MCPInstall

pandoc

This skill should be used when converting documents between formats (Markdown, DOCX, PDF, HTML, LaTeX, etc.) using pandoc. Use for format conversion, document generation, and preparing markdown for Google Docs or other word processors.

Installs
484
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/plinde/claude-plugins --skill pandoc
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads pandoc automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

Pandoc Document Conversion Skill

Convert documents between formats using pandoc, the universal document converter.

Prerequisites

# Check if pandoc is installed
pandoc --version

# Install via Homebrew if needed
brew install pandoc

Common Conversions

Markdown to Word (.docx)

# Basic conversion
pandoc input.md -o output.docx

# With table of contents
pandoc input.md --toc -o output.docx

# With custom reference doc (for styling)
pandoc input.md --reference-doc=template.docx -o output.docx

# Standalone with metadata
pandoc input.md -s --metadata title="Document Title" -o output.docx

Markdown to PDF

# Requires LaTeX - install one of:
#   brew install --cask basictex      # Smaller (~100MB)
#   brew install --cask mactex-no-gui # Full (~4GB)
# After install: eval "$(/usr/libexec/path_helper)" or new terminal

# Basic conversion (uses pdflatex)
pandoc input.md -o output.pdf

# With table of contents and custom margins
pandoc input.md -s --toc --toc-depth=2 -V geometry:margin=1in -o output.pdf

# Using xelatex (better Unicode support - box drawings, arrows, etc.)
export PATH="/Library/TeX/texbin:$PATH"
pandoc input.md --pdf-engine=xelatex -V geometry:margin=1in -o output.pdf

PDF Engine Selection:

EngineUse When
pdflatexDefault, ASCII content only
xelatexUnicode characters (arrows, box-drawing, emojis)
lualatexComplex typography, OpenType fonts

Markdown to HTML

Critical: Always use -f gfm (GitHub Flavored Markdown) for proper line break and list handling. Standard markdown collapses consecutive lines into paragraphs.

# RECOMMENDED: GitHub Flavored Markdown with full styling
pandoc -f gfm -s -H <(cat << 'STYLE'
<style>
body{font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,sans-serif;max-width:800px;margin:0 auto;padding:2em;line-height:1.6}
h1{border-bottom:2px solid #333;padding-bottom:0.3em}
h2{border-bottom:1px solid #ccc;padding-bottom:0.2em;margin-top:1.5em}
h3{margin-top:1.2em}
ul,ol{margin:0.5em 0 0.5em 1.5em;padding-left:1em}
ul{list-style-type:disc}ol{list-style-type:decimal}
li{margin:0.3em 0}ul ul,ol ul{list-style-type:circle;margin:0.2em 0 0.2em 1em}
table{border-collapse:collapse;width:100%;margin:1em 0}
th,td{border:1px solid #ddd;padding:8px;text-align:left}
th{background-color:#f5f5f5}
code{background-color:#f4f4f4;padding:2px 6px;border-radius:3px}
pre{background-color:#f4f4f4;padding:1em;overflow-x:auto;border-radius:5px}
blockquote{border-left:4px solid #ddd;margin:1em 0;padding-left:1em;color:#666}
</style>
STYLE
) input.md -o output.html

# Quick version (minimal styling)
pandoc -f gfm -s input.md -o output.html

# With hard line breaks (newlines become <br>)
pandoc -f markdown+hard_line_breaks -s input.md -o output.html

# Self-contained (embeds images/CSS)
pandoc -f gfm -s --embed-resources --standalone input.md -o output.html

Format Options:

OptionUse When
-f gfmDefault choice - handles lists, line breaks, tables correctly
-f markdown+hard_line_breaksForce all newlines to become <br>
-f commonmarkStrict CommonMark compliance

HTML for Print-to-PDF (No LaTeX Required)

When LaTeX isn't available, create styled HTML and print to PDF from browser:

# Create inline CSS file
cat > /tmp/print-style.css << 'EOF'
body { font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
       max-width: 800px; margin: 0 auto; padding: 2em; line-height: 1.6; }
h1 { border-bottom: 2px solid #333; padding-bottom: 0.3em; }
h2 { border-bottom: 1px solid #ccc; padding-bottom: 0.2em; margin-top: 1.5em; }
h3 { margin-top: 1.2em; }
/* Lists - critical for proper rendering */
ul, ol { margin: 0.5em 0 0.5em 1.5em; padding-left: 1em; }
ul { list-style-type: disc; }
ol { list-style-type: decimal; }
li { margin: 0.3em 0; }
ul ul, ol ul { list-style-type: circle; margin: 0.2em 0 0.2em 1em; }
ul ol, ol ol { margin: 0.2em 0 0.2em 1em; }
ul ul ul, ol ul ul { list-style-type: square; }
/* Tables */
table { border-collapse: collapse; width: 100%; margin: 1em 0; }
th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
th { background-color: #f5f5f5; }
/* Code */
code { background-color: #f4f4f4; padding: 2px 6px; border-radius: 3px; }
pre { background-color: #f4f4f4; padding: 1em; overflow-x: auto; border-radius: 5px; }
/* Other */
blockquote { border-left: 4px solid #ddd; margin: 1em 0; padding-left: 1em; color: #666; }
@media print { body { max-width: none; } }
EOF

# Convert with embedded styles (ALWAYS use -f gfm)
pandoc -f gfm input.md -s --toc --toc-depth=2 -c /tmp/print-style.css --embed-resources --standalone -o output.html

# Open and print to PDF (Cmd+P > Save as PDF)
open output.html

Word to Markdown

# Extract markdown from docx
pandoc input.docx -o output.md

# With ATX-style headers
pandoc input.docx --atx-headers -o output.md

Useful Options

OptionDescription
-s / --standaloneProduce standalone document with header/footer
--tocGenerate table of contents
--toc-depth=NTOC depth (default: 3)
-V key=valueSet template variable
--metadata key=valueSet metadata field
--reference-doc=FILEUse FILE for styling (docx/odt)
--template=FILEUse custom template
--highlight-style=STYLESyntax highlighting (pygments, tango, etc.)
--number-sectionsNumber section headings
-f FORMATInput format (if not auto-detected)
-t FORMATOutput format (if not auto-detected)

Format Identifiers

FormatIdentifier
Markdownmarkdown, gfm (GitHub), commonmark
Worddocx
PDFpdf
HTMLhtml, html5
LaTeXlatex
RSTrst
EPUBepub
ODTodt
RTFrtf

Google Docs Workflow

To get markdown into Google Docs with formatting preserved:

# 1. Convert to docx
pandoc document.md -o document.docx

# 2. Upload to Google Drive
# 3. Right-click > Open with > Google Docs

Google Docs imports .docx files well and preserves:

  • Headings
  • Bold/italic
  • Lists (bulleted and numbered)
  • Tables
  • Links
  • Code blocks (as monospace)

PSI Document Conversion

For PSI documents with tables and complex formatting:

# Convert PSI markdown to Word
pandoc PSI-document.md \
  --standalone \
  --toc \
  --toc-depth=2 \
  -o PSI-document.docx

# Open for review
open PSI-document.docx

Troubleshooting

Lists/Lines Running Together (HTML)

If bullet points, numbered lists, or consecutive lines merge into one paragraph:

Cause: Standard markdown treats consecutive lines as one paragraph. Lists need blank lines before them.

Fix: Use GitHub Flavored Markdown (-f gfm):

# Always use -f gfm for reliable formatting
pandoc -f gfm -s input.md -o output.html

# For documents where newlines should be <br> tags
pandoc -f markdown+hard_line_breaks -s input.md -o output.html

Why this happens:

  • Standard markdown: Line 1\nLine 2 → <p>Line 1 Line 2</p> (merged)
  • GFM: Better list detection, handles edge cases
  • +hard_line_breaks: Line 1\nLine 2 → Line 1<br>Line 2 (preserved)

Tables Not Rendering

Pandoc requires proper markdown table syntax:

| Header 1 | Header 2 |
|----------|----------|
| Cell 1   | Cell 2   |

Code Blocks Missing Highlighting

Use fenced code blocks with language identifier:

```python
def example():
    pass

### PDF Generation Fails

**"pdflatex not found"** - Install LaTeX:
```bash
# Smaller option (~100MB)
brew install --cask basictex

# Full option (~4GB)
brew install --cask mactex-no-gui

# After install, update PATH
eval "$(/usr/libexec/path_helper)"
# Or open a new terminal

Unicode character errors (box-drawing, arrows, emojis):

# Use xelatex instead of pdflatex
export PATH="/Library/TeX/texbin:$PATH"
pandoc input.md --pdf-engine=xelatex -o output.pdf

No LaTeX available - Use HTML print-to-PDF workflow:

pandoc input.md -s --toc -o output.html
open output.html
# Then Cmd+P > Save as PDF

Self-Test

# Verify pandoc installation
pandoc --version | head -1

# Test basic conversion
echo "# Test\n\nHello **world**" | pandoc -f markdown -t html

FAQ

What does the pandoc skill do?

This skill should be used when converting documents between formats (Markdown, DOCX, PDF, HTML, LaTeX, etc.) using pandoc. Use for format conversion, document generation, and preparing markdown for Google Docs or other word processors.

How do I install pandoc?

Run npx skills add https://github.com/plinde/claude-plugins --skill pandoc in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/pandoc/ (personal) or .claude/skills/pandoc/ (project).

Which AI agents can use pandoc?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is pandoc safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains pandoc?

It is published by plinde in plinde/claude-plugins. It has 484 recorded installs.

More from plinde/claude-plugins

View all →

hammerspoon

plinde/claude-plugins

Open the skill to read its SKILL.md instructions.

41 installs

Popular docs & writing skills

View category →

grill-with-docs

mattpocock/skills

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Docs & Writing1.2M installs

lark-markdown

open.feishu.cn

飞书 Markdown:查看、创建、上传、编辑和比较飞书中的原生 Markdown 文件。当用户要操作飞书 Markdown 文件,或比较其远端版本及本地草稿时使用。纯本地 Markdown 文件操作不触发本 skill。不负责将 Markdown 导入为飞书在线文档,也不负责文件搜索、权限、评论、移动、删除等云空间管理操作。

Docs & Writing778.7K installs

writing-beats

mattpocock/skills

Writing, exploit; assemble raw material into a journey of beats, grounding each term before a beat leans on it.

Docs & Writing490.7K installs

writing-shape

mattpocock/skills

Writing, exploit: shape raw material into an article, paragraph by paragraph.

Docs & Writing490.2K installs

writing-fragments

mattpocock/skills

Writing, explore: mine raw fragments, no structure yet.

Docs & Writing489.6K installs

writing-for-agents

mattpocock/skills

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

Docs & Writing479.3K installs