agentleFS
RylaispiritRylaispirit/rylai-codex-hermes-skills/skills/document-converter-suite/SKILL.md

document-converter-suite

Skill56 starsChanged 3 months agoMITView on GitHub

Convert local PDF, Office, Markdown, HTML, text, CSV, TSV, and JSON files; batch-convert folders, extract tables, fill templates, and edit PDF pages.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use the bundled scripts for deterministic local-file work.

    line 20
  2. Very specific:

    Add --overwrite only after checking that replacing the destination is intended.

    line 38
  3. Very specific:

    Read references/routes.md when choosing between conversion engines or explaining limitations.

    line 75
  4. Distinctive:

    Never execute macros, embedded programs, or document attachments.

    line 81
  5. Distinctive:

    Treat OCR as a separate step.

    line 82
  6. Distinctive:

    Prefer semantic extraction for editing and LibreOffice or Pandoc routes for format conversion.

    line 83
  7. Distinctive:

    Do not promise exact fonts, pagination, animation, chart, formula, or layout preservation.

    line 84
  8. Distinctive:

    Use a dedicated format skill when visual fidelity or advanced editing is the primary requirement.

    line 85

≈ “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

Document Converter Suite

Original portable workflow by Rylai.

Use the bundled scripts for deterministic local-file work. Keep source files unchanged and inspect every generated artifact.

Start With A Dependency Check

python scripts/rylai_convert.py doctor

The report distinguishes required Python support from optional routes provided by MarkItDown, Pandoc, LibreOffice, pypdf, python-docx, python-pptx, openpyxl, and pdfplumber.

Convert One File

python scripts/rylai_convert.py convert input.docx output.md
python scripts/rylai_convert.py convert notes.md notes.docx
python scripts/rylai_convert.py convert workbook.xlsx workbook.pdf

Add --overwrite only after checking that replacing the destination is intended.

Convert A Folder

python scripts/rylai_convert.py batch source output --to md --recursive
python scripts/rylai_convert.py batch source output --to pdf --include docx --include pptx

The batch command preserves relative paths and reports every failed file.

Focused Utilities

PDF page operations:

python scripts/rylai_pdf_pages.py info report.pdf
python scripts/rylai_pdf_pages.py extract report.pdf excerpt.pdf --pages 1,3-5
python scripts/rylai_pdf_pages.py merge combined.pdf part-a.pdf part-b.pdf
python scripts/rylai_pdf_pages.py split report.pdf split-pages
python scripts/rylai_pdf_pages.py rotate report.pdf rotated.pdf --pages all --degrees 90

Table extraction:

python scripts/rylai_tables.py data.xlsx table.csv --sheet Summary
python scripts/rylai_tables.py report.pdf table.md --table 2

Template filling:

python scripts/rylai_template_fill.py template.docx filled.docx --values values.json
python scripts/rylai_template_fill.py template.md filled.md --set project=Rylai --set status=Ready

Read references/routes.md when choosing between conversion engines or explaining limitations.

Operating Rules

  • Resolve scripts relative to this skill folder.
  • Accept local files only; do not download a URL and convert it without explicit user approval.
  • Never execute macros, embedded programs, or document attachments.
  • Treat OCR as a separate step. A scanned PDF may contain no extractable text.
  • Prefer semantic extraction for editing and LibreOffice or Pandoc routes for format conversion.
  • Do not promise exact fonts, pagination, animation, chart, formula, or layout preservation.
  • Use a dedicated format skill when visual fidelity or advanced editing is the primary requirement.
  • Report the selected route, missing dependency, and any known loss in the final answer.

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.