InvoiceGuard: Invoice Compliance Guardian
Paste the following prompt into your AI chat to install this skill:
Please follow https://skillhub.cn/install/skillhub.md to install @user_26bdbd50/invoice-guard.
About this skill
Duplicate and Compliance Issues in Invoice Review
Teams reviewing expenses, procurement, or finance archives often receive invoices as images, PDFs, OFD, or XML files. The harder part is not only recognition; it is deciding whether one invoice has been reused, whether required fields are complete, whether the invoice status is abnormal, and whether the final evidence can support an auditable compliance record. InvoiceGuard turns upload, field extraction, deduplication, tax verification, and reporting into one workflow, reducing manual checks on fields such as invoice code plus number, amount, date, buyer/seller tax IDs, and goods description.
How It Works
Key steps include:
- Recognition and extraction: Supports JPG/PNG, PDF, OFD, and XML, extracting invoice type, code and number, date, tax-inclusive amount, buyer/seller names and tax IDs, and goods or service description.
- AI deduplication: Uses exact match, field-hash fingerprinting, and image similarity to detect identical invoice numbers, amount/date collisions, and suspicious screenshot or forged-ticket variants.
- Official verification: In Pro capability, connects to a VAT invoice verification platform to return statuses such as normal, voided, red-flushed, or out of control, and checks the recorded amount against system data.
- Compliance reporting: Generates a Markdown report or a Feishu document, and can import invoice details into Bitable for filtering, aggregation, and team review.
- Batch processing: Runs batch recognition, cross-batch deduplication, batch verification, and summary reporting for large invoice sets.
Boundaries and Notes
This skill is suitable as a compliance and pre-reimbursement check, not a replacement for final finance review. Tax verification API access requires a business taxpayer developer account. Unclear images should be retaken or scanned so the invoice number and amount are visible. According to the provided skill notes, raw invoice data is not stored and is discarded after processing.
Use Cases
- Upload JPG/PNG, PDF, OFD invoices and extract invoice number, amount, date, buyer/seller fields before reimbursement.
- Run batch recognition and cross-batch deduplication on travel receipts to flag identical invoice numbers or amount/date collisions.
- Use Pro tax verification to confirm VAT invoice status as normal, voided, red-flushed, or out of control.
- Generate a compliance report in Feishu Docs and import invoice details into Bitable for filtering by status, date, and amount.
Best For
- Finance reviewers who need to check invoice field completeness and suspected duplicates before reimbursement.
- Operations staff handling travel receipts who need to convert images, PDF, and OFD into filterable structured details.
- Accountants doing supplier payment compliance reviews who need VAT invoice status and amount consistency checks.
- Engineers integrating Feishu workflows who want verification results in Feishu Docs and Bitable.
Related Skills
Switch AI from a polite executor into a skeptical thinking partner, using assumption checks, pre-mortems, and evidence gates to expose weak ideas early.
Applies research discipline, data lookup, evidence grading, red-team checks, and structured reporting to analyze AI company investment logic.
Uses Qichacha or Tianyancha MCP data and public information to score corporate credit across 12 dimensions and output a Markdown risk report.
Calculates personal injury compensation via CLI and outputs case summary, standards, line items, sources, and risk notes.