Skip to main content
somark-document-parser is the simplest path when you want to reuse SoMark inside a Skill-capable agent platform without wrapping upload and parsing logic yourself. If you are still comparing Skill, MCP, API, CLI, and SDK, start with the get started overview.
1

Install

You can install it from any of these sources:GitHub
npx skills add https://github.com/SoMarkAI/somark-document-parser
skills.sh
npx skills add https://github.com/somarkai/somark-document-parser --skill somark-document-parser
clawhub.ai / OpenClaw
openclaw skills install 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, 2000 pages/month) that is automatically credited to your account. After the free quota is exceeded, the system automatically switches to paid quota.
3

Use prompts that trigger the Skill more reliably

To trigger the SoMark skill more reliably, your prompt should usually make three things explicit:
  • “Use SoMark to parse this PDF and return Markdown output.”
  • “Call the SoMark skill to parse this contract, extract the key clauses, and preserve heading structure.”
  • “Call SoMark to parse this paper and tell me the core idea of the paper.”
4

Keep the limits in mind

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