skills.rest
notoriouslabnotoriouslabCommunity·1 Agent Skills Included

doc-cleaner

Convert PDF, Office, and e-books into clean Markdown

Converts PDF, Word, Excel, PowerPoint, Apple Keynote/Numbers, and EPUB files into clean, structured Markdown across 16 formats. Preserves tables, CJK text, and reading order while removing ads and boilerplate from bank statements. Runs fully offline with a no-AI mode or local Ollama, so private documents never leave your machine.
307|40
↗
npx skills add notoriouslab/doc-cleaner --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators
📦 In Repo
notoriouslabnotoriouslab

doc-cleaner

Convert PDFs and Office documents into structured Markdown with YAML frontmatter.

Community
Advanced

Frequently Asked Questions

FAQPage Schema
How to install doc-cleaner?▼

Run `npx skills add notoriouslab/doc-cleaner --all -g -y` in your terminal to install it globally for your agent.

How to convert PDF to Markdown offline?▼

Run `python cleaner.py --input file.pdf --ai none` for fully local extraction with no API keys or network access. Tables and CJK text are preserved automatically.

What file formats does doc-cleaner support?▼

It handles 16 formats including PDF, DOCX, XLSX, CSV, PPTX, Apple Keynote, Numbers, Pages, EPUB, DXF, and TXT, all converted to Markdown.

Can doc-cleaner handle scanned PDFs?▼

Yes. Scanned PDFs are routed to an AI vision mode using Gemini, Groq, or a local Ollama model to rebuild the text and tables.

Is doc-cleaner safe for private financial documents?▼

Yes. The `--ai none` and `--ai ollama` modes process everything locally, so statements and sensitive files never leave your machine.

Related Repositories in Content & Communication

View All in Content & Communication→
anthropicsanthropics
172.9k

skills

Official Anthropic skills for documents, design, and developer workflows

Official📦 18 Skills
bladerblader
39.4k

humanizer

Rewrite AI-sounding text so it reads like a person wrote it

Community📦 2 Skills
DevolutionsDevolutions
25.9k

UniGetUI

Automate software translation reviews, diffs, and localization quality checks

Official📦 7 Skills