conversation-exporter
对话历史导出工具 - 将 WorkBuddy 的对话历史导出为多种格式（JSON/Markdown/TXT），包含时间线、元数据、统计数据、成就里程碑和 Skills 使用记录，便于归档分析和分享
About this skill
This skill, "conversation-exporter," is a vital tool for users of the WorkBuddy AI agent, enabling them to systematically export their interaction history. It converts past conversations into highly organized JSON, human-readable Markdown, or universally compatible plain TXT formats. This facilitates efficient archiving, in-depth analysis of AI interactions, and seamless sharing of project progress and insights. The export meticulously captures a wealth of information, including chronological timelines of all events, comprehensive metadata like date ranges and project details, summaries of "Work Memory" for long-term records, and crucial "Achievement Milestones" such as completed features or key decisions. Furthermore, it logs "Skills Usage Records," providing valuable insights into which AI capabilities were employed and how. Designed for robust utility, the skill ensures data integrity and user privacy. It features UTF-8 encoding to prevent character issues, processes all data locally without external service reliance, includes automatic filtering for sensitive information, and validates data completeness before export. This makes it an indispensable tool for anyone needing to maintain a detailed, shareable, and analyzable record of their AI-powered projects and interactions.
Best use case
The primary use case for the conversation-exporter is to provide comprehensive record-keeping and analytical capabilities for WorkBuddy users. It's ideal for developers, project managers, researchers, or any professional leveraging AI agents for complex, iterative tasks who need to review historical interactions, track project evolution, demonstrate progress, or conduct post-mortem analyses of AI-assisted work. By consolidating all interaction data into structured formats, it transforms raw conversational logs into actionable insights and verifiable project documentation.
对话历史导出工具 - 将 WorkBuddy 的对话历史导出为多种格式（JSON/Markdown/TXT），包含时间线、元数据、统计数据、成就里程碑和 Skills 使用记录，便于归档分析和分享
Users should expect one or more files (JSON, Markdown, and/or TXT) containing a structured and comprehensive record of their WorkBuddy conversation history, including timelines, statistics, and project details, saved to their workspace.
Practical example
Example input
导出我过去一个月的 WorkBuddy 对话历史，生成 JSON 和 Markdown 格式的文件。
Example output
已成功导出对话历史。文件 '对话历史_YYYY-MM-DD.json' 和 '对话历史_YYYY-MM-DD.md' 已保存到您的工作区根目录。它们包含了从 YYYY-MM-DD 到 YYYY-MM-DD 的会话记录、项目信息和 Skills 使用统计。
When to use this skill
- When you need to back up or archive your AI agent's conversation logs.
- When analyzing AI agent performance, project progress, or decision-making processes.
- When sharing project summaries, work records, or AI interaction details with team members or stakeholders.
- When creating a detailed reference of past interactions for future learning or debugging.
When not to use this skill
- When no historical record or analysis of AI interactions is required.
- When only a quick, transient interaction is needed and persistent storage is unnecessary.
- When absolute data privacy is paramount and even filtered local storage is deemed a risk.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/conversation-exporter/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How conversation-exporter Compares
| Feature / Agent | conversation-exporter | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
对话历史导出工具 - 将 WorkBuddy 的对话历史导出为多种格式（JSON/Markdown/TXT），包含时间线、元数据、统计数据、成就里程碑和 Skills 使用记录，便于归档分析和分享
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
Top AI Agents for Productivity
See the top AI agent skills for productivity, workflow automation, operational systems, documentation, and everyday task execution.
AI Agents for Freelancers
Browse AI agent skills for freelancers handling client research, proposals, outreach, delivery systems, documentation, and repeatable admin work.
SKILL.md Source
# 对话历史导出工具
将 WorkBuddy 的对话历史导出为多种格式（JSON、Markdown、TXT），便于归档、分析和分享。
## 触发条件
当用户需要以下操作时使用此 Skill：
- 导出对话历史
- 保存会话记录
- 生成对话摘要
- 分析对话数据
- 归档工作记忆
## 功能特性
### 支持的导出格式
1. **JSON 格式**（`conversation_history.json`）
- 结构化数据，便于程序处理
- 包含完整的时间线、元数据、统计信息
- 支持数据导入到其他系统
2. **Markdown 格式**（`conversation_history.md`）
- 易读的文档格式
- 适合归档和查看
- 支持语法高亮和富文本
3. **TXT 格式**（`conversation_history.txt`）
- 纯文本，兼容性最好
- 无格式干扰
- 适合日志分析
### 导出内容
- **时间线**：按时间顺序的所有交互事件
- **元数据**：日期范围、项目信息、统计数据
- **工作记忆**：从 WorkBuddy 工作记忆目录提取的长期记录
- **项目信息**：项目名称、描述、关键文件路径
- **成就里程碑**：完成的功能、版本迭代、重要决策
- **Skills 使用记录**：已安装的 Skills 列表和使用统计
### 安全特性
- ✅ **UTF-8 编码**：避免中文乱码
- ✅ **本地处理**：不涉及外部服务
- ✅ **数据过滤**：自动过滤敏感信息
- ✅ **格式验证**：导出前验证数据完整性
## 使用指南
### 基本用法
用户请求导出对话历史时：
1. **确定导出格式**
- 默认导出所有三种格式
- 用户可指定特定格式（如 "只导出 JSON"）
2. **读取工作记忆**
- 读取长期记忆文件
- 读取最近的日期文件（今天 + 过去 7 天）
- 读取自动化任务目录获取自动化任务信息
3. **构建导出数据**
- 解析时间线事件
- 统计数据
- 生成摘要
4. **输出文件**
- 文件名格式：`对话历史_YYYY-MM-DD.{ext}`
- 保存到工作区根目录
- 使用 UTF-8 BOM 编码（增强兼容性）
### 高级选项
- **日期范围**：导出指定时间段的对话
- **事件过滤**：按类型过滤事件（如 "只导出 Skills 安装记录"）
- **详细程度**：简洁模式 vs 完整模式
- **包含附件**：是否包含生成的文件列表
## 数据结构
### JSON 格式结构
```json
{
"conversation_history": {
"metadata": {
"export_date": "ISO 8601 日期时间",
"date_range": {
"start": "YYYY-MM-DD",
"end": "YYYY-MM-DD"
},
"workspace": "工作区路径",
"project": "项目名称"
},
"timeline": [
{
"date": "YYYY-MM-DD",
"time": "HH:MM",
"type": "事件类型",
"action": "操作描述",
"details": {}
}
],
"statistics": {
"total_days": 0,
"total_events": 0,
"events_by_type": {}
},
"achievements": [],
"skills_summary": {},
"automations": []
}
}
```
### Markdown 格式结构
```markdown
# 对话历史摘要
## 元数据
- 导出日期：...
- 时间范围：...
- 项目：...
## 时间线
### YYYY-MM-DD
- [HH:MM] 事件类型：操作描述
## 统计数据
...
## 成就里程碑
...
```
## 配置选项
### 文件编码
- JSON/MD: `utf-8-sig`（带 BOM，增强兼容性）
- TXT: `utf-8-sig`
### 文件路径
- 默认：工作区根目录，文件名格式为 `对话历史_{date}.{ext}`
- 可通过参数指定自定义路径
## 注意事项
1. **隐私保护**
- 自动过滤 API Keys、密码等敏感信息
- 不导出完整的对话内容，只保留摘要
- 用户可手动编辑导出文件删除敏感信息
2. **性能考虑**
- 大量历史数据可能影响导出速度
- 建议定期清理工作记忆（7天以上数据可归档）
3. **编码问题**
- 始终使用 UTF-8 编码
- 对于 Windows 系统，建议使用 `utf-8-sig` 避免 Excel 打开乱码
## 示例工作流
### 完整导出
1. 用户请求："导出对话历史"
2. 读取工作记忆文件
3. 解析并构建数据结构
4. 生成三种格式的文件
5. 显示导出摘要和文件路径
### 部分导出
1. 用户请求："导出最近的 3 天对话"
2. 按日期范围过滤数据
3. 生成指定格式文件
4. 返回结果
### 类型过滤
1. 用户请求："导出 Skills 安装记录"
2. 过滤事件类型为 `skill_installation`
3. 生成导出文件
4. 返回结果
## 错误处理
- 工作记忆文件不存在：提示用户首次使用，无历史数据
- 编码错误：自动尝试多种编码方式
- 文件写入失败：检查权限和磁盘空间
## 技术实现
### 依赖工具
- 文件读取工具：读取工作记忆文件
- 文件写入工具：写入导出文件
- 目录列表工具：列出工作记忆目录
### 无需外部依赖
- 本 Skill 不依赖外部 API
- 不使用网络连接
- 完全本地处理
## 更新日志
- **v1.0** (2026-03-25)
- 初始版本
- 支持 JSON、MD、TXT 三种格式
- UTF-8 编码，避免乱码
- 完整的工作记忆解析Related Skills
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
filesystem
Advanced filesystem operations for listing files, searching content, batch processing, and directory analysis. Supports recursive search, file type filtering, size analysis, and batch operations like copy/move/delete. Use when you need to: list directory contents, search for files by name or content, analyze directory structures, perform batch file operations, or analyze file sizes and distribution.
Budget & Expense Tracker — AI Agent Financial Command Center
Track every dollar, enforce budgets, spot spending patterns, and build wealth — all through natural conversation with your AI agent.
yt-dlp
A robust CLI wrapper for yt-dlp to download videos, playlists, and audio from YouTube and thousands of other sites. Supports format selection, quality control, metadata embedding, and cookie authentication.
time-checker
Check accurate current time, date, and timezone information for any location worldwide using time.is. Use when the user asks "what time is it in X", "current time in Y", or needs to verify timezone offsets.
pihole-ctl
Manage and monitor local Pi-hole instance. Query FTL database for statistics (blocked ads, top clients) and control service via CLI. Use when user asks "how many ads blocked", "pihole status", or "update gravity".
mermaid-architect
Generate beautiful, hand-drawn Mermaid diagrams with robust syntax (quoted labels, ELK layout). Use this skill when the user asks for "diagram", "flowchart", "sequence diagram", or "visualize this process".
memory-cache
High-performance temporary storage system using Redis. Supports namespaced keys (mema:*), TTL management, and session context caching. Use for: (1) Saving agent state, (2) Caching API results, (3) Sharing data between sub-agents.
mema
Mema's personal brain - SQLite metadata index for documents and Redis short-term context buffer. Use for organizing workspace knowledge paths and managing ephemeral session state.
file-organizer-skill
Organize files in directories by grouping them into folders based on their extensions or date. Includes Dry-Run, Recursive, and Undo capabilities.
media-compress
Compress and convert images and videos using ffmpeg. Use when the user wants to reduce file size, change format, resize, or optimize media files. Handles common formats like JPG, PNG, WebP, MP4, MOV, WebM. Triggers on phrases like "compress image", "compress video", "reduce file size", "convert to webp/mp4", "resize image", "make image smaller", "batch compress", "optimize media".
edge-tts
Text-to-speech conversion using node-edge-tts npm package for generating audio from text. Supports multiple voices, languages, speed adjustment, pitch control, and subtitle generation. Use when: (1) User requests audio/voice output with the "tts" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.