Summary
A workhorse for moving content between PDFs, Office files, markdown, HTML, and tabular formats without expecting pixel-perfect results. It's honest about being best-effort: you'll preserve structure and editability, not layout fidelity. The bundled scripts handle single files, batch jobs, PDF utilities like merge and split, table extraction, and basic form filling. Good for when you need clean, editable output from messy sources and can live with lost formatting. The guardrails are sensible: it won't pretend scanned PDFs are anything but OCR jobs, and it warns you to test incrementally on large documents instead of blindly processing gigabyte spreadsheets.
Install to Claude Code
npx -y skills add dkyazzentwatwa/chatgpt-skills --skill document-converter-suite --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.mdView on GitHub
Document Converter Suite
Run best-effort extraction and rebuild workflows across common document formats. Preserve clean structure, not pixel-perfect layout.
Use This For
- Converting between
pdf,docx,pptx,xlsx,txt,csv,md, andhtml - Pulling tables or spreadsheet-style grids into editable outputs
- Running utility PDF operations such as merge, split, rotate, watermark, or page extraction
- Filling simple document or form-style templates
Workflow
- Confirm the source format, target format, and whether editability or fidelity matters more.
- Use
scripts/convert.pyfor single documents andscripts/batch_convert.pyfor folders. - Use the bundled utility scripts when the user needs a focused PDF or table task:
scripts/pdf_toolkit.pyscripts/table_extractor.pyscripts/form_filler.py
- Say explicitly when the output is best-effort and likely to lose layout, images, OCR text, or advanced formatting.
Guardrails
- Do not promise visual fidelity.
- Treat scanned PDFs as OCR problems, not conversion problems.
- Raise safety caps gradually on large sheets or documents instead of processing everything blindly.
References
references/conversion_matrix.mdfor supported paths.references/limitations.mdfor failure modes and tradeoffs.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →First SeenJun 3, 2026
