Skip to main content
somark-document-parser is an AI Agent Skill that enables Claude Code, Cursor, Cline, OpenCode, and 40+ other AI coding assistants to truly understand PDFs, images, Word files, and PowerPoint files — not just OCR’d text, but proper headings, tables, formulas, and layout.
1

Install

npx skills add https://github.com/SoMarkAI/somark-document-parser
Compatible with Claude Code, Cursor, Cline, OpenCode, and 40+ other AI agents.
2

Set up your API key

Get an API key at somark.tech, then set it as an environment variable:
export SOMARK_API_KEY=sk-your-api-key
You can also configure it in your agent’s settings. The skill will guide you through setup on first use.
SoMark includes a free tier (500 pages/day, 10000 pages/month) that is automatically credited to your account. After the free quota is exceeded, the system automatically switches to paid quota.
3

Use

Give your AI assistant natural language instructions and it will call SoMark automatically:
  • “Parse this PDF for me”
  • “Extract the key clauses from this contract”
  • “Summarize the paper I just uploaded”
  • “Convert this document to Markdown”
  • “What does this image say?”

​
Supported File Formats

TypeFormats
DocumentsPDF, DOC, DOCX, PPT, PPTX
ImagesPNG, JPG, JPEG, BMP, TIFF, WEBP, HEIC, HEIF, GIF

​
Why SoMark

Most agents struggle with documents because raw PDF/image data loses structure. SoMark preserves:
  • Heading hierarchy — agents understand document sections
  • Tables — fully reconstructed, not flattened into prose
  • Formulas and diagrams — converted to LaTeX or described accurately
  • Multi-column layouts — reading order maintained
The result: your agent gives accurate, context-aware answers instead of hallucinating from garbled text.

​
Limits

ConstraintLimit
Max file size200 MB
Max pages per file300
QPS per account1