设置
- Preferences: communication style, tool preferences

  
优先级：用户正确和偏好 > 解决方案 > 决策 > 事件 > 环境事实。最有价值的记忆能阻止用户不得不重复自己(已经做过的努力)。
Priority: user corrections and preferences > solutions > decisions > events > environment facts. The most valuable memory prevents the user from having to repeat themselves.

  
跳过：可从源代码、Git历史或现有记忆中已捕获的任何内容中，推导出的代码模式(大意是从输入信息或已有记忆中简单推导就能得出的范式或经验)。
Skip: code patterns derivable from source, git history, or anything already captured in existing memory.

  
每条事实单独列出，简明扼要。无需前言，也无需评论
Output as concise bullet points, one fact per line. No preamble, no commentary.

如果没有值得注意的事件，输出：（无）
If nothing noteworthy happened, output: (nothing)

你有两个同等重要的任务：
1、从谈话历史中提取出新的事实
2、对现有内存文件去重 - 即使在历史记录中从未提及，也能发现并标记出冗余、重复或过时的内容
You have TWO equally important tasks:

1. Extract new facts from conversation history

2. Deduplicate existing memory files — find and flag redundant, overlapping, or stale content even if NOT mentioned in history

  
每个发现分别输出一行：
[FILE] 原子事实(不在记忆中的)
[FILE-REMOVE] 删除的原因
[SKILL] 横短线命名法：可重用模式的一行式描述
Output one line per finding:

[FILE] atomic fact (not already in memory)

[FILE-REMOVE] reason for removal

[SKILL] kebab-case-name: one-line description of the reusable pattern

  

Files: USER (identity, preferences), SOUL (bot behavior, tone), MEMORY (knowledge, project context)

  
规则：
- 原子事实：“有个叫Luna的猫”，而不是“讨论宠物护理”
- 准确：[USER]的地理位置是东京，而非大阪
- 捕获用户验证过并且已确认的方法
Rules:

- Atomic facts: "has a cat named Luna" not "discussed pet care"

- Corrections: [USER] location is Tokyo, not Osaka

- Capture confirmed approaches the user validated

  
去重 - 扫描所有记忆文件找到以下重复的范式：
- 在多个地方陈述了相同的事实（例如，USER.md和多个MEMORY.md条目中都有的“用中文交流”）
- 覆盖了同一主题的重叠或嵌套章节
- 在USER.md或SOUL.md中信息，被捕获到MEMORY.md中了（MEMORY.md不应复制永久文件内容）
- 可以在不丢失信息的情况下进行压缩的详细条目
每找到一个重复的副本，对其中权威性较低的副本输出[FILE-REMOVE]（更倾向于将事实保存在它们的规范位置）
Deduplication — scan ALL memory files for these redundancy patterns:

- Same fact stated in multiple places (e.g., "communicates in Chinese" in both USER.md and multiple MEMORY.md entries)

- Overlapping or nested sections covering the same topic

- Information in MEMORY.md that is already captured in USER.md or SOUL.md (MEMORY.md should not duplicate permanent-file content)

- Verbose entries that can be condensed without losing information

For each duplicate found, output [FILE-REMOVE] for the less authoritative copy (prefer keeping facts in their canonical location)

  

稳定性 - MEMORY.md中，有些行可能有``← Nd``后缀表示自上次修改以来的天数：
- SOUL.md 和 USER.md 没有年龄注释 — 它们是永久性的，只会随更正而更新
- 年龄仅表示内容最后一次被触碰的时间，而不是是否应该被删除
- 使用内容做判断：用户的 习惯/偏好/个性特征 都是永久性的，而无关年龄
- 只修剪客观上过时的内容：已通过的事件、已解决的跟踪、已取代的方法
- 带有``← Nd``（N>{stale_threshold_days}}）的那些行，值得更仔细的审查，但不要自动删除
- 删除时：更推荐(你)删除其中独立的各个项目而不是整个章节
Staleness — MEMORY.md lines may have a ``← Nd`` suffix showing days since last modification:

- SOUL.md and USER.md have no age annotations — they are permanent, only update with corrections

- Age only indicates when content was last touched, not whether it should be removed

- Use content judgment: user habits/preferences/personality traits are permanent regardless of age

- Only prune content that is objectively outdated: passed events, resolved tracking, superseded approaches

- Lines with ``← Nd`` (N>{{ stale_threshold_days }}) deserve closer review but are NOT automatically removable

- When removing: prefer deleting individual items over entire sections

  

技能发现 — 当所有这些条件都为真时，标记[Skill]：
- 在对话历史中出现了2次以上的 一个特定的、可重复的工作流
- 它涉及明确的步骤（而不是类似“喜欢简洁的答案”这样模糊的偏好）
- 它可以保证自己的指令集足够强大（而不是像“读取文件”这样微不足道）
- 不要担心重复 — 下一阶段将检查现有skill
Skill discovery — flag [SKILL] when ALL of these are true:

- A specific, repeatable workflow appeared 2+ times in the conversation history

- It involves clear steps (not vague preferences like "likes concise answers")

- It is substantial enough to warrant its own instruction set (not trivial like "read a file")

- Do not worry about duplicates — the next phase will check against existing skills

  

不要添加：当前天气、瞬时状态、临时错误、会话填充。
Do not add: current weather, transient status, temporary errors, conversational filler.

  

[SKIP] 如果没有需要更新的内容。
[SKIP] if nothing needs updating.

根据以下的分析去更新内存文件。
- [FILE]条目：将描述的内容添加到相应的文件中
- [FILE-REMOVE]条目：从记忆文件中删除相应内容
- [SKILL]条目：使用 write_file 在 skills/<name>/SKILL.md下 创建新skill
Update memory files based on the analysis below.

- [FILE] entries: add the described content to the appropriate file

- [FILE-REMOVE] entries: delete the corresponding content from memory files

- [SKILL] entries: create a new skill under skills/<name>/SKILL.md using write_file

  

## 文件路径（工作区root目录的相对路径）
- SOUL.md
- USER.md
- 内存/memory.md
- skills/<name>/SKILL.md（仅适用于[SKILL]条目）
## File paths (relative to workspace root)

- SOUL.md

- USER.md

- memory/MEMORY.md

- skills/<name>/SKILL.md (for [SKILL] entries only)

  

不要猜测路径。
Do NOT guess paths.

  

## 编辑规则
- 直接编辑 — 下面提供的文件内容，不需要 read_file
- 使用与 old_text (格式)完全相同的文本，包括周围的空白行以方便唯一匹配
- 在一次 edit_file 调用中批量更改同一文件
- 对于删除操作：章节标题 + 所有类似 old_text 的文档排版，new_text 应该是空的
- 仅限于部分编辑操作 — 永远不要重写整个文件
- 如果没有要更新的内容，直接停止而不要去调用工具
## Editing rules

- Edit directly — file contents provided below, no read_file needed

- Use exact text as old_text, include surrounding blank lines for unique match

- Batch changes to the same file into one edit_file call

- For deletions: section header + all bullets as old_text, new_text empty

- Surgical edits only — never rewrite entire files

- If nothing to update, stop without calling tools

  

## 技能创建规则（适用于[Skill]条目）
- 使用 write_file 创建 skills/<name>/SKILL.md
- 在编写之前，请先阅读 `{skill_creator_path}` 以获取格式参考（前体结构、命名约定、质量标准）
- **反复检查**：阅读下面列出的现有skill，以验证新skill在功能上不是多余的。如果现有skill已经涵盖了相同的工作流程，则跳过创建。
- 包含带有名称和描述字段的 YAML frontmatter
- 将 SKILL.md 控制在2000字以内 — 简洁可行
- 包括：使用时间、步骤、输出格式，至少一个示例
- 不要覆盖现有的skill — 如果skill目录已存在，请跳过
- Agent想引用特定工具要去访问（read_file、write_file、exec、web_search等）
- skill是指令集，而不是代码 — 不要把实现代码放进去
## Skill creation rules (for [SKILL] entries)

- Use write_file to create skills/<name>/SKILL.md

- Before writing, read_file `{{ skill_creator_path }}` for format reference (frontmatter structure, naming conventions, quality standards)

- **Dedup check**: read existing skills listed below to verify the new skill is not functionally redundant. Skip creation if an existing skill already covers the same workflow.

- Include YAML frontmatter with name and description fields

- Keep SKILL.md under 2000 words — concise and actionable

- Include: when to use, steps, output format, at least one example

- Do NOT overwrite existing skills — skip if the skill directory already exists

- Reference specific tools the agent has access to (read_file, write_file, exec, web_search, etc.)

- Skills are instruction sets, not code — do not include implementation code

  

## 质量
- 每一行都必须包含独立值
- 清晰标题下面是简明的文档排版
- 缩减（不是删除）时：保留基本事实，删除详细信息
- 如果不确定是否要删除，请保留，但要添加“（请核对）”
## Quality

- Every line must carry standalone value

- Concise bullets under clear headers

- When reducing (not deleting): keep essential facts, drop verbose details

- If uncertain whether to delete, keep but add "(verify currency)"