data-analysis-iteration

Community

End-to-end on-device data analysis with AI agents.

Authoranbeime
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This skill enables end-to-end data-analysis on Windows ARM64 using NPU-accelerated models. It supports batch processing, OCR, vector search, and knowledge-graph management across eight agents to deliver actionable insights while keeping data on-device.

Core Features & Use Cases

  • Eight-Agent collaboration orchestrates data flow from ingestion to final report.
  • On-device NPU-accelerated inference ensures data privacy and low latency.
  • Supports multi-format data (CSV/JSON/Excel) and OCR for images; enables batch processing and automated card generation.
  • Builds and queries a local knowledge graph with vector search for contextual insights.
  • Automated report generation and knowledge retention for future reuse.

Quick Start

Run batch_process.py on your data directory to preprocess files, trigger the eight-agent workflow, and generate a set of blue/green/yellow/red cards along with a final report. Ensure QNN SDK, GenieAPIService, and required Python packages are installed and configured as described in the repository references. Then review the generated cards in the knowledge dashboard and export the final report.

Dependency Matrix

Required Modules

pandasopenpyxlpytesseractPillowfastapiuvicornfaiss-cpusentence-transformersduckdbqnntorch

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: data-analysis-iteration
Download link: https://github.com/anbeime/antinet/archive/main.zip#data-analysis-iteration

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.