Tano73Tano73/agent-skills/skills/pandoc-convert/SKILL.md

pandoc-convert

Skill2 starsChanged 2 months agoMITView on GitHub

Convert documents between formats using pandoc. Use this skill whenever the user wants to convert, transform, or export a document from one format to another — for example Markdown to Word, HTML to PDF, Word to Markdown, EPUB to HTML, RST to DOCX, or any other format-to-format conversion. Trigger this skill any time the user mentions "convert", "export", "trasforma", "converti", or references two different document formats together, even if they don't explicitly mention pandoc.

In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skill-creatorSkill
- ffpa-analyzerSkill
- llm-wiki-managerSkill
- markdown-chapter-splitterSkill
- mineru-pdf-to-mdSkill
- skill-security-auditorSkill
- team-kbSkill
- todo-managerSkill
- wbs-generatorSkill

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Identify the output format: if the user hasn't specified a target format, always ask before converting.
line 14
Distinctive:
If the user asks what formats are supported:
line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Pandoc Document Converter

This skill converts documents between formats using pandoc. Pandoc supports a wide range of formats including Markdown, HTML, DOCX, EPUB, PDF, RST, LaTeX, ODT, and many more.

Workflow

Identify the input: locate the source file the user wants to convert. If the path is unclear or the file doesn't exist, ask the user to confirm before proceeding.
Identify the output format: if the user hasn't specified a target format, always ask before converting. Don't guess. Example: "In quale formato vuoi convertire il file?" or "What output format do you want?".
Determine the output file name: derive it from the input file name with the appropriate extension (e.g. report.md → report.docx). Ask the user if they'd prefer a different name or location.
Run pandoc: execute the conversion:
```
pandoc "<input_file>" -o "<output_file>"
```
Pandoc usually auto-detects formats from file extensions, so you rarely need --from or --to unless the extension is ambiguous.
Confirm success: tell the user the output file path and confirm it was created. If the conversion fails, show the pandoc error and suggest a fix (e.g. missing LaTeX engine for PDF, unsupported format combination).

Common format pairs and tips

Input → Output	Notes
`.md` → `.docx`	Works out of the box
`.md` → `.pdf`	Requires a LaTeX engine (`pdflatex`, `xelatex`) or `--pdf-engine=wkhtmltopdf`
`.docx` → `.md`	Good for extracting content from Word docs
`.html` → `.docx`	Pandoc handles most HTML well
`.rst` → `.html`	Common for Python docs
`.md` → `.epub`	Works out of the box
`.md` → `.html`	Use `--standalone` (`-s`) to get a full HTML page

For PDF output, if a LaTeX engine is not available, suggest --pdf-engine=wkhtmltopdf or converting to HTML first.

Checking available formats

If the user asks what formats are supported:

pandoc --list-input-formats
pandoc --list-output-formats

Error handling

Missing input file: confirm the path with the user.
Unsupported conversion: explain the limitation and suggest an intermediate step (e.g. DOCX → Markdown → PDF).
PDF engine missing: inform the user and suggest installing texlive or using wkhtmltopdf.
Encoding issues: try adding --from=markdown+smart or specifying the encoding explicitly.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free