agentleFS
Sign inStart free
johnsonhk88johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction/skills/bank-statement-parsing/SKILL.md

bank-statement-parsing

Skill631 starsChanged 8 days agoApache-2.0View on GitHub

Guidelines for parsing bank statements using YOLO layout detection + OCR + LLM.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Always start by extracting text from the PDF.

    line 9
  2. Distinctive:

    Do not trust "Paid In" / "Paid Out" column headers when they are ambiguous.

    line 10
  3. Distinctive:

    If Balance increases → Credit (Paid In)

    line 12
  4. Distinctive:

    If Balance decreases → Debit (Paid Out)

    line 13
  5. Distinctive:

    If column alignment in the extracted text is messy, rely on balance math rather than position.

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Bank Statement Parsing Skill

Core Rules

  • Always start by extracting text from the PDF.
  • Do not trust "Paid In" / "Paid Out" column headers when they are ambiguous.
  • Verify every transaction by checking how the running Balance changes:
    • If Balance increases → Credit (Paid In)
    • If Balance decreases → Debit (Paid Out)
  • Extract Opening Balance from "Balance Brought Forward".
  • Extract Closing Balance from the final running balance in the transactions.
  • Preserve original descriptions exactly. Do not summarize or shorten them.
  • If column alignment in the extracted text is messy, rely on balance math rather than position.

Expected Output

Return transactions in a consistent structure with: Date, Description, Debit, Credit, Balance.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free