# Wigolo Extract

Local-first structured extraction from any webpage, tables, definition lists...

- Repository: https://github.com/KnockOutEZ/wigolo (5517 stars)
- Category: AI and agents
- License: AGPL-3.0-only
- Last updated: 2026-11-01
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add KnockOutEZ/wigolo --skill wigolo-extract -g -a claude-code -y`
Codex: `npx skills add KnockOutEZ/wigolo --skill wigolo-extract -g -a codex -y`
Cursor: `npx skills add KnockOutEZ/wigolo --skill wigolo-extract -g -a cursor -y`
Gemini CLI: `npx skills add KnockOutEZ/wigolo --skill wigolo-extract -g -a gemini-cli -y`

## Description

Local-first structured extraction from any webpage, tables, definition lists, key-value pairs, JSON-LD, microdata, chart hints (SVG titles / aria-labels / figcaptions), brand assets, and metadata. Use when the user wants structured data, pricing tables, feature comparisons, or says "extract the table", "get structured data", "pull the pricing", "extract as JSON". For autonomous navigation across many pages, use wigolo's `agent` tool instead.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# wigolo extract

Structured data extraction beyond simple markdown.

## Quick Reference

```json
// Full structured extraction (ALWAYS prefer this)
{ "url": "https://bun.sh", "mode": "structured" }

// JSON Schema extraction, heuristic field matching
{ "url": "https://example.com/pricing", "mode": "schema", "schema": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "string" }, "sku": { "type": "string" } } } }

// CSS selector extraction
{ "url": "https://example.com", "mode": "selector", "css_selector": ".product-card", "multiple": true }

// Metadata only (matches fetch metadata shape)
{ "url": "https://example.com", "mode": "metadata" }

// From raw HTML
{ "html": "<table>...</table>", "mode": "tables" }
```

## Modes

| Mode | What it extracts | When to use |
|------|-----------------|-------------|
| `structured` | Tables + definition lists + JSON-LD + chart hints + key-value pairs | **Default choice, use this** |
| `tables` | HTML tables only | When you specifically need only tables |
| `schema` | Fields matching a JSON Schema (LLM-sourced fields verified against source; hallucinated values returned as null) | When you know the exact fields you want |
| `brand` | Logo, favicon, colors, fonts, social_links (with provenance; favicons never promote to logo_url) | Brand kit / identity extraction |
| `metadata` | OpenGraph, meta tags, JSON-LD, canonical_url, og_image | For page metadata only |
| `selector` | CSS selector matches | When you know the exact CSS selector |

**Always use `mode: "structured"` instead of `mode: "tables"`.** Structured captures everything tables does, plus definitions, key-value pairs, JSON-LD, and chart descriptions.

## Chart Hints

When a page has visual charts (SVG, Canvas), `chart_hints` contains text descriptions extracted from aria-labels, SVG `<title>`, and figcaptions. Use these to describe visual data even when the underlying data is JavaScript-rendered.

## Schema Mode

The rest: https://github.com/KnockOutEZ/wigolo/blob/HEAD/skills/wigolo-extract/SKILL.md