菜单
Convert local document bytes into clean Markdown with Context.dev. Use when the user asks to parse, read, OCR, summarize, or extract text from an attached PDF, Office document, spreadsheet, image, source file, HTML file, or other supported local file.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
基于 SOC 职业分类
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/context-dot-dev/cursor-plugin --skill context-parse命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Run and manage large asynchronous Context.dev web jobs. Use when the user needs to scrape many URLs, crawl at scale, process up to 25,000 URLs in one job, avoid synchronous timeouts, inspect batch progress or results, or cancel or delete a previously submitted batch.
Retrieve company brand intelligence and design data with Context.dev. Use when the user asks for a company's logo, colors, fonts, style guide, social profiles, description, industry, address, stock information, brand kit, or lookup by domain, name, email, ticker, ISIN, transaction descriptor, or direct URL.
Discover or read multiple pages from a website with Context.dev. Use when the user asks to map a site, find URLs in a sitemap, crawl documentation or a site section, gather several linked pages, or locate the most relevant pages within one domain.
| name | context-parse |
| description | Convert local document bytes into clean Markdown with Context.dev. Use when the user asks to parse, read, OCR, summarize, or extract text from an attached PDF, Office document, spreadsheet, image, source file, HTML file, or other supported local file. |
Use the Context.dev parse-document MCP tool for local file bytes. Use a scrape tool instead when the source is a web URL.
fileBase64.The decoded input must not exceed 25 MiB. Do not upload unrelated files, and do not paste file contents into chat when the user only asked for a derived answer.