# Local Doc Ops

> Use when extracting, inspecting, splitting, or converting local PDFs, documents, and image-based files before they enter a knowledge pipeline.

- Skill: `zarubinvibe/local-doc-ops` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add zarubinvibe/local-doc-ops`
- Raw SKILL.md: https://api.skillmd.com/api/skills/zarubinvibe/local-doc-ops/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: DevOps & Infra
- Author: zarubinvibe (https://skillmd.com/u/zarubinvibe)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/zarubinvibe/local-doc-ops

---


# Local Document Operations

Use local deterministic tools before spending model context.

Preferred order:

1. Use structured parsers for PDFs and office documents.
2. Use Apple Vision OCR for images on macOS.
3. Use transcription for audio or video.
4. Only then ask a model to interpret unclear content.

Keep raw extracted text in cache or inbox. Write only refined knowledge into the vault.

Bundled helper:

```bash
python skills/local-doc-ops/pdf-kit.py --help
```