DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to import one Douyin video or image post into Obsidian with Douyin to Obsidian

Send one Douyin link to /dy in cc-connect and get a sourced knowledge note in your vault.

  • Top pick
  • Research
  • Intermediate
  • 60 minutes
  • From the README
  • Claude Code

Credentials. The skill reads Chrome cookies from your configured profile in the local request process, so use only a profile you control.

Who it is forA knowledge worker who saves a useful Douyin video or image post and wants its content as a note in their own Obsidian vault.

The problemWatching a short video and copying its key points by hand is slow, and the content is hard to search later.

The outcomeA structured Obsidian note with the original work link, transcribed or OCR-checked content, and an entry in the import log.

What you need first

  • Apple Silicon Mac; Intel Mac, Windows and Linux are not fully supported
  • Python 3.12 and a locally runnable Node.js
  • Xcode Command Line Tools (xcrun and Swift) for OCR
  • Chrome installed and logged in to Douyin in the profile you configure, for private favorites
  • A cc-connect instance configured with Claude Code and a working model and channel
  • An existing Obsidian vault that you can read and write

Steps

  1. Run xcode-select --install if Command Line Tools are not installed yet.
  2. Clone the repository with git clone https://github.com/llm-xiaoye/douyin-to-obsidian.git and enter the folder with cd douyin-to-obsidian.
  3. Set DY_PYTHON, DY_WORKSPACE, DY_VAULT and DY_PROFILE to your absolute paths, then run scripts/install.py with --workspace, --vault and --browser-profile as shown in section 3.
  4. Run "$DY_WORKSPACE/.claude/skills/douyin-to-obsidian/.venv/bin/python" -B "$DY_WORKSPACE/.claude/skills/douyin-to-obsidian/scripts/doctor.py" and confirm ok is true. (inferred, check the README)
  5. In a new cc-connect session in that workspace, send /dy <douyin-link> with the video or image post link. (inferred, check the README)

Prompt for your agent

Using the repo llm-xiaoye/douyin-to-obsidian, install the /dy skill into the cc-connect workspace at <workspace path> with the vault at <vault path>, then run doctor. Once doctor reports ok true, import the Douyin work at <douyin-link> and report the new note path. Verify that the note contains the original work link and that the import log has a new entry.

Caveat. Only titles, silent tracks or missing image pages do not produce a note, and public videos may still fail due to platform limits, network or permissions.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for llm-xiaoye/douyin-to-obsidian and "Import one Douyin video or image post into Obsidian"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer