- Home
- Skills
- Finance & Accounting
- Bank Statement CSV Cleanup & Import Preflight Pack
More screenshots
Works with the AI tools you already use
Bank Statement CSV Cleanup & Import Preflight Pack
Clean a local bank-transaction CSV into a stable import table and isolate invalid, ambiguous and duplicate-looking rows before bookkeeping work.
$5
Bank Statement CSV Cleanup & Import Preflight Pack
Example session with this skill installed
Analyze my authorized local bank export transactions_july.csv with the included policy file. Create a new review packet in ./audit_july, then summarize rejected rows, possible duplicates and the files I should review before import.
- Read your context and instructions
- Compiled the bank statement csv
- Generated the data export
Preflight complete
The local deterministic check completed without modifying the source CSV. A new packet was written to ./audit_july and every input and generated file was bound in evidence-receipt.json with SHA-256.
| Output | Purpose | Sample result |
|---|---|---|
| clean-transactions.csv | Stable import-ready table | 142 accepted rows |
| rejected-rows.csv | Rows that failed required checks | 4 rows |
| duplicate-candidates.csv | Possible repeated transactions | 2 groups |
| issues.jsonl | Machine-readable findings | 7 findings |
| BANK_CSV_PREFLIGHT.md | Human review report | Created |
Review findings
- One row contains an invalid date and remains excluded from the clean table.
- Three rows are missing required amount or description fields.
- Two possible duplicate groups share the same normalized date, amount and description. They are flagged for review and were not automatically deleted.
- Formula-active spreadsheet cells were escaped in every generated CSV.
Next steps
- Open rejected-rows.csv and correct only the original source data when you have supporting evidence.
- Review duplicate-candidates.csv before deciding whether any transaction is truly duplicated.
- Use clean-transactions.csv only after your normal bookkeeping review.
- Keep evidence-receipt.json with the packet so another reviewer can verify exactly which inputs produced these outputs.
The tool did not log into a bank, categorize transactions, post to a ledger or certify reconciliation.
bank-statement-csv-cleanup-import-prefli.csv
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
What you get
About this skill
This downloadable local package turns authorized buyer-supplied files into a fixed, reproducible review packet. It includes an installable Python CLI, a local stdio MCP adapter and a companion Agent Skill. One run creates:
- result.json
- clean-transactions.csv
- rejected-rows.csv
- duplicate-candidates.csv
- issues.jsonl
- BANK_CSV_PREFLIGHT.md
- evidence-receipt.json
The deterministic core rejects unsafe paths and malformed inputs, never overwrites an existing packet, escapes formula-active CSV cells and binds each input and output with SHA-256. Processing stays local. No API key, login, upload, telemetry or live external action is included.
Best for bookkeepers, accountants, small-business operators and agencies preparing bank exports for review. Requires Windows 11, Python 3.11–3.14 and authorized local evidence files. Optional mcp==2.2.0 enables the local MCP adapter.
Limitations: no PDF or image OCR, bank login, transaction categorization, reconciliation certification, tax or accounting advice, ledger posting, file import or source-file modification. This is a one-time local V1.
How to install
Works the same in every agent - Claude, Cursor, Codex, Copilot and 20+ more.
- 1
Download the ZIP
Free skills download straight away. Paid skills unlock right after purchase.
- 2
Unzip into your skills folder
Every agent reads skills from one folder on your machine. Drop the unzipped folder in there.
- 3
Ask your agent to use it
Restart the agent if it was already running. It picks the skill up automatically - no config needed.
Skills folder by agent
Click the path to copy it. Create the folder if it does not exist yet.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
30-day refund
Not a fit? Get your money back
Trust & safety
Security scanned
Verified clean 18 days ago
- Passed all security checks, Safe to install