yuque-lakebook-export-cn

Yuque Lakebook Export

Overview

Export Yuque knowledge bases, Yuque documents, or .lakebook files and convert them into a local Markdown directory, prioritizing compatibility with Obsidian. The workflow supports single or batch export and handles common migration issues such as missing images, cropped image mismatches, broken internal links, incorrect directory hierarchy, and abnormal Markdown table rendering.

When to Use

Use this skill when the user needs the following capabilities:

• Export one or more Yuque .lakebook
• Convert Yuque knowledge bases to Markdown
• Migrate Yuque content to Obsidian
• Fix image, cropped image, internal link, directory hierarchy, and table rendering issues after Yuque export

Do Not Use

Do not use this skill for:

• Ordinary Markdown editing unrelated to Yuque or .lakebook Unrelated ordinary Markdown editing
• Web scraping tasks
• Export conversion tasks from non-Yuque sources

Usage Instructions

1. Prefer non-interactive mode for stable Agent execution.
2. Before executing any non-interactive export, the Agent must first confirm the output root directory with the user and must not decide the output directory on its own.
3. If the user has not yet clearly provided an output directory, first ask with a brief question and wait for the user's reply before executing the export.
4. Uniformly prioritize using uv, and do not temporarily create .venv、.yuque-export-venv environments in the task directory.
5. Before executing any uv command, first check whether the current environment can use uv。
6. If uv is not installed, or is not in PATH , the Agent must first ask the user to confirm whether to install uv, and must not silently install it directly.
7. Before executing uv sync or uv run python scripts/cli.py ... , you must first switch to the tool directory of the currently installed skill, that is, the one containing this SKILL.md、pyproject.toml、uv.lock and scripts/ . Do not execute these commands directly in the directory containing .lakebook , the target output directory, or the root directory of the user's current workspace.
8. When executing, the Agent uses the following entry point:

uv run python scripts/cli.py

1. Sync dependencies before first use:

uv sync

1. Recommended execution order:

cd /path/to/installed-skill-root
uv sync
uv run python scripts/cli.py ...

1. Single-file execution:

uv run python scripts/cli.py -l "/path/to/your_file.lakebook" -o "/target/root"

1. Batch execution:

uv run python scripts/cli.py -l "/path/to/your_file_1.lakebook" "/path/to/your_file_2.lakebook" -o "/target/root"

1. Although scripts/cli.py still retains interactive selection capability for manual use in human terminals, the Agent should not rely on interactive mode because terminal interaction state cannot be reliably obtained. Always explicitly pass -l and -o parameters during execution.
2. Do not manually create temporary virtual environments in the current working directory, the user's download directory, or any task directory; dependencies should be uniformly managed by the uv environment in the skill tool directory.
3. It is known that some document bodies exported from Yuque contain <!doctype lake>, and older implementations may export them as lake## 标题; the current built-in implementation of this skill already handles this issue.
4. After export completes, check:

• .md Whether the file is generated
• Whether a same-named .assets directory is generated
• Whether internal links are converted to relative Markdown paths
• Whether images can display normally in Obsidian
• Whether the first line of the document has an abnormal lake## prefix

1. If the export fails, first check the batch log generated in the same directory as the input .lakebook .

For detailed behavior, output rules, and troubleshooting instructions, see references/usage.md。