pdf-to-page

pdf-to-page is a skill for Claude Code from DavidROliverBA/ArchitectKB. It costs 0 tokens per session (3,147 once invoked), scanned A, original, MIT.

A document-conversion workflow that turns a PDF into an Obsidian Page note and saves extracted images as PNG files in an attachments folder.

In plain words
What is it for?
Use it for architecture specifications, meeting presentations, and other PDFs when you want extracted text, recognized tables, reading order, and images in separate files.
Why use it?
It saves the structure and visual material of a PDF in a form that can be edited and linked in an Obsidian vault.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: names the AskUserQuestion tool.

Good fit Use it for architecture specifications, meeting presentations, and other PDFs when you want extracted text, recognized tables, reading order, and images in separate files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidroliverba/architectkb/pdf-to-page
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add DavidROliverBA/ArchitectKB --skill pdf-to-page
Clone the repo
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for pdf-to-page

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidroliverba/architectkb/pdf-to-page/github.svg)](https://agentmods.dev/skills/davidroliverba/architectkb/pdf-to-page)
Your own site
<a href="https://agentmods.dev/skills/davidroliverba/architectkb/pdf-to-page"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/pdf-to-page/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pdf-to-page

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidroliverba/architectkb/pdf-to-page"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/pdf-to-page.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,147 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.03147
Opus 5 $0.00000 $0.01573
Sonnet 5 $0.00000 $0.00629
Haiku 4.5 $0.00000 $0.00315

Measured 11d ago against content hash adf1c192390c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pdf-to-page scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/pdf-to-page/SKILL.md · 428 lines

How it starts

The opening of the file, as written. The whole thing — 428 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pdf-to-page

Convert PDF documents into Page notes with extracted images saved as PNG files in +Attachments/.

Updated: 2026-01-08 - Now uses docling for faster, more accurate PDF processing with native table recognition and reading order detection. User can choose between Sonnet (concise) or Opus (comprehensive) analysis.

Usage

/pdf-to-page <pdf-path>
/pdf-to-page +Attachments/architecture-spec.pdf
/pdf-to-page +Attachments/meeting-presentation.pdf --title "Custom Title"

Instructions

This skill uses docling for PDF structure extraction + 1 agent for visual analysis and YourOrg entity extraction.

Phase 1: PDF Loading & Validation

  1. Verify the PDF file exists at the specified path
  2. Check file extension is .pdf
  3. Note any custom title provided by user (otherwise derive from filename)
  4. Prepare output directory: +Attachments/ for PNG files

Phase 1.5: Analysis Depth Selection

Use AskUserQuestion to ask the user which analysis depth they prefer:

Question: "What level of analysis do you want for this PDF?"
Header: "Analysis"
Options:
  1. "Sonnet - Concise" (Recommended)
     Description: "Faster processing, concise overview. Best for straightforward documents."
  2. "Opus - Comprehensive"
     Description: "Deeper analysis with detailed YourOrg context. Best for complex technical documents."

When to recommend each:

  • Sonnet: Default choice. Fast, cost-effective, good for most documents
  • Opus: Use for complex technical documents, architecture specs, or when comprehensive YourOrg entity extraction is critical

Store the selection for use in Phase 3.

Phase 2: Docling Processing (Fast & Accurate)

Use docling to extract PDF structure with native table recognition and reading order detection:

from docling.document_converter import DocumentConverter
import json

# Initialize converter
converter = DocumentConverter()

# Process PDF
result = converter.convert(pdf_path)

# Extract structured outputs
markdown_content = result.document.export_to_markdown()
doc_dict = result.document.export_to_dict()
json_data = json.dumps(doc_dict, indent=2)

# Get statistics
page_count = len(result.document.pages)
table_count = len(result.document.tables) if hasattr(result.document, 'tables') else 0
image_count = len(result.document.images) if hasattr(result.document, 'images') else 0

Read the full file on GitHub · 428 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 428 lines · 0 tokens per session scan A adf1c192390c

Subscribe to this mod's changes

pdf-to-page is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,147 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories