any2pdf

An agent skill and Python script that lets AI coding assistants convert Markdown into publication-quality PDFs, handling mixed CJK and Latin text with the right fonts on each platform.

Visit website github.com

any2pdf is a Markdown-to-PDF converter built as a single Python file with one dependency, reportlab, designed to be driven by an AI coding assistant such as Claude Code, Cursor, Copilot or Gemini CLI through natural language. Instead of exposing a rigid CLI, its skill has the agent ask about design choices such as style, a frontispiece and a watermark, then run the conversion.

It targets edge cases in mixed Chinese-English and other CJK text: correct line wrapping so names are not split mid-word, correct rendering of dates and merged headings, and platform-appropriate serif and CJK font pairs on macOS, Windows and Linux. It also renders Markdown callouts, inline images and LaTeX-style formulas.

More in Agent skills

See all 581

Provenance gate
github.com
A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.
- Agent skills
- AI evals
Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents
github.com
A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.
- Agent skills
Vitruvius
github.com
An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.
- Agent skills
- AI evals

More in Agent skills

Provenance gate

Expected Harm Calculus (EHC-4): Asimov's Four Laws for Autonomous AI Agents

Vitruvius

Cookies