my skill

Convert Markdown files to PDF using Pandoc and LaTeX with options for syntax highlighting, table of contents, and custom CSS.

Security Scan

The skill's files and runtime instructions are coherent with its stated purpose (convert Markdown to PDF via pandoc + LaTeX); it requires local Pandoc/LaTeX to be installed and does not request credentials or network endpoints.

Purpose & Capability

The SKILL.md and the included Python script both implement Markdown->PDF conversion via pandoc and a LaTeX engine, which matches the description. Minor inconsistency: the registry metadata lists no required binaries, but the documentation and script clearly depend on external binaries (pandoc and a LaTeX engine). This is a manifest-documentation mismatch but not a functional or malicious issue.

Instruction Scope

Instructions and the script are narrowly scoped to: checking pandoc/LaTeX presence, reading the provided .md (and optional CSS) file, and invoking pandoc to produce a PDF. There are no instructions to read unrelated files, access environment secrets, or send data to external endpoints. The script uses subprocess.run to call local pandoc, which is expected for this task.

Install Mechanism

This is an instruction-only skill with a bundled script and no install spec. Nothing in the package downloads or installs software automatically — the SKILL.md directs users to install pandoc/LaTeX themselves from official sources. Risk from install mechanism is low.

Credentials

The skill requests no environment variables, credentials, or configuration paths. The functionality legitimately requires only local binaries (pandoc and a LaTeX engine); no secrets or external API access are requested.

Persistence & Privilege

The skill is not marked always:true and is user-invocable. It does not attempt to modify other skills or system-wide agent settings. Autonomous invocation is allowed by default but is not combined with elevated privileges or broad credentials here.

Assessment

This skill appears to do what it claims: convert Markdown to PDF by calling your local pandoc and LaTeX engine. Before installing or running: (1) ensure you install pandoc and a LaTeX distribution from official sources; (2) review and run the included script locally rather than granting it automated network access — it only executes pandoc locally via subprocess; (3) avoid converting untrusted Markdown on systems where your LaTeX distribution allows shell escape (LaTeX can execute system commands when configured to do so), or run conversions in a sandbox if inputs are untrusted; (4) note the manifest omission that doesn't list pandoc/LaTeX as required binaries — this is a documentation/registry oversight, not a functional red flag. If you need higher assurance, inspect the script (scripts/md2pdf.py) and test on a non-sensitive machine first.

md2pdf

Convert Markdown files to beautifully typeset PDF using Pandoc + LaTeX.

Prerequisites

• pandoc — winget install pandoc or https://pandoc.org/installing.html
• LaTeX engine — XeLaTeX recommended (bundled with TeX Live or MiKTeX). Install via:
  • winget install MiKTeX or https://miktex.org/download
  • Or winget install TeXLive for TeX Live

The script auto-detects available engines in order: xelatex > lualatex > pdflatex.

Quick Start

Run the bundled script:

python scripts/md2pdf.py <input.md> [output.pdf]

Options:

• --toc — Include table of contents
• --css <file> — Apply custom CSS stylesheet
• --highlight <style> — Code highlight style (default: tango)

Default Behavior

The script applies these defaults when using XeLaTeX/LuaLaTeX (the preferred engines):

• CJK support: SimSun (serif), SimHei (sans), Microsoft YaHei (mono)
• Margin: 1 inch all sides
• Code blocks: syntax highlighted with Pygments

Workflow

1. Confirm the input .md file exists and is readable
2. Run scripts/md2pdf.py with appropriate options
3. If pandoc or LaTeX is missing, report the installation instructions to the user
4. Return the generated PDF path to the user (send the file if applicable)

Advanced: Direct Pandoc Calls

For options not covered by the script, call pandoc directly:

# Custom LaTeX template
pandoc input.md -o output.pdf --pdf-engine=xelatex --template=custom.tex

# Specific page size
pandoc input.md -o output.pdf --pdf-engine=xelatex -V geometry:margin=2cm -V papersize:a4

# Metadata
pandoc input.md -o output.pdf --pdf-engine=xelatex -V title="My Report" -V author="Author"