Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From buildbrain
Extract schedules, text, and tables from PDF construction drawings. Can search for specific terms to find relevant pages. Results saved to output/ for cross-validation.
npx claudepluginhub thebrownproject/buildbrainHow this skill is triggered — by the user, by Claude, or both
Slash command
/buildbrain:pdf-extractThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Extract data from PDF construction documents. For full CLI command syntax and flags, see `/cli-tools`.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.
Share bugs, ideas, or general feedback.
Extract data from PDF construction documents. For full CLI command syntax and flags, see /cli-tools.
If no file path provided:
ls data/*.pdf 2>/dev/null
Multiple files → ask user. No files → tell user to place PDF in data/.
schedules (auto-detects what's in the PDF)search first to find pages, then tables on those pagestables or textScripts are at skills/cli-tools/scripts/pdf_extract.py. Always include --save.
python skills/cli-tools/scripts/pdf_extract.py <file.pdf> <command> [options] --save
Common patterns:
# What schedules are in this PDF?
schedules --save
# Find the door schedule
search "door schedule" --save
# then: tables --pages <matched_pages> --save
# Extract everything from a page
text --pages 5 --save
tables --pages 5 --save
schedules: list each type found, page, headers, row countsearch: matching pages with snippets, suggest extraction commandstables: describe each table — headers, rows, what it contains/cross-validate door to compare against IFC model"text extractionsearch with specific terms