Skills
.Work. You
Rest

schematron

Community

Convert messy HTML into structured JSON.

Data & Analytics#html#json#web-scraping#extract#schematron#inference.net
AuthorMagicWifiMoney
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Schematron extracts reliable, strict JSON from noisy or inconsistent HTML pages so you can turn web pages, government opportunity listings, RFPs, and press releases into clean structured data without expensive LLM calls.

Core Features & Use Cases

  • High-volume HTML → JSON: Use schematron-3b for cost-effective extraction and schematron-8b for higher accuracy on complex schemas.
  • Schema-first extraction: Enforce strict JSON Schemas with required fields and additionalProperties set to false to ensure consistent outputs.
  • Practical workflows: Batch-process SAM.gov opportunities, scrape competitor sites, parse RFPs, and monitor agency press releases while cleaning HTML and handling large-context pages.

Quick Start

Extract SAM.gov opportunity fields from this HTML and return strict JSON that matches the SAM_OPPORTUNITY_SCHEMA.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: schematron
Download link: https://github.com/MagicWifiMoney/openclaw-starter-kit/archive/main.zip#schematron

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.