agentleFS
YangsonHungYangsonHung/awesome-agent-skills/skills/en/yuque-lakebook-export/SKILL.md

yuque-lakebook-export

Skill18 starsChanged 8 days agoMITView on GitHub

Use when exporting Yuque or .lakebook content to local Markdown for Obsidian migration or cleanup.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 6 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks for:

    line 15
  2. Distinctive:

    Do not use this skill for:

    line 24
  3. Distinctive:

    Prefer non-interactive execution so the agent can run deterministically.

    line 32
  4. Distinctive:

    Before any non-interactive export, the agent must confirm the output root directory with the user.

    line 33
  5. Distinctive:

    If the user has not provided an output directory, ask a concise question and wait for the user's answer before running the export command.

    line 34
  6. Very specific:

    Prefer uv consistently. Do not create temporary .venv or similar task-local environments in the working directory.

    line 35
  7. Very specific:

    Before running any uv command, first check whether uv is available in the environment.

    line 36
  8. Very specific:

    If uv is not installed or not available in PATH, the agent must ask the user for confirmation before installing uv.

    line 37
  9. Distinctive:

    Use this entrypoint for agent execution:

    line 39
  10. Very specific:

    Do not manually create temporary virtual environments in the current working directory, the user's download directory, or any task …

    line 72
  11. Very specific:

    If export fails, inspect the batch log written next to the input .lakebook files.

    line 81

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Yuque Lakebook Export

Overview

Convert Yuque knowledge bases, Yuque documents, or .lakebook files into local Markdown folders prepared for Obsidian. The workflow supports single or batch exports and cleanup for common migration issues such as missing images, cropped image mismatches, broken internal links, wrong folder hierarchy, and Markdown table rendering problems.

When to Use

Use this skill when the user asks for:

  • Exporting one or more Yuque .lakebook files
  • Converting a Yuque knowledge base into Markdown
  • Migrating Yuque content into Obsidian
  • Fixing Yuque export issues around images, cropped images, internal links, hierarchy, or tables

Do not use

Do not use this skill for:

  • Generic Markdown editing that does not involve Yuque or .lakebook
  • Website scraping tasks
  • Export tasks that already come from a non-Yuque format

Instructions

  1. Prefer non-interactive execution so the agent can run deterministically.
  2. Before any non-interactive export, the agent must confirm the output root directory with the user. Do not choose an output directory on the user's behalf.
  3. If the user has not provided an output directory, ask a concise question and wait for the user's answer before running the export command.
  4. Prefer uv consistently. Do not create temporary .venv or similar task-local environments in the working directory.
  5. Before running any uv command, first check whether uv is available in the environment.
  6. If uv is not installed or not available in PATH, the agent must ask the user for confirmation before installing uv. Do not install it silently.
  7. Before running uv sync or uv run python scripts/cli.py ..., the agent must first switch into the installed skill tool directory, meaning the directory that contains this SKILL.md, pyproject.toml, uv.lock, and scripts/. Do not run these commands directly from the .lakebook source directory, the output directory, or the user's current workspace root.
  8. Use this entrypoint for agent execution:
uv run python scripts/cli.py
  1. Sync dependencies before first use:
uv sync
  1. Recommended command order:
cd /path/to/installed-skill-root
uv sync
uv run python scripts/cli.py ...
  1. Standard single-file execution:
uv run python scripts/cli.py -l "/path/to/your_file.lakebook" -o "/target/root"
  1. Standard 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 supports interactive terminal selection for manual human use, agents must not rely on interactive mode because they cannot reliably capture terminal interaction state. Always pass explicit -l and -o arguments.
  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 managed by uv from the skill tool directory.
  3. Some Yuque exports include <!doctype lake> at the start of the document body; older implementations could render this as a stray lake## prefix in Markdown. The current skill implementation already handles this case.
  4. After export, verify:
  • .md files exist
  • sibling .assets folders exist
  • internal links are relative Markdown paths
  • images render in Obsidian
  • exported documents do not start with an erroneous lake## prefix
  1. If export fails, inspect the batch log written next to the input .lakebook files.

For detailed behavior, troubleshooting, and output rules, read references/usage.md.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.