letterly-automation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Chinese

This skill provides a complete workflow for importing and processing your voice transcriptions from Letterly into your Obsidian vault.

本Skill提供了一套完整的工作流，可将你在Letterly中的语音转录内容导入并处理至Obsidian知识库中。

Export: Uses a Playwright browser agent to log in and download the latest CSV export from
```
web.letterly.app
```
.
Process: Extracts only notes marked as "magic" in the CSV, creates markdown files with custom frontmatter, and places them in
```
unprocessed/
```
.
Link: Analyzes the new notes and links them to existing vault content using the local semantic embedding database (
```
.nexus/cache.db
```
).
Deliver: Moves the final, linked notes to
```
My Outputs/Transcriptions/
```
and cleans up the temporary CSV.

To trigger the full workflow, simply tell the model: "Process new Letterly transcriptions" or "Sync my Letterly magic notes".

要触发完整工作流，只需告知模型： “处理新的Letterly转录内容” 或 “同步我的Letterly魔法笔记”。

If you need to run it manually from the terminal:

bash

undefined

若需从终端手动运行：

bash

undefined

uv venv .venv --python 3.12 uv pip install -r scripts/requirements.txt .venv/bin/playwright install chromium

.venv/bin/python scripts/workflow.py

undefined

.venv/bin/python scripts/workflow.py

undefined

Login Timeout: If the script times out waiting for login, ensure you have the browser window visible and log in within the 120-second window.
Database Missing: Ensure you are running this from your Obsidian vault root where
```
.nexus/cache.db
```
exists.
No Magic Notes: The script only imports notes that have been processed with the "Magic" rewrite type in Letterly.