skill / Product & Materials Research

Product Spec PDF Parser

A Claude Code skill that reads product PDF files — price books, fact sheets, and spec sheets — and extracts structured furniture specification data into a standardized FF&E schedule. Claude reasons over extracted text to handle wildly varying layouts.

procurement data-lookup
Install ↓ View on GitHub →
New to skills? Read the cheat sheet for architects and designers →

What it does

Type /product-spec-pdf-parser in Claude Code and point it at PDF files or a folder. The skill extracts text with PyMuPDF, then Claude reads and reasons over the content to identify products, variants, SKUs, dimensions, materials, and pricing — structuring everything into a 24-field FF&E schedule.

Handles price books (Herman Miller Aeron), fact sheets with SKUs (Hem Alphabeta), spec sheets, and multi-product catalogs. No regex or custom parsers — Claude IS the parser.

Install

Claude Desktop:

  1. Open Customize → Browse plugins
  2. Click + → Add marketplace from GitHub
  3. Enter AlpacaLabsLLC/skills-for-architects
  4. Install the Product & Materials Research plugin

Claude Code (terminal):

claude install github:AlpacaLabsLLC/skills-for-architects/05-materials-research
pip install PyMuPDF

Usage

/product-spec-pdf-parser

Then provide PDF paths or a folder:

/product-spec-pdf-parser

~/Documents/specs/alphabeta-floor-lamp.pdf
~/Documents/specs/aeron-price-book.pdf

Choose variant depth — expand (one row per variant, default) or summarize (one row per product).

Output schema

24 fields per product, extending the Canoa Clipper FF&E format with PDF-specific fields:

FieldExample
Product NameAlphabeta Floor Lamp
VariantDiamond, Black
SKUHEM-AF-DB
Brand / DesignerHem / Luca Nichetto
Collection / CategoryAlphabeta / Lighting
DescriptionModular floor lamp with interchangeable shades
W / D / H / Seat H— / — / 135.5 / —
Unit / Weightcm / 4.5 kg
MaterialsAluminium, Steel
Colors/FinishesBlack
List Price / Price Adder595.00 / —
CurrencyEUR
Warranty / Certifications— / CE
Country of OriginSweden
Source Filealphabeta-fact-sheet.pdf

PDF types supported

TypeStrategy
Fact sheet with SKUsOne row per SKU
Fact sheet with finishesOne row per upholstery/finish option
Price book / configuratorOne row per product type, options summarized
Product catalogRows for each distinct product

How it handles failures

  • Scanned/image PDFs — detected and flagged for OCR
  • Password-protected PDFs — caught and reported
  • Large PDFs (100+ pages) — processed in 10-page chunks with progress updates

After every batch: Parsed: X products from Y PDF(s)

Pairs with

Use /product-spec-bulk-fetch for web URLs instead of PDFs, then /product-spec-bulk-cleanup to normalize. Chain: PDF parse → cleanup → spec-ready schedule.