pushpankar-kiran

India Ipo Dashboard — Data skill for Claude Code

Data community

Personal analytics dashboard for Indian IPOs: benchmark-adjusted returns, market-pulse analytics, and AI-assisted 'similar past IPO' comparison.

How to install India Ipo Dashboard

This entry records only its repository, not the path inside it, so there is no exact command to give. Open pushpankar-kiran/india-ipo-dashboard and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What India Ipo Dashboard does

Personal analytics dashboard for Indian IPOs: benchmark-adjusted returns, market-pulse analytics, and AI-assisted 'similar past IPO' comparison. FastAPI + SQLite + yfinance, hybrid deterministic core + Claude Agent SDK.

Alternatives in Data

Context Mode — Benchmark Results — Benchmarked against real outputs from popular Claude Code MCP servers, Skills, and dev tools 5.6k ★
Core Data Agent Skill — An Agent Skill focused on Apple’s Core Data framework, helping with data modeling, fetch requests, performance 301 ★
Extraction Pipeline — Extraction Pipeline — Core Domain Logic — GenAI IDP Accelerator 295 ★

README

India IPO Performance Dashboard

[![CI](https://github.com/pushpankar-kiran/india-ipo-dashboard/actions/workflows/ci.yml/badge.svg)](https://github.com/pushpankar-kiran/india-ipo-dashboard/actions/workflows/ci.yml) [![Python 3.12+](https://img.shields.io/badge/python-3.12%2B-blue.svg)](https://www.python.org/) [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE) [![Code style: FastAPI](https://img.shields.io/badge/API-FastAPI-009688.svg)](https://fastapi.tiangolo.com/)

Track historical IPO performance, benchmark-adjusted against the Nifty 50, compare upcoming IPOs against the past ones that resemble them, and get an AI-written verdict grounded in those comparables.

Built in phases per [`india-ipo-dashboard-spec.md`](india-ipo-dashboard-spec.md). **Phases 1–3 are complete** (100+ IPOs, tested core, analytics, and the AI comparison layer).

Screenshots

Dashboard & Market Pulse	Price timeline & fundamentals	AI "similar past IPO" verdict

Architecture

A **hybrid** design: a deterministic, unit-tested core owns every number a decision rests on, and (from Phase 3+) a Claude Agent SDK layer handles the messy, judgement-heavy work — data ingestion and "similar IPO" comparison. The AI layer never computes a return; it only proposes structured data that is validated before the tested core does the maths.

app/
├── core/
│   ├── calculations.py   # pure, tested maths — single source of truth for every number
│   ├── models.py         # SQLModel schema (the contract every layer agrees on)
│   └── prices.py         # yfinance price checkpoints (only network-touching core module)
├── api/routes.py         # FastAPI JSON API (parameterised queries only)
├── data/
│   ├── seed_ipos.json    # curated starting dataset
│   └── seed.py           # loader + price refresh
├──