Financial Data Extraction

Financial Data Extraction is a skill for Claude Code, Codex from Ruinius/financial-analyst-skills. It costs 41 tokens per session (4,163 once invoked), scanned A, original, MIT.

A workflow for extracting financial figures from PDF reports and adding standardized Markdown tables to the related document. It covers balance sheets, income statements, shares, organic growth, and selected GAAP reconciliations.

In plain words
What is it for?
Use it to extract balance-sheet data, income statements, shares outstanding, organic growth, and GAAP reconciliation details, then append the results to the document's Markdown file.
Why use it?
It turns figures spread across financial PDFs into structured data that later analysis can use, while separating transformer-based extraction from language-model interpretation.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract balance-sheet data, income statements, shares outstanding, organic growth, and GAAP reconciliation details, then append the results to the document's Markdown file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ruinius/financial-analyst-skills/financial_data_extraction
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Ruinius/financial-analyst-skills --skill financial_data_extraction
Clone the repo
git clone --depth 1 https://github.com/Ruinius/financial-analyst-skills

Made for: Claude Code, Codex.

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 Financial Data Extraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/ruinius/financial-analyst-skills/financial_data_extraction/github.svg)](https://agentmods.dev/skills/ruinius/financial-analyst-skills/financial_data_extraction)
Your own site
<a href="https://agentmods.dev/skills/ruinius/financial-analyst-skills/financial_data_extraction"><img src="https://agentmods.dev/badge/skills/ruinius/financial-analyst-skills/financial_data_extraction/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for Financial Data Extraction

Your own site · 80×15
<a href="https://agentmods.dev/skills/ruinius/financial-analyst-skills/financial_data_extraction"><img src="https://agentmods.dev/badge/skills/ruinius/financial-analyst-skills/financial_data_extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,163 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 $0.00041 $0.04163
Opus 5 $0.00020 $0.02082
Sonnet 5 $0.00008 $0.00833
Haiku 4.5 $0.00004 $0.00416

Measured 12d ago against content hash 58c840255ec4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Financial Data Extraction 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (resources/transformer_example.py, scripts/transform_and_append.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.

skills/financial_data_extraction/SKILL.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Financial Data Extraction (Phase 2)

Prerequisites

  • Classification metadata available in processing_data/TICKER_DOCTYPE_DATE_temp.md
  • If Tiger-Transformer is not running on localhost:8000 then ask the user to run .\tools\start_transformer.bat
  • If a static file server is not running on localhost:8181 then ask the user to run .\tools\start_file_server.bat

DO NOT EVER start servers without human user.

Overview

This skill extracts four financial components from the PDF and appends structured markdown tables to the document's .md file:

Component Requires Transformer Dependency Conditional
Balance Sheet Yes (/predict/balance-sheet) None No
Income Statement + Shares Yes (/predict/income-statement) None No
Organic Growth No (LLM-only) Income Statement (needs revenue) No
GAAP Reconciliation No (LLM-only) None earnings_announcement only

Output Script

After extracting raw data into a JSON file, run the centralized Python script:

python skills/financial_data_extraction/scripts/transform_and_append.py --json <extracted.json> --md <output.md>

The script handles:

  • Tiger-Transformer API calls for balance sheet and income statement standardization
  • Expense sign normalization (expenses → negative)
  • Accumulated depreciation sign correction
  • Organic growth calculation (simple YoY with organic growth override)
  • Markdown table formatting and appending

The script is idempotent — re-running will skip sections that already exist in the output file.

See resources/transformer_example.py for a standalone template on querying the Transformer API directly.


Step 1: Single-Pass PDF Read

Open the PDF in the browser ONCE and scroll through to extract ALL raw data needed for every component below. Collect it into a temporary JSON structure or your scratchpad. Close the browser. All subsequent steps run offline from this raw data.

What to capture during the single pass:

Read the full file on GitHub · 387 lines

Files

What ships with it

4 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. 12d ago First seen · 387 lines · 41 tokens per session scan A 58c840255ec4

Subscribe to this mod's changes

Financial Data Extraction is a skill published in the GitHub repository Ruinius/financial-analyst-skills (5 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 4,163 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-31.

Related

Other skills, from other repositories

report-generator

Generate professional HTML/PDF investment reports with interactive visualizations.

yennanliu/InvestSkill · 11 tokens

iflytek-ocr-invoice

An image-reading tool that extracts structured information from Chinese invoices, receipts, bills, and tickets. OCR means turning text in a photo or scan into computer-readable data.

iflytek/iFly-Skills · 77 tokens

cwicr-report-generator

Generate professional cost estimation reports from CWICR calculations. HTML, PDF, Excel outputs with charts and breakdowns.

datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction · 29 tokens

consulting-pdf-from-youtube

Generate polished Chinese consulting-style PDF reports from YouTube videos. Uses a transcription priority chain -- YouTube auto-subs first, Whisper fallback second (with quality gates and proper noun verification). Includes bot-detection bypass escalation when yt-dlp is blocked. Use when a user shares a YouTube link…

davidtoby/agent-skills · 76 tokens

chinese-pdf-report

Create professional Chinese PDF reports with reliable font rendering on macOS, especially when previous HTML-to-PDF output produced garbled Chinese text, missing glyphs, or ugly default typography. Use when asked to generate or re-export Chinese-heavy PDFs, fix Chinese font issues, improve typography for formal…

davidtoby/agent-skills · 80 tokens

youtube-bilingual-transcript-report

Download a YouTube video, build English and Chinese timestamped transcripts, create a structured summary with independent insights, and export a professional Chinese PDF report. Includes fallback when Chinese subtitle download hits HTTP 429 and when full-resolution video download is unnecessarily heavy.

davidtoby/agent-skills · 57 tokens