发现优质的 AI Agent 技能

Extract the current Claude Code conversation from internal JSONL storage and format it as a readable markdown document showing: - All user questions - All model responses with associated operations (files read/edited, searches, commands, documentation lookups) - Timeline of the conversation flow

> 灵感来自 memU，零外部依赖，纯 Markdown + OpenClaw 原生工具实现

- **组织清晰**：按年月分层，便于查找和备份 - **格式统一**：统一文件命名和格式规范 - **易于迁移**：相对路径，支持整体移动 - **兼容性强**：使用通用格式（Markdown、JPEG等）

Manus-style persistent markdown planning. Filesystem = long-term memory. Context window = working RAM.

For long documents (e.g. contracts) sent to an LLM for edits, use **compact read → structured representation → LLM → edit JSON → write-back**. Markdown output is token-efficient compared to full JSON.

Manage contacts, relationships, and follow-ups with markdown files. No database needed.

Custom skill to send emails with advanced options including HTML/Markdown conversion, attachments, and retry handling. Integrates existing configuration, ensuring secure and reliable operations.

```md

Publish Markdown articles to WeChat Official Account draft box.

Use persistent markdown files as your "working memory on disk." Based on context engineering principles from Manus.

Slash commands are markdown files in `.claude/commands/` (project) or `~/.claude/commands/` (global) that expand into prompts when invoked.

This is the **Basic Edition** of the high-performance local RAG suite, providing efficient code and document retrieval within constraints. - **Constraints**: - Only indexes files **under 20MB**. - Uses single-threaded (sequential) indexing for lower resource usage. - **Support**: JS/TS, Python, C++, Go, Markdown, PDF, DOCX, XLSX, etc.