Agent Plugins Marketplace
← All plugins

pdf-extract

v1.0.0

Extract information from PDFs reliably. Triages whether a text layer exists, routes to the right path (native text extraction / OCR + layout-aware parser / vision-model direct), serializes tables in a lossless form, and binds every extracted field to a page and a verbatim span. Covers scanned PDFs, multi-column layouts, tables, and schema-constrained extraction with citations.

Claude Code1 Skill

By dobachi0 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes
Claude Code
Parsed components
1 skill or MCP entry
Source updated
Aug 30, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install plugin

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install pdf-extract@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/dobachi/claude-skills-marketplace

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/pdf-extract/.

Plugin files

plugins/pdf-extract/
├── .claude-plugin/plugin.json
└── skills/pdf-extract/SKILL.md

Included Skills1

pdf-extractskills/pdf-extract/SKILL.md

Extracts information from PDFs by triaging the file first (does a text layer exist? is the layout simple?) and routing to the cheapest path that survives it — native text extraction, OCR plus a layout-aware parser, or a vision model reading page images — then binds every extracted field to a page number and a verbatim span. Use when the user wants text, tables, or structured fields pulled out of a PDF — "PDFから抽出して", "PDFを読み取って", "この請求書/論文/報告書からデータを取って", "PDFを構造化データにして", "スキャンPDFをOCRして", "extract from this PDF", "parse this PDF", "OCR this scan", "get the tables out of this PDF". Also use when a PDF extraction already went wrong (garbled reading order, merged columns, broken tables, invented numbers). Not for summarizing text you have already extracted (`document-summary`), not for pulling out figures and images (`document-figures`), not for web research (`grounded-research`), not for auditing a finished document's claims (`fact-checker`), not for translating extracted text (`faithful-translation`).

Plugin manifests1

plugins/pdf-extract/.claude-plugin/plugin.json
{
  "name": "pdf-extract",
  "description": "Extract information from PDFs reliably. Triages whether a text layer exists, routes to the right path (native text extraction / OCR + layout-aware parser / vision-model direct), serializes tables in a lossless form, and binds every extracted field to a page and a verbatim span. Covers scanned PDFs, multi-column layouts, tables, and schema-constrained extraction with citations.",
  "version": "1.0.0",
  "author": {
    "name": "dobachi"
  }
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[pdf-extract on Agent Plugins Marketplace](https://pluginsmp.com/plugins/pdf-extract)