Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

Feishu Doc Scraper

Extracts Feishu/Lark docs, wikis, sheets, and Minutes transcripts into faithful local Markdown without letting the model rewrite the body.

Docs & OfficeAdvanced★ 1,323⑂ 212AI score 8/10Last updated: Aug 8, 2026

What it does

Given a Feishu (飞书)/Lark URL, this skill writes the source content to Markdown files without any model paraphrasing of the body text.

  • Path A (primary): resolve wiki node → doc token via lark-cli, then pipe the body to disk with jq/pandoc
  • Collection recursion: BFS over <mention-doc>, <sheet>, image, cross-tenant and Minutes references until every leaf doc is fetched
  • Path B: on permission-denied (code 131006), convert an owner-exported .docx, restoring heading levels from font sizes and w:shd highlights
  • Path C: pull Minutes transcripts from the native transcription endpoint (never re-run ASR on downloaded media)
  • Path D: browser DOM capture as a last resort
  • Enforces acceptance gates: residual rich-media tag grep must be empty, and no U+FFFD replacement characters may remain

Who it's for

  • Teams whose internal wiki lives in Feishu and who want a local Obsidian/Markdown copy
  • Anyone archiving meeting transcripts from Feishu Minutes on a schedule
  • Researchers and compliance writers where verbatim fidelity beats summarization

Examples

  1. "Export this whole Feishu wiki collection to Markdown" → recursively fetches dozens of referenced child docs and reports which ones are permission-walled
  2. "Save this 妙记 transcript" → uses the native transcript API so speaker labels and timestamps survive
  3. "The doc says permission denied" → asks the owner for a .docx export, then rebuilds heading hierarchy and highlights and visually verifies the render

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the feishu-doc-scraper folder from the GitHub repo daymade/claude-code-skills into my ~/.claude/skills/feishu-doc-scraper/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/daymade/claude-code-skills.git /tmp/claude-code-skills && mkdir -p ~/.claude/skills && cp -r /tmp/claude-code-skills/feishu-doc-scraper ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repo: git clone https://github.com/daymade/claude-code-skills.git /tmp/claude-code-skills
  3. Copy the skill folder: mkdir -p ~/.claude/skills && cp -r /tmp/claude-code-skills/feishu-doc-scraper ~/.claude/skills/
  4. Install the main dependency: npm i -g @larksuite/cli (version 1.0.32 verified).
  5. Authenticate lark-cli against your Feishu tenant. For *.feishu.cn domains, set export LARK_CLI_NO_PROXY=1 first.
  6. Install helpers: pip install python-docx and pandoc (e.g. brew install pandoc).
  7. Restart Claude Code, paste a Feishu URL and say "extract this into Markdown" — the skill triggers automatically.
View source on GitHub ↗License: MIT