From agent-skills
Read PDF files with Go. Extracts text page by page, supports page ranges, keyword search, and summarizes content. Notes OCR requirement for scanned PDFs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agent-skills:pdfThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use `${CLAUDE_SKILL_DIR}` to reference the Go file. For scanned/image-only PDFs, inform the user OCR is needed (e.g. `ocrmypdf scanned.pdf searchable.pdf`).
Use ${CLAUDE_SKILL_DIR} to reference the Go file. For scanned/image-only PDFs, inform the user OCR is needed (e.g. ocrmypdf scanned.pdf searchable.pdf).
go run ${CLAUDE_SKILL_DIR}/read_pdf.go <file.pdf> [flags]
| Flag | Description |
|---|---|
--pages <range> | Page range: 1-5, 3, 2,4,7 |
--search <term> | Search keyword (case-insensitive), report page + line |
--lines <n> | Max lines per page in preview (default 20) |
--summary | Print only page count and first page content |
--full | Print full text of every page (no line limit) |
npx claudepluginhub bos-hieu/agent-skills --plugin agent-skillsProcess PDF files: extract text, create new PDFs, merge and split documents using pdftotext, PyMuPDF, ReportLab, and pdfkit.
Parses local or remote PDF files into markdown or structured JSON using fastCRW. Supports CLI, MCP, and REST interfaces with options for AI summaries and structured extraction.
Reads, creates, and edits PDF files using Python libraries (pypdf, pdfplumber). Handles text/table extraction, merging, splitting, rotation, watermarks, forms, encryption, OCR.