How do I install the Pyragify skill?

Run npx skillmds@latest add auto-skiller/pyragify in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Pyragify safe to use?

SkillMD's automated safety review verdict for this skill is PASS. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: makes network calls. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Pyragify?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Pyragify free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Pyragify?

Auto-Skiller (@auto-skiller) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Pyragify by auto-skiller — Agent Skill

Name: Pyragify
Rating: 4.5 (4 reviews)
Author: Auto-Skiller

File contents

pyragify Skill

Source

Repo: https://github.com/ThomasBury/pyragify
PyPI: pip install pyragify
Version: v0.2.0 (April 2026)
License: Unlicense (fully free)

What It Does

Converts any code repository or document directory into clean, semantically-chunked .txt files optimized for NotebookLM ingestion. Run this BEFORE uploading to NotebookLM.

Setup

pip install pyragify

Usage

CRITICAL: Always use relative portable paths to execute the OS Engine so the workspace can be ported to new machines without breaking:

# With a config file (recommended)
.\.venv\Scripts\pyragify.exe --config-file config.yaml

# Or inline
.\.venv\Scripts\pyragify.exe \
  --repo-path /path/to/repository \
  --output-dir /path/to/output \
  --max-words 200000 \
  --skip-dirs "__pycache__" \
  --skip-dirs "node_modules" \
  --verbose

Example `config.yaml`

repo_path: c:\Users\BAB AL SAFA\Desktop\open-workspace
output_dir: c:\Users\BAB AL SAFA\Desktop\open-workspace\.core\toolbox_library\core.toolbox\notebooklm\skills\pyragify\output
max_words: 200000
max_file_size: 10485760  # 10 MB
skip_patterns:
  - "*.log"
  - "*.tmp"
skip_dirs:
  - "__pycache__"
  - "node_modules"
  - ".git"
verbose: false

Output Structure

output/
  python/      ← Python functions, classes, comments
  markdown/    ← Markdown sections split by headers
  html/        ← HTML script and style chunks
  css/         ← CSS rule chunks
  other/       ← All other readable file types
  remaining/   ← Overflow chunks after word limit
  metadata.json
  hashes.json  ← MD5 hashes for incremental re-runs (only reprocesses changed files)

Supported Inputs

.py — chunked by function/class/comment
.md, .markdown — split by header sections
.html — script and style chunks
.css — CSS rule chunks
All other UTF-8 readable files — included as plain text

Workflow with notebooklm-py

# Step 1: Preprocess the workspace
pyragify --config-file config.yaml

# Step 2: Upload output chunks to NotebookLM
notebooklm create "Workspace Analysis"
notebooklm use <notebook_id>
notebooklm source add "./output/markdown/chunk_0.txt"
notebooklm source add "./output/python/chunk_0.txt"

# Step 3: Query and generate
notebooklm ask "What are the architectural gaps in this workspace?"

---name: pyragifydescription: Converts code repositories and document directories into semantically-chunked text files optimized for NotebookLM ingestion, with support for config files and incremental processing.---# pyragify Skill## Source- **Repo**: https://github.com/ThomasBury/pyragify- **PyPI**: `pip install pyragify`- **Version**: v0.2.0 (April 2026)- **License**: Unlicense (fully free)## What It DoesConverts any code repository or document directory into clean, semantically-chunked `.txt` files optimized for NotebookLM ingestion. Run this BEFORE uploading to NotebookLM.## Setup```bashpip install pyragify```## Usage**CRITICAL:** Always use relative portable paths to execute the OS Engine so the workspace can be ported to new machines without breaking:```bash# With a config file (recommended).\.venv\Scripts\pyragify.exe --config-file config.yaml# Or inline.\.venv\Scripts\pyragify.exe \ --repo-path /path/to/repository \ --output-dir /path/to/output \ --max-words 200000 \ --skip-dirs "__pycache__" \ --skip-dirs "node_modules" \ --verbose```## Example `config.yaml````yamlrepo_path: c:\Users\BAB AL SAFA\Desktop\open-workspaceoutput_dir: c:\Users\BAB AL SAFA\Desktop\open-workspace\.core\toolbox_library\core.toolbox\notebooklm\skills\pyragify\outputmax_words: 200000max_file_size: 10485760 # 10 MBskip_patterns: - "*.log" - "*.tmp"skip_dirs: - "__pycache__" - "node_modules" - ".git"verbose: false```## Output Structure```output/ python/ ← Python functions, classes, comments markdown/ ← Markdown sections split by headers html/ ← HTML script and style chunks css/ ← CSS rule chunks other/ ← All other readable file types remaining/ ← Overflow chunks after word limit metadata.json hashes.json ← MD5 hashes for incremental re-runs (only reprocesses changed files)```## Supported Inputs- `.py` — chunked by function/class/comment- `.md`, `.markdown` — split by header sections- `.html` — script and style chunks- `.css` — CSS rule chunks- All other UTF-8 readable files — included as plain text## Workflow with notebooklm-py```bash# Step 1: Preprocess the workspacepyragify --config-file config.yaml# Step 2: Upload output chunks to NotebookLMnotebooklm create "Workspace Analysis"notebooklm use <notebook_id>notebooklm source add "./output/markdown/chunk_0.txt"notebooklm source add "./output/python/chunk_0.txt"# Step 3: Query and generatenotebooklm ask "What are the architectural gaps in this workspace?"```

Frequently asked questions

Pyragify