Why should I use batches instead of one large run?

Batching provides better memory management, allows for periodic review of data accuracy, and creates checkpoints to prevent re-processing large amounts of work in case of system errors.

What are the prerequisites for using this skill?

You must have your database initialized (init_db.py), PDFs placed in the staging folder, and the dashboard service stopped to ensure database availability.

What happens if a PDF fails during batching?

The ingestion skill logs the error for that specific file and continues with the rest of the batch, allowing you to review and retry failures separately at the end.

Can I stop the process and resume later?

Yes. The skill uses a database ingestion log and TodoWrite lists to track progress, enabling you to pause the workflow and pick up exactly where you left off without duplicates.

Batch PDF Statement Ingestion

Name: Batch PDF Statement Ingestion
Author: houfu

byhoufu

0•

生産性とワークフロー

Orchestrates the processing of large volumes of bank statements into your ledger using resumable, checkpointed batch workflows.

This skill is designed for users of the Lavender Ledger system who need to import significant amounts of historical financial data. It orchestrates the ingestion of 50+ PDF bank statements by breaking the workload into manageable batches, allowing for granular progress tracking via TodoWrite and manual verification between steps. By leveraging a database-backed ingestion log, it ensures that process interruptions or errors do not lead to duplicate entries, providing a robust, fail-safe way to handle high-volume personal finance data entry.

主な機能

01Configurable batch sizes to optimize memory and review frequency

02Built-in error isolation to prevent single failures from stopping the workflow

03User-in-the-loop verification between processing cycles

04Checkpointing and resumable processing via database-backed logs

05Progress tracking using TodoWrite for transparent status updates

060 GitHub stars

ユースケース

01Importing several years of historical bank statements during initial setup

02Processing large monthly batches of business or personal expense receipts

03Recovering from interrupted data imports without duplicating database entries

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add houfu/lavender-ledger batch_ingestion

For use in Claude.ai and ChatGPT

Download Skill