ariadne-finance

Ingest financial PDFs, Excel, and CSV reports into a searchable knowledge graph.

12|Updated Jun 4, 2026
One-click install
npx skills add https://github.com/kyssta-exe/Ariadne --skill ariadne-finance
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ariadne-finance
Source: https://github.com/kyssta-exe/Ariadne/tree/main/addons/finance/skill
Command: npx skills add https://github.com/kyssta-exe/Ariadne --skill ariadne-finance

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Finance research teams struggle to extract consistent financial data from PDFs, Excel, and CSV reports and to connect disparate entities into a cohesive knowledge graph for faster insights.

Core Features & Use Cases

  • Ingest financial documents (PDF/Excel/CSV) into Ariadne memories for indexing and retrieval.
  • Recognize stock tickers, classify market sectors, and build a knowledge graph linking entities across reports.
  • Enable end-to-end workflows for searching across multiple documents and enriching memories with market data.

Quick Start

Ingest a financial document to begin memory-building and enable subsequent search and graph queries.

Frequently Asked Questions about ariadne-finance

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract financial data from PDF and Excel reports into a searchable memory?

To extract financial data from PDFs and Excel reports, ingest the documents into Ariadne memories for indexing and retrieval. This builds a searchable financial memory that enables subsequent search and graph queries across all ingested files.

Can I automatically recognize stock tickers and classify market sectors from financial documents?

Automated ticker recognition and market sector classification are supported during document ingestion. The Skill processes financial PDFs and spreadsheets to identify stock tickers and classify sectors while building a linked knowledge graph across reports.

How do I build a financial knowledge graph linking entities across multiple PDF and CSV reports?

Building a financial knowledge graph is done by ingesting multiple PDF and CSV reports into Ariadne. The Skill links recognized entities and tickers across documents, creating a queryable graph structure for cross-report financial analysis.

What is the best way to search across multiple financial documents after ingestion?

The best way to search across financial documents is using the provided Python API and CLI workflows after ingestion. These tools query the financial memory and knowledge graph, enabling cross-document entity retrieval with robust error handling.

Does the financial data ingestion workflow support CSV files alongside PDF and Excel formats?

CSV file ingestion is fully supported alongside PDF and Excel formats. The Skill processes CSV financial reports to extract tickers, classify sectors, and integrate the data into the searchable Ariadne memory and knowledge graph.

What are the limitations of building a financial memory from ingested PDF reports?

Limitations depend on document structure quality and data consistency within source PDFs. The Skill provides robust error handling during ingestion, but poorly formatted financial reports may affect ticker recognition and knowledge graph linking accuracy.