aws-solutions-library-samples

Extraction Pipeline — Data skill for Claude Code

Data community

Extraction Pipeline — Core Domain Logic — GenAI IDP Accelerator.

How to install Extraction Pipeline

Installs to ~/.claude/skills/aws-solutions-library-samples-accelerated-intelligent-document-processing-on-aws-extraction-pipeline/SKILL.md

Terminal

mkdir -p ~/.claude/skills/aws-solutions-library-samples-accelerated-intelligent-document-processing-on-aws-extraction-pipeline && curl -fsSL https://raw.githubusercontent.com/aws-solutions-library-samples/accelerated-intelligent-document-processing-on-aws/HEAD/.claude/skills/extraction-pipeline.md -o ~/.claude/skills/aws-solutions-library-samples-accelerated-intelligent-document-processing-on-aws-extraction-pipeline/SKILL.md

Restart Claude Code, or start a new session, for it to be picked up.

What Extraction Pipeline does

Extraction Pipeline — Core Domain Logic — GenAI IDP Accelerator

Processing Flow

Documents → S3 Input Bucket → EventBridge → Queue Sender Lambda
→ SQS → Queue Processor Lambda → Step Functions
→ [OCR → Classification → Extraction → Assessment → Rule Validation → Summarization]
→ S3 Output Bucket

Two Processing Modes

Controlled by `use_bda` flag in configuration:

Pipeline Mode (`use_bda: false`) — Default

OCR: Amazon Textract (or Bedrock OCR backend)
**Classificati

Alternatives in Data

Skill Production Pipeline — Claude-skills — Effective: 2026-03-07 Applies to ALL new skills, improvements, and deployments 5.3k ★
Ars Full — ARS full pipeline — research → write → review → revise → finalize 4.5k ★
Osint Employees — Gather employee names + email patterns for password spray prep 4.5k ★