# Convert Pdf

> >

- **Type:** Skill
- **Install:** `agentstack add skill-digital-stoic-org-agent-skills-convert-pdf`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [digital-stoic-org](https://agentstack.voostack.com/s/digital-stoic-org)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [digital-stoic-org](https://github.com/digital-stoic-org)
- **Source:** https://github.com/digital-stoic-org/agent-skills/tree/main/convert/skills/convert-pdf

## Install

```sh
agentstack add skill-digital-stoic-org-agent-skills-convert-pdf
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Convert PDF → Markdown

## 1. Parse & Validate

Extract from arguments:

| Arg | Required | Default |
|-----|----------|---------|
| `$1` input PDF | ✅ | — |
| `→ path` output | No | `./converted/{kebab-basename}.md` |
| `--docling` | No | Force docling |
| `--complex` | No | Force docling |
| `--ocr` | No | Force docling + OCR |

Validate: file exists, ends `.pdf`, is readable. Create `./converted/` if missing.

## 2. Select Backend

```bash
# If --docling, --complex, or --ocr → skip to docling path
# Otherwise, probe with pdftotext:
CHARS=$(pdftotext -layout -l 3 "$INPUT" - | wc -c)
# CHARS = 100 → pdftotext path
```

## 3a. pdftotext Path (default — 90% of files)

```bash
pdftotext -layout "$INPUT" "${OUTPUT%.md}.txt"
```

Post-process the `.txt` → `.md` using Write tool:
- Split on `\f` → `---` page separators
- ALL CAPS lines > 20 chars → `## Header`
- Collapse 3+ blank lines → 2
- Prepend YAML frontmatter: `source`, `pages`, `backend: pdftotext`
- Write final `.md`, delete intermediate `.txt`

## 3b. docling Path (complex/OCR)

First: `toolsmith:install-dependency docling` if not available.

```bash
# Find .venv by scanning upward from CWD
source "$(find_venv)/bin/activate"
docling --to md --output ./converted/ "$INPUT"
```

If `--ocr` flag: `docling --to md --ocr --ocr-engine easyocr --output ./converted/ "$INPUT"`

⚠️ **Docling rules — violations create 0-byte files:**

| ✅ Correct | ❌ Wrong |
|-----------|---------|
| `--to md` | `--to markdown` |
| `--output DIR` | `-o DIR` |
| Writes to filesystem | NEVER `>` redirect or `\| tee` |

## 4. Verify & Report

```bash
[ -s "$OUTPUT" ] || { echo "❌ Output empty"; exit 1; }
wc -c "$OUTPUT"
```

Report: `✅ Converted {file} → {output} ({size}, {backend})`

See `reference.md` for backend comparison, advanced docling options, and troubleshooting.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [digital-stoic-org](https://github.com/digital-stoic-org)
- **Source:** [digital-stoic-org/agent-skills](https://github.com/digital-stoic-org/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-digital-stoic-org-agent-skills-convert-pdf
- Seller: https://agentstack.voostack.com/s/digital-stoic-org
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.