my-personal-assistant: Skill for Claude Code

.claude/skills/finance-process/extract-pdf-transactions/SKILL.md

extract-pdf-transactions is a skill for Claude Code from ronnycoding/my-personal-assistant. It costs 0 tokens per session (529 once invoked), scanned A, original, MIT.

A tool for extracting dates, descriptions, amounts, and balances from transaction tables in PDF bank and credit-card statements.

In plain words
What is it for?
Use it to process one or more PDF statements, including statements spread across multiple pages, and save the results as CSV data.
Why use it?
It converts hard-to-edit statement documents into structured transaction data and checks whether the extracted information is complete.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is ronnycoding/my-personal-assistant's own configuration. It tells Claude Code how to work on my-personal-assistant itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything my-personal-assistant configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ronnycoding/my-personal-assistant. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/ronnycoding/my-personal-assistant/main/.claude/skills/finance-process/extract-pdf-transactions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ronnycoding/my-personal-assistant

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for extract-pdf-transactions

README.md
[![agentmods](https://agentmods.dev/badge/skills/ronnycoding/my-personal-assistant/extract-pdf-transactions.svg)](https://agentmods.dev/skills/ronnycoding/my-personal-assistant/extract-pdf-transactions)
Your own site
<a href="https://agentmods.dev/skills/ronnycoding/my-personal-assistant/extract-pdf-transactions"><img src="https://agentmods.dev/badge/skills/ronnycoding/my-personal-assistant/extract-pdf-transactions.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 529 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00529
Opus 5 $0.00000 $0.00264
Sonnet 5 $0.00000 $0.00106
Haiku 4.5 $0.00000 $0.00053

Measured 6d ago against content hash 2d33b6244b1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

extract-pdf-transactions scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/extract_bac_statements.py, scripts/extract_pdf_statements.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/finance-process/extract-pdf-transactions/SKILL.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Extract PDF Transactions Skill

Extract transaction data from PDF bank and credit card statements.

Skill Metadata

  • Name: extract-pdf-transactions
  • Category: Financial Data Processing
  • Complexity: Medium
  • Privacy: Local processing only, no external APIs

Capabilities

This skill extracts structured transaction data from PDF financial statements:

  1. Multi-format PDF parsing - Supports various bank statement layouts
  2. Table detection - Automatically identifies transaction tables
  3. Data extraction - Parses dates, descriptions, amounts, and balances
  4. Multi-page support - Processes statements spanning multiple pages
  5. Error handling - Gracefully handles malformed PDFs
  6. Validation - Verifies extracted data quality

Usage

/finance-process extract --input="~/Documents/Finance/*.pdf" --output="~/Documents/Finance/transactions.csv"

How It Works

  1. PDF Discovery: Finds all PDF files matching the input pattern
  2. Content Extraction: Uses pdfplumber to extract text and tables
  3. Table Parsing: Identifies transaction tables using pattern matching
  4. Data Normalization: Standardizes column names and formats
  5. Validation: Checks for completeness and accuracy
  6. CSV Export: Saves transactions to specified output file

Script

The main script is scripts/extract_pdf_statements.py which:

  • Accepts PDF file paths (glob patterns supported)
  • Extracts transaction tables
  • Outputs to CSV format
  • Provides progress feedback and error reporting

Dependencies

Required Python packages:

  • pdfplumber (primary extraction engine)
  • pandas (data manipulation)
  • python-dateutil (date parsing)
  • tabula-py (fallback for complex tables)

Output Format

The skill produces CSV files with these columns:

  • date - Transaction date (YYYY-MM-DD)
  • description - Transaction description/merchant
  • amount - Transaction amount (negative for debits)
  • balance - Account balance after transaction
  • category - Auto-categorized transaction type
  • source_file - Original PDF filename

Read the full file on GitHub · 78 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 78 lines · 0 tokens per session scan A 2d33b6244b1f

Subscribe to this mod's changes

extract-pdf-transactions is a skill published in the GitHub repository ronnycoding/my-personal-assistant (12 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 529 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-02.