kimi-pdf

Converts documents to PDFs and edits them via a unified command-line interface.

221|54|Updated Feb 2, 2026
One-click install
npx skills add https://github.com/thvroyal/kimi-skills --skill kimi-pdf
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kimi-pdf
Source: https://github.com/thvroyal/kimi-skills/tree/main/skills/kimi-pdf
Command: npx skills add https://github.com/thvroyal/kimi-skills --skill kimi-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, pikepdf, pdfplumber, pypdf, tectonic, LibreOffice, and includes scripts (resource) components.

What problem does it solve?

This Skill consolidates HTML-based and LaTeX-based PDF generation workflows with robust processing of existing PDFs. It streamlines academic and professional document creation by combining web-based rendering, LaTeX typesetting, and Python-based PDF manipulation into a single, repeatable pipeline.

Core Features & Use Cases

  • HTML to PDF: Convert HTML content into polished PDFs using Playwright + Paged.js, with support for diagrams (Mermaid) and math (KaTeX) while preserving layout.
  • LaTeX via Tectonic: Compile LaTeX sources into publication-ready PDFs with log filtering and per-PDF statistics.
  • Process Existing PDFs: Read, extract text/tables/images, merge/split pages, and edit metadata or form fields using a unified CLI.
  • Use Case: A research group autogenerates conference papers from HTML drafts, then refines figures and equations, all within a single workflow.

Quick Start

Use the pdf skill to convert a document.html to PDF, or to compile main.tex, or to process an existing PDF via the unified CLI. Example commands: pdf.sh html document.html; pdf.sh latex main.tex; pdf.sh process info document.pdf.

Frequently Asked Questions about kimi-pdf

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert HTML to PDF while preserving diagrams and math equations?

Convert HTML to PDF using Playwright and Paged.js, which natively support Mermaid diagrams and KaTeX math equations while preserving the original layout for professional document generation.

What is the best way to compile LaTeX sources into publication-ready PDFs?

Compile LaTeX sources into publication-ready PDFs using Tectonic, which provides log filtering and per-PDF statistics to ensure accurate typesetting for academic papers and professional reports.

Can I extract text and merge pages from an existing PDF document?

Yes, you can extract text, tables, and images, or merge and split pages from existing PDFs using a unified CLI powered by Python libraries like pdfplumber, pypdf, and pikepdf.

Does this PDF processing workflow require installing LibreOffice?

LibreOffice is an optional dependency for additional document conversion tasks. The core PDF pipeline relies on Playwright, Tectonic, and Python libraries like pikepdf, pdfplumber, and pypdf.

How do I automate generating conference papers from HTML drafts and refining figures?

Automate conference paper generation by converting HTML drafts to PDF using Playwright, then refine figures and equations within a single workflow that combines web-based rendering and LaTeX typesetting into a repeatable pipeline.