AI Coding Assistants

Get your AI coding assistant writing correct Xberg code on the first try — right function signatures, right config field names, right per-language conventions — instead of hallucinated APIs you have to fix.

The Xberg plugin teaches your assistant how to use the library, covering extraction, configuration, OCR, chunking, embeddings, batch processing, error handling, and plugins across Python, Node.js/TypeScript, Rust, and CLI.

Installing

Install the Xberg plugin from the xberg-io/xberg marketplace. It ships the Xberg agent skills (extraction APIs, OCR backends, configuration, language conventions) and works with every major coding agent — expand your harness below.

Claude Code

/plugin marketplace add xberg-io/xberg
/plugin install xberg@xberg

Codex CLI

/plugins add https://github.com/xberg-io/xberg

Then search for xberg and select Install Plugin.

Cursor

Settings → Plugins → Add from URL → https://github.com/xberg-io/xberg, then select Xberg.

Gemini CLI

gemini extensions install https://github.com/xberg-io/xberg

Factory Droid

droid plugin marketplace add https://github.com/xberg-io/xberg
droid plugin install xberg@xberg

GitHub Copilot CLI

copilot plugin marketplace add https://github.com/xberg-io/xberg
copilot plugin install xberg@xberg

opencode

Add the package to opencode.json:

{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["@xberg-io/opencode-xberg"]
}

What the Skill Provides

When your AI coding assistant discovers the skill, it knows:

All extraction functions and their correct signatures across languages
Configuration field names (for example, max_chars not max_characters in Python)
Rust feature gates (for example, tokio-runtime for sync functions)
Language-specific conventions (snake_case in Python/Rust, camelCase in Node.js)
Error handling patterns for each language

Quick Examples

from xberg import ExtractInput, ExtractionConfig, OcrConfig, extract

output = await extract(ExtractInput(kind="uri", uri="document.pdf"))
print(output.results[0].content)

config = ExtractionConfig(
    ocr=OcrConfig(backend="tesseract", language="eng"),
    output_format="markdown",
)
output = await extract(ExtractInput(kind="uri", uri="document.pdf"), config=config)

import { ExtractInputKind, extract } from '@xberg-io/xberg';

const output = await extract({
  kind: ExtractInputKind.Uri,
  uri: 'document.pdf',
});
console.log(output.results[0].content);

use xberg::{extract, ExtractInput, ExtractionConfig};

let config = ExtractionConfig::default();
let output = extract(ExtractInput::from_uri("document.pdf"), &config).await?;

xberg extract document.pdf
xberg extract document.pdf --format json --output-format markdown

AI Coding Assistants

Installing

What the Skill Provides

Quick Examples

Further Reading