Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

LiteParse — Local Document Parsing

A skill for extracting layout-aware text with bounding boxes from PDFs, Office files and images entirely on your own machine.

Docs & OfficeIntermediate★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

LiteParse teaches Claude Code to drive a fast Rust-based document parser that runs fully offline:

  • Extracts layout-preserved plain text from PDF, DOCX/XLSX/PPTX and image files
  • Emits structured JSON with per-item bounding boxes, font metadata and OCR confidence
  • Runs OCR on scans via bundled Tesseract (language codes, parallel workers, air-gapped tessdata)
  • Renders page screenshots as PNG for multimodal reasoning over charts and handwriting
  • Supports batch directory ingestion, page subsets, password-protected PDFs, stdin/bytes input and phrase search via search_items

Who it's for

  • Engineers building layout-aware RAG pipelines over large PDF corpora
  • Teams that need citation grounding with exact on-page coordinates
  • Security-sensitive orgs that cannot ship documents to a cloud parser
  • Researchers ingesting scanned papers, protocols or supplementary material

Examples

  1. Bulk literature ingest: lit batch-parse ./papers ./parsed --format json --recursive, then load the coordinate-rich JSON into a vector store.
  2. Citation highlighting: combine text_items bboxes with search_items(page.text_items, "Materials and Methods") to draw highlight boxes in a viewer.
  3. Figure analysis: parser.screenshot("report.pdf", page_numbers=[3,4]) to capture chart pages as PNGs and pair them with extracted text.

· · · Install guide · · ·

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the skills/liteparse folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/liteparse/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/liteparse ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal and clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  2. Create the skills directory: mkdir -p ~/.claude/skills
  3. Copy the skill in: cp -r scientific-agent-skills/skills/liteparse ~/.claude/skills/
  4. Install the parser: uv pip install "liteparse==2.0.0" (or pip install "liteparse==2.0.0")
  5. Verify: lit --help and python -c "import liteparse; print(liteparse.__version__)"
  6. Optional: install LibreOffice for Office formats and ImageMagick for images.
  7. Restart Claude Code and try a prompt like "Parse this PDF to JSON with bounding boxes".
View source on GitHub ↗License: MIT