split-batchlisted

Split a single multi-document PDF into one PDF per detected document. Post-processing for stacks of paperwork scanned in one pass: detect document boundaries from page content (page-number resets, letterhead/sender changes, address blocks) or from blank separator sheets, present a proposed split map, and emit one PDF per document after the user confirms. Use when the user has a searchable PDF that bundles several documents and says things like "split this batch", "split this stack", "these are multiple documents", "I scanned a pile", "separate these documents", or when `naps2-scan` hands off a batch-mode scan. Requires a searchable (OCR'd) PDF as input — it does NOT scan. For scanning, use `naps2-scan`.
xxthunder/xxthunder-agentic-skills · ★ 1 · Data & Documents · score 63

Install: claude install-skill xxthunder/xxthunder-agentic-skills

# Split Batch Split one multi-document PDF into N single-document PDFs: **extract page text → detect boundaries → confirm split map → emit PDFs**. ## When This Skill Triggers - "Split this batch" / "Split this stack" / "Separate these documents" - "These are multiple documents" / "I scanned a pile / stack" - `naps2-scan` hands off after a batch-mode scan (its Step 3b) - The user has one searchable PDF in the working directory that bundles several distinct documents This skill is **post-processing only**. It does not drive a scanner and does not OCR — it needs a PDF whose text is already extractable. To scan paper, use `naps2-scan` (which can chain into this skill). To merge two simplex halves, use `simplex-merge`. ## Prerequisites - **A searchable PDF** in the working directory (typically `naps2-scan` output after OCR and any simplex merge). If the PDF has no extractable text, detection cannot run — tell the user to OCR it first (re-scan via `naps2-scan` with `--enableocr`). - **`uv` on PATH** — the helper scripts under `scripts/` are [PEP 723](https://peps.python.org/pep-0723/) inline-metadata Python scripts run via `uv run`. Verify with `uv --version`. `uv` resolves `pypdf` automatically; no manual `pip install`. Install with `winget install astral-sh.uv` (Windows) or the installer at <https://docs.astral.sh/uv/>. If a prerequisit