md-to-office

Converts Markdown files to PDF files using the pandoc command-line utility. Use when a user asks to convert a .md or markdown file to a .pdf file.

Security Scan

The skill's instructions clearly rely on the pandoc binary (and often a LaTeX engine) but the metadata does not declare that dependency or provide a source/homepage — that mismatch and lack of guardrails merit caution.

Purpose & Capability

The name/description and SKILL.md consistently describe using pandoc to convert Markdown to PDF (coherent purpose). However, the registry metadata lists no required binaries or install spec even though pandoc (and sometimes a LaTeX engine) is required at runtime. The skill also has no source/homepage to verify provenance.

Instruction Scope

SKILL.md stays on-topic (how to run pandoc, examples for PDF, templates, reading from URLs). It permits reading local files (templates, reference.docx) and fetching web content — which is expected for a converter but not explicitly constrained. The instructions do not tell the agent to check for the pandoc binary beforehand or to avoid reading arbitrary sensitive paths, nor do they document safe handling of remote content.

Install Mechanism

This is an instruction-only skill (no install spec or code), so it doesn't write files to disk. That's lower install risk. However, because it relies on an external binary, the lack of a declared dependency is an inconsistency: the agent may attempt to execute commands that aren't present.

Credentials

The skill requests no environment variables, credentials, or config paths — which is appropriate for a local pandoc conversion tool.

Persistence & Privilege

The skill is not 'always' and does not request elevated/persistent privileges or modify other skills. Autonomous invocation is allowed (platform default) but not combined with other high-risk features.

What to consider before installing

This skill appears to be a straightforward pandoc usage guide, but there are some gaps you should address before installing/using it: 1) Verify that pandoc (and a LaTeX engine like xelatex if you need PDF output) is present on the agent host — the skill does not declare this dependency. 2) Be aware the skill's examples include reading local template/reference files and fetching URLs; ensure the agent has permission only to read intended input files and that you do not convert sensitive files unintentionally. 3) Because there's no source or homepage, you cannot verify provenance — prefer skills with a known source. 4) Ask the skill author to declare required binaries and add pre-run checks (e.g., validate pandoc exists, confirm file paths, and limit network fetches) before granting it invocation. If you decide to try it, test on non-sensitive sample files first.

Local Pandoc Conversion Skill

This skill uses the pandoc command-line utility to convert documents between numerous markup formats.

Basic Usage

The fundamental structure of a pandoc command is:

pandoc [options] [input-file]…

Simple Conversion

To convert a Markdown file to HTML:

pandoc -o output.html input.md

Specifying Formats

While pandoc can infer formats from file extensions, you can be explicit with the -f (from) and -t (to) flags.

# Convert HTML to Markdown
pandoc -f html -t markdown input.html

Standalone Documents

To create a complete document with a proper header and footer (e.g., a full HTML file), use the -s or --standalone flag.

pandoc -s -o output.html input.md

Advanced Examples

The following examples are extracted from the official Pandoc User's Guide.

PDF Output

To create a PDF, pandoc typically uses a LaTeX engine. Ensure one is installed.

# Basic PDF creation
pandoc input.md -o output.pdf

# Control PDF engine and style via variables
pandoc input.md -o output.pdf --pdf-engine=xelatex -V geometry:margin=1in -V fontsize=12pt

Document Structure & Metadata

Pandoc can automatically generate a table of contents and use document metadata.

# Create a document with a Table of Contents (up to level 3 headings)
pandoc --toc --toc-depth=3 -o output.docx input.md

# Set metadata fields from the command line
pandoc -M title:"My Report" -M author:"Galactus" -o output.pdf input.md

Templates and Styling

You can control the final output's structure and style with templates and other options.

# Use a custom template for HTML output
pandoc -s --template=my-template.html -o output.html input.md

# For HTML output, link to a custom CSS file
pandoc -s --css=styles.css -o output.html input.md

# For DOCX output, use a reference document for styling
pandoc --reference-doc=reference.docx -o output.docx input.md

Reading from the Web

Pandoc can directly fetch and convert content from a URL.

pandoc -f html -t markdown https://www.fsf.org

Other Useful Options

# Preserve tabs instead of converting them to spaces
pandoc --preserve-tabs ...

# Control line wrapping in the output source code
pandoc --wrap=none ...

# Shift heading levels (e.g., make all H1s into H2s, H2s into H3s)
pandoc --shift-heading-level-by=1 ...

This enhanced documentation provides a more robust foundation for using pandoc.