liteparse · sammcj — Claude Code skill: document parsing, how to install
liteparse extracts text and structure from PDF, DOCX, PPTX, XLSX and images to markdown locally, no cloud or LLM required.
Apache-2.0 ★ 173 updated 2026-10-24
npx skills add sammcj/agentic-coding --skill liteparse -a claude-codeWhat liteparse does
Parses documents via the lit CLI built on @llamaindex/liteparse. Handles OCR through built-in Tesseract.js or external HTTP servers like EasyOCR and PaddleOCR, outputs plain text or JSON with bounding boxes. You can target page ranges, skip OCR for text-only PDFs, raise DPI to 300 for quality, or generate page screenshots for agents that need visual layout.
Office formats convert to PDF before parsing — LibreOffice is required for Word, PowerPoint and Excel; ImageMagick for raster images. Without them, those formats will not process. Batch mode via batch-parse handles directories, and liteparse.config.json saves repeated flags.
What it helps with
- extract text from PDF with block coordinates preserved
- parse DOCX or PPTX to markdown without manual conversion
- run OCR across a directory of scanned documents
- generate page screenshots from PDF for an LLM agent
- process XLSX tables into structured JSON
Example prompts for the agent
- Parse
contract.pdfto markdown, pages 1–5 and 10 only - Run OCR on all PDFs in
./scans, output to./output - Generate screenshots of the first 10 pages of
report.pdfat 300 DPI
How to install liteparse
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill liteparse -a claude-code2Manually: put the files in place
~/.claude/skills/liteparse/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/liteparse/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill liteparse -a codex2Manually: put the files in place
.agents/skills/liteparse/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill liteparse -a cursor2Manually: put the files in place
.cursor/skills/liteparse/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sammcj/agentic-coding Skills/liteparse/SKILL.md2Manually: put the files in place
.github/skills/liteparse/SKILL.md1Skills CLI (Vercel)
npx skills add sammcj/agentic-coding --skill liteparse -a gemini-cli2Platform CLI
gemini skills install https://github.com/sammcj/agentic-coding --path Skills/liteparseManually: put the files in place
.devin/skills/liteparse/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about liteparse
How to install liteparse in Claude Code?
Run npx skills add sammcj/agentic-coding --skill liteparse -a claude-code. The skill appears in ~/.claude/skills/liteparse/SKILL.md.
What does liteparse do?
Extracts text and structure from PDF, Office documents and images locally via the lit CLI. Built-in OCR, output to markdown or JSON with bounding boxes, batch directory processing.
Can I use liteparse without installing it globally?
Yes, replace lit <args> with npx -y @llamaindex/liteparse <args> in commands. The tool runs via npx without global installation.
Source text
SKILL.md · Apache-2.0
---
name: liteparse
description: Provides fast document to markdown extraction. Use this skill when the user asks to parse, perform multi-format document conversion or spatially extract text from an unstructured file (PDF, DOCX, PPTX, XLSX, images, etc.) locally.
---
# LiteParse Skill
Parse unstructured documents (PDF, DOCX, PPTX, XLSX, images, and more) locally with LiteParse: fast, lightweight, no cloud dependencies or LLM required.
## Step 0 - Use via npx, or install LiteParse
NOTE: Rather than installing `liteparse` globally, you can instead run it directly with `npx`, substituting `lit <args>` with `npx -y @llamaindex/liteparse <args>` in the commands below.
```bash
npx -y @llamaindex/liteparse
```
Otherwise if installing globally, use `pnpm install -g @llamaindex/liteparse` and then run `lit <args>`.
---
## Step 1 - Produce the CLI Command or Script
### Parse a Single File
```bash
# Basic text extraction
lit parse document.pdf
# JSON output saved to a file
lit parse document.pdf --format json -o output.json
# Specific page range
lit parse document.pdf --target-pages "1-5,10,15-20"
# Disable OCR (faster, text-only PDFs)
lit parse document.pdf --no-ocr
# Use an external HTTP OCR server for higher accuracy
lit parse document.pdf --ocr-server-url http://localhost:8828/ocr
# Higher DPI for better quality
lit parse document.pdf --dpi 300
```
### Batch Parse a Directory
```bash
lit batch-parse ./input-directory ./output-directory
# Only process PDFs, recursively
lit batch-parse ./input ./output --extension .pdf --recursive
```
### Generate Page Screenshots
Screenshots are useful for LLM agents that need to see visual layout.
```bash
# All pages
lit screenshot document.pdf -o ./screenshots
# Specific pages
lit screenshot document.pdf --pages "1,3,5" -o ./screenshots
# High-DPI PNG
lit screenshot document.pdf --dpi 300 --format png -o ./screenshots
# Page range
lit screenshot document.pdf --pages "1-10" -o ./screenshots
```
---
## Step 3 - Key Options Reference
### OCR Options
| Option | Description |
|--------|-------------|
| (default) | Tesseract.js - zero setup, built-in |
| `--ocr-language fra` | Set OCR language (ISO code) |
| `--ocr-server-url <url>` | Use external HTTP OCR server (EasyOCR, PaddleOCR, custom) |
| `--no-ocr` | Disable OCR entirely |
### Output Options
| Option | Description |
|--------|-------------|
| `--format json` | Structured JSON with bounding boxes |
| `--format text` | Plain text (default) |
| `-o <file>` | Save output to file |
### Performance / Quality Options
| Option | Description |
|--------|-------------|
| `--dpi <n>` | Rendering DPI (default: 150; use 300 for high quality) |
| `--max-pages <n>` | Limit pages parsed |
| `--target-pages <pages>` | Parse specific pages (e.g. `"1-5,10"`) |
| `--no-precise-bbox` | Disable precise bounding boxes (faster) |
| `--skip-diagonal-text` | Ignore rotated/diagonal text |
| `--preserve-small-text` | Keep very small text that would otherwise be dropped |
---
## Step 4 - Using a Config File
For repeated use with consistent options, generate a `liteparse.config.json`:
```json
{
"ocrLanguage": "en",
"ocrEnabled": true,
"maxPages": 1000,
"dpi": 150,
"outputFormat": "json",
"preciseBoundingBox": true,
"skipDiagonalText": false,
"preserveVerySmallText": false
}
```
For an HTTP OCR server:
```json
{
"ocrServerUrl": "http://localhost:8828/ocr",
"ocrLanguage": "en",
"outputFormat": "json"
}
```
Use with:
```bash
lit parse document.pdf --config liteparse.config.json
```
---
## Step 5 - HTTP OCR Server API (Advanced)
If the user wants to plug in a custom OCR backend, the server must implement:
- **Endpoint**: `POST /ocr`
- **Accepts**: `file` (multipart) and `language` (string) parameters
- **Returns**:
```json
{
"results": [
{ "text": "Hello", "bbox": [x1, y1, x2, y2], "confidence": 0.98 }
]
}
```
Ready-to-use wrappers exist for EasyOCR and PaddleOCR in the LiteParse repo.
---
## Supported Input Formats
| Category | Formats |
|----------|---------|
| PDF | `.pdf` |
| Word | `.doc`, `.docx`, `.docm`, `.odt`, `.rtf` |
| PowerPoint | `.ppt`, `.pptx`, `.pptm`, `.odp` |
| Spreadsheets | `.xls`, `.xlsx`, `.xlsm`, `.ods`, `.csv`, `.tsv` |
| Images | `.jpg`, `.jpeg`, `.png`, `.gif`, `.bmp`, `.tiff`, `.webp`, `.svg` |
Office documents require LibreOffice; images require ImageMagick. LiteParse auto-converts these formats to PDF before parsing.
© sammcj · Apache-2.0 · sammcj/agentic-coding
Similar skills
All skills for Office documents →liteparse by other authors comes first.