Skills
.Work. You
Rest

llm-extraction-formfill

Community

Convert OCR to structured JSON with provenance.

Data & Analytics#provenance#JSON#uncertainty#OCR#extraction#transcripts
AuthorJustinChaney2023
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Convert OCR/transcript text into a structured JSON form with provenance and uncertainty using local LLMs. Use when implementing extraction prompts, schema-constrained decoding, validation, and safe form-filling (no hallucinations).

Core Features & Use Cases

  • Schema-guided extraction with provenance and uncertainty
  • Deterministic validators and a safe form-filling workflow
  • Reusable prompts and schemas to extract structured fields from documents

Quick Start

Use the llm-extraction-formfill skill to transform an OCR transcript into a filled_form.json with value, confidence, source_spans, and rationale.

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: llm-extraction-formfill
Download link: https://github.com/JustinChaney2023/orate/archive/main.zip#llm-extraction-formfill

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.