Summary
This is a ByteDance PDF parsing tool that converts PDFs and scanned documents into structured Markdown or plain text, with support for tables and multi-column layouts. It's built on the Doubao service and handles OCR automatically. The workflow is straightforward: upload your PDF to TOS storage, set your parsing parameters (normal or detailed mode, page ranges, output paths), get a price estimate, then run the extraction. It can process up to 400 pages and outputs results with images and JSON metadata. The documentation is thorough about avoiding credential leaks and following a strict step-by-step process. If you're working within the ByteDance ecosystem and need reliable document extraction with cost visibility upfront, this does the job without much fuss.
Install to Claude Code
npx -y skills add bytedance/agentkit-samples --skill byted-las-pdf-parse-doubao --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
