./Doc Cleaner

將 PDF、DOCX、XLSX 及純文字檔轉換為乾淨的結構化 Markdown。

notoriouslab
Document Processing
159
Python
159
Stars
16
Forks
1
Watch

>README

>Code Quality

TestsCI/CDDockerTypesSKILL.md

>Repository Health

Inactive1 issues

>Contributors

notoriouslabsunnyworm

>File Structure

files
.claude
commands
spectra
ai
__init__.py
base.py
gemini.py
groq.py
mlx.py
nvidia.py
ollama.py
classifiers
__init__.py
noise.py
pdf_classifier.py
pii.py
output
__init__.py
markdown.py
parsers
__init__.py
docx.py
pdf.py
text.py
xlsx.py
prompts
__init__.py
default.txt
finance.txt
.env.example
.gitignore
CLAUDE.md
cleaner.py
config.example.json
CONTRIBUTING.md
LICENSE
README.en.md
README.md
requirements.txt
SECURITY.md
SKILL.md
View on GitHub

>Technical Details

Language
Python
License
MIT
Created
Mar 9, 2026
Updated
Apr 2, 2026
install.sh
View Source

Clone the repository to your local machine

$git clone https://github.com/notoriouslab/doc-cleaner.git
Get SkillZIP

Resources

GitHub RepositoryReport Issue
Browse Document Processing

Alternatives to Doc Cleaner

Compare features and choose the best fit for your workflow.

SkillMatchStarsLanguageUpdatedHealth
Doc Cleanercurrent
notoriouslab
—159PythonThis year
DOCX
anthropics
Same category. Both use Python
37%107,891PythonThis year
XLSX
anthropics
Same category. Both use Python
37%107,891PythonThis year
Claude Skills
alirezarezvani
Same category
37%99TypeScriptThis year

>Related Skills

View all in category →
/

PDF

107,891

Comprehensive PDF toolkit for extracting text/tables, creating, merging, splitting documents, and handling forms

document-processinganthropics
featured
/

Google Docs Skill

4

Google Docs & Drive skill for AI coding assistants (Claude Code, gemini-cli, Codex, Cursor). Fork of robtaylor/google-docs-skill with Markdown support & large doc insertion.

document-processingdanielkwapien
/

Tax Organizer

11

Claude skill to organizes and processes personal tax documents to generate accurate, tax reports and drafts.

document-processingelderengineer