com um clique
memory-organizer
// 智能对话分析与记忆整理助手。获取并压缩指定 Agent 的对话记录,用于在用户授权/触发条件满足时,将信息分类写入 USER.md / AGENT.md / MEMORY.md(含索引与 memory/ 日志)/ IDENTITY.md / SOUL.md。
// 智能对话分析与记忆整理助手。获取并压缩指定 Agent 的对话记录,用于在用户授权/触发条件满足时,将信息分类写入 USER.md / AGENT.md / MEMORY.md(含索引与 memory/ 日志)/ IDENTITY.md / SOUL.md。
深度研究技能,用于系统性调研与分析。适用于研究、调研、竞品分析、市场分析或结构化信息收集等需求。
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.
| name | memory-organizer |
| description | 智能对话分析与记忆整理助手。获取并压缩指定 Agent 的对话记录,用于在用户授权/触发条件满足时,将信息分类写入 USER.md / AGENT.md / MEMORY.md(含索引与 memory/ 日志)/ IDENTITY.md / SOUL.md。 |
本技能用于两件事:
重要:默认只做对话压缩,不自动更新任何记忆文件。只有在用户明确要求/触发条件满足时才进入“记忆整理”。
USER.md写入内容示例:
不写入:临时状态、一次性偏好、明显会变化的短期安排。
写入模板(建议):
## 新增(来源:YYYY-MM-DD 对话)
- 偏好:...
- 习惯:...
- 个人信息:...
AGENT.md写入内容示例:
写入模板(建议):
## 会话新增规则(来源:YYYY-MM-DD 对话)
- ...
MEMORY.md(索引) + memory/(详情)MEMORY.md:只放“索引级”信息(项目结论、入口链接、关键里程碑),保持精简。memory/YYYY-MM-DD.md:写“YYYY-MM-DD 当天实际发生的会话与产出”的详细结论记录。
### [PROJECT:项目名] 当天事项标题(YYYY-MM-DD)
- **结论**: 用 1-3 句给出最终结果/决策(可复用口径)
- **上下文**: 为什么做这件事?触发点/需求是什么?关键约束是什么?
- **关键动作**: 只写“对结果有贡献的动作”(不要流水账),可列 3-7 条
- **证据/产物**:
- 输出文件:[...] (file://...)
- 关键脚本/代码:[...] (file://...)
- 关键对话摘录:引用 1-3 条带时间戳的用户原话(可选)
- **影响**:
- 对用户/项目的价值、后续工作如何衔接
- 风险/注意事项(如任务 id 漂移、依赖版本等)
- **后续 TODO**(可选): ...
- **标签**: #tag1 #tag2
## 重要项目
- [PROJECT:项目名] 一句话结论(来源:YYYY-MM-DD)
- 入口:...(文件链接)
- 关键变更:...
IDENTITY.md 或 SOUL.md如何区分:
IDENTITY.md:角色、身份切换规则、对外代表口径、边界定义(“我是谁/如何扮演”)SOUL.md:表达风格、语气、价值观、长期行为准则(“我怎么说/怎么做”)写入内容示例:
满足其一即可:
不触发:
# 查看可用 Agent
python scripts/fetch_conversations.py --list-agents
# 获取最近 7 天对话(必须指定 agent-id)
python scripts/fetch_conversations.py --agent-id agent_93905d3d --days 7
# 获取指定时间范围的对话
python scripts/fetch_conversations.py --agent-id agent_93905d3d --start-time 2024-01-01 --end-time 2024-01-31
# 获取从某时开始到最近的对话
python scripts/fetch_conversations.py --agent-id agent_93905d3d --start-time 2024-01-01T00:00:00
# 只指定结束时间(从开始到该时间)
python scripts/fetch_conversations.py --agent-id agent_93905d3d --end-time 2024-01-31
# 保存到文件
python scripts/fetch_conversations.py --agent-id agent_93905d3d --days 7 --output /tmp/conversations.txt
参数:
--agent-id: 必需,目标 Agent ID--days: 分析天数(默认:7)
--start-time/--end-time 互斥,不能同时使用--start-time: 开始时间,格式支持:
YYYY-MM-DD(如 2024-01-01)- 表示当天 00:00:00YYYY-MM-DDTHH:MM:SS(如 2024-01-01T09:30:00)- 精确时间--end-time: 结束时间,格式同上
--output: 输出文件路径| 消息类型 | 处理方式 |
|---|---|
| 用户消息 | 完整保留,带时间戳 |
| 助手消息 | 默认压缩为“关键行动/结论”,带时间戳 |
| 最后一个助手回复 | 尽可能保留最终结论(允许比中间消息更完整) |
| TOOL/中间消息 | 完全移除 |
.env 或 credentials/ 前必须二次确认(遵循工作空间安全规范)SAGE_PORT 环境变量--list-agents 查看--days 参数scripts/fetch_conversations.py (相对于 Skill 根目录){SAGE_ROOT}/agents/{agent_id}/
AGENT.md: 工作空间规范和工具使用说明IDENTITY.md: 身份定义、角色扮演的核心设定MEMORY.md: 核心记忆索引、项目状态、待办事项SOUL.md: 性格、行为风格和价值观USER.md: 用户背景、偏好和沟通风格档案memory/: 详细记忆日志文件夹(按日期记录)版本:1.5 | 最后更新:2026-03-16