How do I install the @6171/pdf Toolkit skill?

Run npx skillmds@latest add starchild-ai-agent/6171-pdf-toolkit 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 @6171/pdf Toolkit safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with @6171/pdf Toolkit?

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 @6171/pdf Toolkit free to use?

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

Who published @6171/pdf Toolkit?

starchild-ai-agent (@starchild-ai-agent) published this skill. Their other Agent Skills are listed on their SkillMD profile.

@6171/pdf Toolkit by starchild-ai-agent

Name: @6171/pdf Toolkit
Author: starchild-ai-agent

File contents

PDF Toolkit

Core Capabilities

Action	Description	Command
Info	Extract metadata (title, author, pages, size, PDF version)	`--action info --input file.pdf`
Text	Extract all text from every page	`--action text --input file.pdf`
Classify	Detect scanned (image-based) vs text-based PDF	`--action classify --input file.pdf`
Merge	Combine multiple PDFs into one	`--action merge --inputs a.pdf b.pdf --output merged.pdf`
Split	Split into individual pages	`--action split --input file.pdf --output-dir out/`

Usage

# Quick info
python3 skills/pdf-toolkit/scripts/pdf_extract.py --action info --input report.pdf

# Extract text
python3 skills/pdf-toolkit/scripts/pdf_extract.py --action text --input report.pdf --json

# Check if scanned
python3 skills/pdf-toolkit/scripts/pdf_extract.py --action classify --input report.pdf

# Merge
python3 skills/pdf-toolkit/scripts/pdf_extract.py --action merge --inputs a.pdf b.pdf --output combined.pdf

# Split into pages
python3 skills/pdf-toolkit/scripts/pdf_extract.py --action split --input report.pdf --output-dir output/pages

Gotchas

Scanned PDFs (no selectable text) produce empty text extraction. The classify action detects this. For OCR, recommend an external OCR tool (Tesseract, etc.).
Encrypted PDFs need --password. pypdf handles most encryption types.
Large PDFs (1000+ pages) — text extraction with pdfplumber is slower but higher quality than pypdf. Use info first to check page count.
Merge preserves all pages from each input file.
Split outputs to --output-dir (default: output/split_pages), each page named page_0001.pdf.

---name: 6171-pdf-toolkitdescription: Inspect, extract text, merge, split, and classify PDFs. Use when the user wants to work with PDF documents — extract text, check metadata, merge/split pages, or classify scanned vs digital PDFs.---# PDF Toolkit## Core Capabilities| Action | Description | Command ||--------|-------------|---------|| **Info** | Extract metadata (title, author, pages, size, PDF version) | `--action info --input file.pdf` || **Text** | Extract all text from every page | `--action text --input file.pdf` || **Classify** | Detect scanned (image-based) vs text-based PDF | `--action classify --input file.pdf` || **Merge** | Combine multiple PDFs into one | `--action merge --inputs a.pdf b.pdf --output merged.pdf` || **Split** | Split into individual pages | `--action split --input file.pdf --output-dir out/` |## Usage```bash# Quick infopython3 skills/pdf-toolkit/scripts/pdf_extract.py --action info --input report.pdf# Extract textpython3 skills/pdf-toolkit/scripts/pdf_extract.py --action text --input report.pdf --json# Check if scannedpython3 skills/pdf-toolkit/scripts/pdf_extract.py --action classify --input report.pdf# Mergepython3 skills/pdf-toolkit/scripts/pdf_extract.py --action merge --inputs a.pdf b.pdf --output combined.pdf# Split into pagespython3 skills/pdf-toolkit/scripts/pdf_extract.py --action split --input report.pdf --output-dir output/pages```## Gotchas- **Scanned PDFs** (no selectable text) produce empty text extraction. The `classify` action detects this. For OCR, recommend an external OCR tool (Tesseract, etc.).- **Encrypted PDFs** need `--password`. pypdf handles most encryption types.- **Large PDFs** (1000+ pages) — `text` extraction with pdfplumber is slower but higher quality than pypdf. Use `info` first to check page count.- **Merge** preserves all pages from each input file.- **Split** outputs to `--output-dir` (default: `output/split_pages`), each page named `page_0001.pdf`.

Frequently asked questions

@6171/pdf Toolkit