bytedance avatar

Byted Las Pdf Parse Doubao

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.

skills.sh installs
166
GitHub stars
484
last updated
Aug 21, 2026

Install

$ npx -y skills add bytedance/agentkit-samples --skill byted-las-pdf-parse-doubao --agent claude-code

Installs into .claude/skills of the current project.

Files

PDF 解析 (las_pdf_parse_doubao)

当用户希望从 PDF/图片中提取文本、表格、段落等结构化内容时使用本 Skill。

注意事项(⚠️ 必须遵守)

  • 千万不要让用户输入 AccessKey 和 SecretKey。
  • 下载文件只能使用 las-cli tos download 命令(兼容 tos 和非 tos 资源)。
  • las-cli operators call 和 las-cli price 命令的输出结果非常重要,必须完整返回给用户。

工作流(严格按步骤执行)

复制此清单并跟踪进度:

执行进度:
- [ ] Step 0: 前置检查
- [ ] Step 1: 初始化与准备
- [ ] Step 2: 预估价格
- [ ] Step 3: 执行任务并呈现结果
- [ ] Step 4: 失败排查

Step 0: 前置检查

版本检查(必须):请执行 las-cli install 0.3.8。若 las-cli 命令不存在,则执行 npm i -g "@volcengine/las-cli@0.3.8"

  • 新版本提醒:请执行 npm info @volcengine/las-cli version 查看当前可用的最新 Skill 版本(las-cli 与 Skill 版本一一对应)。若返回版本高于本 Skill 标注版本,请先提示用户升级当前 Skill。升级方式:请用户发送自然语言指令 帮我安装byted-las-pdf-parse-doubao技能,等待自动完成安装即可。
  • 认证检查:优先使用运行时自动注入的平台身份;若当前环境未自动注入,再运行 las-cli config show 确认旧版凭证 las.apiKey 和 volcengine.region 已配置。

Step 1: 初始化与准备

  • 上传资源: 若输入为本地文件,先上传到 TOS。
    las-cli tos upload ./document.pdf
    # 假设返回 "tos_url": "tos://my-bucket/inputs/xxx.pdf"
    

Sponsors

Details

Repository
github.com/bytedance/agentkit-samples
Category
Office & Documents
First seen
Jun 3, 2026

More from bytedance/agentkit-samples

All 6
1nexu-io avatarhtml-ppt-taste-editorialnexu-io/open-design16:9 HTML deck in editorial-minimalist taste. Warm cream slides, serif display + grotesque body, hairline rules, monospace meta, generous macro-whitespace, one 160skills.sh installs
2opensensenova avatarsn-da-excel-workflowopensensenova/sensenova-skillsExcel 数据分析多步编排器。覆盖:(1) 读取多 Sheet Excel 文件并统计行数,(2) 大文件检测(≥10k 行自动 Parquet 优化),(3) 数据清洗(缺失值、文本标准化、无效字符),(4) 条件筛选与分类提取,(5) 跨 Sheet 统计聚合,(6) 导出 Excel/CSV 并提供下载链接。覆147skills.sh installs
3letta-ai avatargoogle-workspaceletta-ai/skillsConnect to Gmail and Google Calendar via OAuth 2.0. Use when users want to search/read emails, create drafts, search calendar events, check availability, or sch126skills.sh installs
4axoviq-ai avatardocxaxoviq-ai/synthadocExtract text from Microsoft Word documents0skills.sh installs
5davila7 avatarExcel Analysisdavila7/claude-code-templatesAnalyze Excel spreadsheets, create pivot tables, generate charts, and perform data analysis. Use when analyzing Excel files, spreadsheets, tabular data, or .xls0skills.sh installs
6davila7 avatarPDF Processing Prodavila7/claude-code-templatesProduction-ready PDF processing with forms, tables, OCR, validation, and batch operations. Use when working with complex PDF workflows in production environment0skills.sh installs