pdf

name	pdf
description	Use when the user brings a PDF into their BRICKS project and wants its content in the app — menus, price lists, schedules, catalogs, brochures, reports, or scanned documents. Extracts text on the design machine with a bundled script, routes the results into Data entries, Property Bank values, data-calculation sources, or media assets, and covers converting pages to images for slideshows. Also covers wiring runtime PDF ingestion (vectorStore RAG, parseDocument in data calculations) for apps that accept documents while running — note that mobile/TV launchers cannot parse PDF at runtime (web/desktop only). Triggers on "import this PDF", "read the menu from this PDF", "use this catalog", or any .pdf path in the prompt. Do NOT use for creating or exporting PDF files, or for Word docs, spreadsheets, and slide decks (use the docx / xlsx / pptx skills).
license	MIT
metadata	{"version":"0.1.0","author":"BRICKS"}

PDF Import

Turn a PDF into live app content: Data entries, Property Bank values, media assets, or searchable knowledge.

Announce at start: "I'm using the pdf skill to import this PDF."

Step 1: Extract the text

Run the bundled script. Resolve the path against this skill directory (the directory containing this SKILL.md) and pass the absolute script path to bun. Keep it a single command — no pipes, redirections, or chained shell commands. Internally it runs the version-pinned officeparser@5.1.1 CLI via bunx: the first run downloads it (needs network once), then it's cached. If that first run fails writing to Bun's cache in a restricted sandbox, the error message shows the project-local cache fallback to use.