skills.rest
opensquilla
opensquillaOFFICIAL
Explore all skills by this author →
WebsiteGitHub

meta-pdf-reformat-pipeline

Modernizes legacy PDFs through extraction, rewriting, auditing, and re-merging.

6.8k|540|Updated May 6, 2026
Search Tags:#audit#text extraction#pipeline#PDF#rewrite#reformat#document modernization
One-click install
npx skills add https://github.com/opensquilla/opensquilla --skill meta-pdf-reformat-pipeline
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: meta-pdf-reformat-pipeline
Source: https://github.com/opensquilla/opensquilla/tree/main/src/opensquilla/skills/exp/meta-pdf-reformat-pipeline
Command: npx skills add https://github.com/opensquilla/opensquilla --skill meta-pdf-reformat-pipeline

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Legacy PDFs such as scanned manuals, historical contracts, and old legal documents often contain outdated phrasing and inconsistent structure, and manually rewriting and reassembling them page by page is slow and error-prone.

Core Features & Use Cases

  • Four-Step Pipeline: Orchestrates structural extraction, natural-language rewriting of problem pages, an audit summary, and re-merging into the final PDF.
  • Human Review Checkpoint: The audit step produces a change summary so a reviewer can inspect modifications before the merge is finalized.
  • Composable Sub-Skills: Delegates work to pdf-toolkit, nano-pdf, and summarize skills, with a documented manual fallback sequence.
  • Use Case: Given a decades-old scanned operations manual, extract its text, modernize the wording on problematic pages, review the change summary, and produce a refreshed final PDF.

Quick Start

Reformat the attached legacy PDF by extracting its text, rewriting the outdated pages, summarizing the changes, and merging everything back into a modernized document.

Frequently Asked Questions about meta-pdf-reformat-pipeline

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I modernize an old PDF document automatically?▼

Run the reformat pipeline, which extracts structured text and page metadata, rewrites problematic pages with modernized phrasing, generates an audit summary of changes, and merges the rewritten pages back into the source PDF.

How to rewrite PDF pages without losing the original meaning?▼

The rewrite step instructs the nano-pdf skill to modernize phrasing and standardize headings while explicitly preserving original meaning. An audit step then summarizes all changes so a reviewer can verify fidelity before merging.

Can I review changes before the reformatted PDF is finalized?▼

Yes. The audit step produces a change summary of up to 600 words describing what was rewritten, giving a human reviewer a diff-style overview before the merge step finalizes the document.

What happens if the automated PDF pipeline fails?▼

The skill documents a manual fallback: run pdf-toolkit extract, then nano-pdf rewrite, then summarize, then pdf-toolkit merge as separate steps to complete the same workflow manually.

What types of documents work best with PDF reformatting?▼

The pipeline targets historical contracts, scanned manuals, and legal documents that need modernization. Documents must be processable by the underlying pdf-toolkit extraction step to yield structured text and page metadata.

Related Skills

Explore More Content & Communication Skills→
guccangguccang
3

ocr-and-documents

Extract text, tables, metadata, and images from PDFs and scanned documents.

Community
Advanced
jdonohoojdonohoo
15

enterprise

Formalize enterprise governance, risk, and compliance decision workflows with stakeholder sign-offs.

Community
Advanced
kreuzberg-devkreuzberg-dev
9.2k

extracting-with-ocr

Extract text from scanned PDFs and images using OCR backends and language packs.

Official
Intermediate
claude-office-skillsclaude-office-skills
368

pdf-to-docx

Convert PDF files to editable Word documents with pdf2docx.

Official
Intermediate