A specialized API-driven skill for transforming Typst and LaTeX source files into production-ready PDF documents without local dependencies.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install typetex
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install typetex using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Typst & LaTeX Compiler skill provides a powerful interface for generating high-fidelity PDF documents directly from source code. By utilizing the TypeTex compilation API, this tool eliminates the need for maintaining heavy local TeX Live or Typst installations. It is designed to fit seamlessly into modern developer workflows, allowing for the programmatic creation of technical reports, academic papers, and automated documentation.
As a versatile component of the Openclaw Skills library, it supports both the modern, fast Typst language and the industry-standard LaTeX ecosystem. It handles complex multi-file projects, bibliography management, and image embedding, making it an essential tool for any developer or AI agent requiring professional-grade typesetting capabilities.
To get started with this skill, ensure you have a standard environment capable of making HTTPS requests. No local compiler installation is required as the heavy lifting is handled via API. Verify the service status using the following command:
curl -X GET https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/health
For a basic Typst compilation, you can use a simple curl command:
curl -X POST https://studio-intrinsic--typetex-compile-app.modal.run/public/compile/typst \
-H "Content-Type: application/json" \
-d '{
"content": "#set page(paper: \"a4\")\n= Created via Openclaw Skills\nThis is a Typst document.",
"main_filename": "main.typ"
}' | jq -r '.pdf_base64' | base64 -d > output.pdf
The skill utilizes a structured JSON schema for managing compilation tasks. Below is the organization of the input and output data:
| Field | Description |
|---|---|
content |
The raw text of the main source file to be compiled. |
main_filename |
The entry point filename (e.g., main.typ or main.tex). |
auxiliary_files |
An object containing additional assets. Keys are filenames, values are content (base64 for binaries). |
success |
A boolean indicating if the compilation was successful. |
pdf_base64 |
The resulting PDF file encoded in base64 format. |
error |
Detailed error message returned if compilation fails. |
log_output |
(LaTeX only) The full compilation log for debugging purposes. |
Loading
AgentYard is an innovative platform and skill that allows AI agents to autonomously collaborate, build, and ship code within a shared GitHub repository.

A persistent, cross-session memory system that enables AI agents to store and retrieve personal facts, preferences, and historical decisions.

A comprehensive strategy backtesting and simulated trading API designed for AI agents to validate crypto trading logic through decision trees.

A decentralized messaging bridge that connects AI agents to the DogeChat Nostr network for location-aware communication.

Cairn is an AI-native project management system that uses markdown files as a shared workspace for humans and AI agents.

A comprehensive scientific computing toolkit providing over 300 authoritative tools for chemistry, thermodynamics, and molecular analysis.








































