fetch-feishu-doc

name

fetch-feishu-doc

description

Fetch content from Feishu open platform documentation (open.feishu.cn) as structured Markdown. Feishu developer docs are SPA pages — WebFetch only returns empty HTML shells with no actual content. This skill uses Playwright MCP (Chrome Extension / extend mode) to render the page and extract content via the built-in "复制页面" button, which copies the full page as Markdown to the clipboard. Use this skill PROACTIVELY whenever you encounter or need to reference: - Any open.feishu.cn/document/ URL (card components, API endpoints, SDK guides, etc.) - Feishu card JSON component specs (tag definitions, properties, examples) - Feishu API documentation (request/response formats, error codes, permissions) - Feishu event subscription or webhook documentation - Any Feishu open platform integration pattern DO NOT use this skill for: - User's own Lark cloud documents (bytedance.larkoffice.com) — use download-lark-doc or lark-parse instead - Non-Feishu URLs — use WebFetch or other tools IMPORTANT: This skill requires Playwright MCP running in extend mode (Chrome Extension). It does NOT work in headless mode because it relies on the system clipboard (pbpaste).

Fetch Feishu Open Platform Documentation

Extract full documentation content from any open.feishu.cn page as Markdown.

Why this skill exists

Feishu's developer documentation site (open.feishu.cn) is a Single Page Application. The actual content is rendered client-side via JavaScript. This means:

• WebFetch returns an empty HTML shell — no documentation content
• curl / HTTP GET gives the same empty result
• Screenshots + OCR lose structure and accuracy

The reliable approach: let a real browser render the page, then use Feishu's own "复制页面" (Copy Page) button which exports the full page content as well-formatted Markdown to the system clipboard.

Prerequisites

• Playwright MCP configured in extend mode (Chrome Extension), not headless
• macOS with pbpaste available (clipboard read)

Workflow

Step 1: Navigate to the documentation page

browser_navigate(url="<the open.feishu.cn URL>")

Step 2: Wait for content to render

SPA pages need time to load and render. Wait for the main content area to appear:

browser_wait_for(selector="article", state="visible", timeout=10000)

If article doesn't match, use browser_snapshot() to inspect the page structure and find the content container.

Step 3: Find and click the "复制页面" button

Take a snapshot to locate the copy button:

browser_snapshot()

Look for the element with text "复制页面" in the snapshot results. Then click it:

browser_click(ref=<the ref for "复制页面">)

The button text is always "复制页面" — this is stable across all open.feishu.cn documentation pages.

Step 4: Read Markdown from clipboard

After clicking, the page content is now in the system clipboard as Markdown. Read it:

pbpaste

This gives you the full documentation page as structured Markdown — headings, code blocks, tables, links all preserved.

Step 5: Use the content

The extracted Markdown is ready to use. Common next steps:

• Answer the user's question using the documentation
• Save to a local reference file for future use
• Extract specific code examples or API specs

Troubleshooting

"复制页面" button not found in snapshot: The button may be in a toolbar that appears on hover or scroll. Try:

1. browser_scroll(direction="up") to scroll to the top
2. Re-take browser_snapshot() — the button is typically in the page header area
3. If still not visible, look for an icon-only copy button or a "..." menu that contains it

Clipboard is empty or contains old content:

1. Add a brief wait after clicking: browser_wait_for(timeout=1000)
2. Re-run pbpaste

Page shows login prompt: Most open.feishu.cn documentation is publicly accessible. If a login wall appears, the URL may point to a restricted resource. Check if the URL is correct.