
Jangbu Import (Grade A)Security-tested data-ai skill for Claude AI. Grade A. 원본 재무 데이터(엑셀·은행 CSV·카드 내역 CSV·영수증 이미지·세금계산서 PDF·카드명세서 PDF)를 표준 거래내역 13개 필드로 변환하는 스킬. PaddleOCR 로컬 처리로 영수증·세금계산서·카드명세서에서 거래 자동 추출, Level 2 민감정보 마스킹
Overview
Key features
- Transaction data transformation
- PaddleOCR-based document processing
- Sensitive information masking
- Support for multiple data sources (Excel, CSV, receipt images, tax invoices, card statements)
- Standardized 13-field transaction history output
Pricing
- Model
- Free
- Category
- Skills
- Rating
- No reviews yet
Use cases
Financial Data Integration
Jangbu Import can be used to integrate financial data from various sources, such as bank transactions, card transactions, and receipts, into a standardized format for easier analysis and processing.
Automated Transaction Extraction
The skill can automatically extract transactions from receipts, tax invoices, and card statements using PaddleOCR, reducing manual data entry efforts and increasing efficiency.
Pros & Cons
Pros
- Transforms various financial data sources into a standardized format
- Automatically extracts transactions from receipts, tax invoices, and card statements using PaddleOCR
- Applies Level 2 sensitive information masking for security
Cons
- Limited support for certain card statement formats, requiring LLM fallback
- May require manual review and correction for inaccurate OCR results
Reviews
Sign in to leave a review.
No reviews yet. Be the first!
Q&A
What happens if the OCR cannot parse a card statement correctly?
If PaddleOCR fails to extract all rows, the response includes needs_llm_fallback:true and lists unparsed rows. Users can review the suggested corrections via the ocr_analyze step, or rely on the LLM fallback parser for formats that lack a dedicated parser (e.g., Samsung, Lotte, BC cards).
Asked by Ivo Novotný · Jul 27, 2025
How does the skill handle sensitive information in card statements?
Before processing, the document is stored locally ( ~/.jangbu/raw/ocr/ ) and only masked views and summaries are sent to the LLM. Level 2 sensitive‑information masking is applied to hide data such as resident registration numbers or business registration numbers.
Asked by Vikram Rao · Jul 10, 2025
Which financial file formats can Jangbu Import process?
Jangbu Import accepts Excel (XLSX) files, bank CSVs, card transaction CSVs, receipt images (JPG/PNG/PDF), tax invoice PDFs, and card statement PDFs. Each source type is specified with a corresponding source_type or doc_type parameter.
Asked by Noelia Campos · Jul 7, 2025
Ask a question
Skills alternatives

Security-tested data-ai skill for Claude AI. Grade A. Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktre

Security-tested data-ai skill for Claude AI. Grade A. GA4 BigQuery Export Schema Reference — complete field reference, nested structures, query patterns, and performance tips

Security-tested data-ai skill for Claude AI. Grade A. Meta Conversions API (CAPI) Setup Reference — architecture, event types, customer information hashing, deduplication, implementation examples, AEM

Security-tested development skill for Claude AI. Grade A. Lista o que uma funcao/metodo chama (call graph direto)

Security-tested data-ai skill for Claude AI. Grade A. Name Haskell test modules after the module under test with a Spec suffix in the same namespace. Use when writing or reviewing Haskell test module

Security-tested data-ai skill for Claude AI. Grade A. Simulate a 5-member expert board deliberation for major decisions. Use when evaluating plans, architecture choices, feature designs, or any decisi

Security-tested development skill for Claude AI. Grade A. MVC avançado via PE (Pontos de Entrada) — adicionar grids customizadas em telas MVC padrão (CNTA300/MATA070/MATA440/MATA460/FINA040 via *STRU)
Security-tested devops skill for Claude AI. Grade A. **WORKFLOW SKILL** — Maintains repository documentation accuracy and freshness across the docs site, agent files, and changelog. WHEN: "update docs
Trending now

Accurate Homework Help with Full Explanations

Document intelligence API that parses, splits, OCRs, and extracts structured data from complex PDFs, slides, and spreadsheets.

Open multimodal 12B model handling interleaved images and text with a 128K context window.

Sponsored answers, paid per click.
