Skill Claude · ChatGPT / MCP
Product specs from PDFs
Extract product specifications from catalogs and PDFs.
What it does
Give Norma the product PDFs and the scope to extract. Norma reads the text, tables and visual evidence, keeps variants distinct, and returns structured specifications with source pages.
Install
Connect Arch Studio in Claude or ChatGPT, then return to your conversation and ask Norma for the task. Your assistant uses its available file access and tools to carry out the skill.
Add to Claude
Add to ChatGPTVersions and source
Arch Studio 1.5.1.2 · MCP
Available as MCP workflow instructions in compatible Claude and ChatGPT connections. The assistant performs the work with its own tools and permissions and verifies the actual result before reporting completion.
Arch Studio 1.5.1.2 · Open source
Included in the public plugin for Claude Code and Codex. In this version: Product specs from PDFs — Turn PDF price books, fact sheets and specification sheets into structured product schedules.
Usage
Ask Norma in plain language. With Arch Studio connected through MCP, no $ or / command is required. Norma is your assistant working with Arch Studio.
Use Arch Studio to extract the two chair variants on these catalog pages. Keep each model’s dimensions and finishes separate, cite pages and labels, and do not combine available options into an invented SKU.The full catalog lives in your assistant once Arch Studio is connected. Ask: Norma, what can you do? List the skills, tools, agents and workflows available in this host, grouped by practice area.
What it extracts
Models and variants
Norma keeps distinct catalog models and options separate rather than inventing a selected SKU combination.
Dimensions and specifications
Norma retains labels, units and the page evidence supporting each field.
Price-book information
Norma keeps base prices and options tied to their actual source meaning.
Coverage
Norma identifies unreadable pages, incomplete fields and uncertainty in the extraction.
Workflow
- Scope — Norma identifies the PDFs and requested variant depth.
- Extract — Norma reads the actual pages and organizes the supported product fields.
- Review — Norma presents the parsed records and source gaps before any requested save.
Pairs with
Clean product data. Norma can standardize the supported fields after PDF extraction.