Liteparse

If you need to extract text and data from PDFs, Word docs, PowerPoint slides, or images without sending anything to the cloud, this is a solid local option. It wraps the LiteParse CLI, which means you get fast parsing without LLM overhead or API costs. The setup asks you to confirm the npm package is installed globally before running commands. Worth noting that it comes from a fork of llamaparse-agent-skills and has passed security audits from Gen Agent Trust Hub, Socket, and Snyk. Good fit for when you're handling sensitive documents or just want deterministic extraction without the ceremony of a full document intelligence service.

skills.sh installs: 165
GitHub stars: 234
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add flora131/atomic --skill liteparse --agent claude-code

Installs into .claude/skills of the current project.

Files

LiteParse

Extract text from documents locally with the lit CLI — a fast, model-free parser. This skill is about using it cheaply: each lit parse re-runs full extraction, and every line you dump into the conversation is paid for on every subsequent turn. The patterns below come from analyzing real agent traces where the same PDF was parsed up to 9 times and single image reads cost 140k+ characters of context. Don't repeat those mistakes.

The golden rule: parse ONCE to a file, then search the file

lit parse re-extracts the whole document every time you call it. Re-parsing per search is the #1 waste seen in traces. Parse a document exactly once, to a temp file, then run all your searches against that file:

# ONE TIME, per document. --no-ocr for born-digital PDFs (almost all reports) — much faster.
lit parse "/abs/path/doc.pdf" --format text --no-ocr -o /tmp/doc.txt && wc -l /tmp/doc.txt

Then search the file with cheap shell tools — never re-run lit parse to search again.