gnkbhuvan

Screen and deeply analyze potential NSE multibagger stocks using a Peter Lynch-style quality, growth, valuation, and technical framework. Use when the user asks for multibagger stocks, undervalued high-growth NSE stocks, Peter Lynch-style analysis, top NSE multibagger candidates, smallcap/midcap compounders, value traps, or worst-case scenarios for high-potential stocks.

Master orchestrator for complete AI NSE/BSE stock analysis. Use this skill whenever the user asks to analyze a stock, generate a complete stock profile, assess 1-year upside/downside, review fundamentals, news, valuation, technicals, risks, or decide whether to buy, hold, accumulate, avoid, reduce, or watchlist an Indian equity. Route broad multibagger, undervalued high-potential, top NSE candidates, and Peter Lynch-style screening requests to the nse-multibagger skill.

Build the company and business profile section for NSE/BSE stock analysis. Use when the user asks what a company does, how it makes money, its sector, moat, market position, growth runway, cyclicality, or competitive strengths and weaknesses.

Technical analysis module for NSE/BSE stock reports. Use for weekly/daily trend, support and resistance, moving averages, RSI, MACD, ADX, Bollinger Bands, volume, breakouts, breakdowns, risk levels, and timing context.

Assess valuation for NSE/BSE stocks using P/E, P/B, EV/EBITDA, dividend yield, ROE, ROCE, peer comparison, historical valuation, growth expectations, and margin of safety.

Produce the final AI view for NSE/BSE stock analysis: rating, confidence, thesis, action zone, 1-year scenario view, invalidation, top risks, educational caveat, and investor-style one-liner.

Analyze financial reports for NSE/BSE stocks: revenue, profit, margins, EPS, debt, cash flow, ROE, ROCE, working capital, capex, and earnings quality. Use for quarterly results, annual reports, fundamentals, or business performance review.

Apply quality + value investor mental models to stock analysis. Use for long-term investor assessment inspired by public principles associated with Rakesh Jhunjhunwala, Radhakishan Damani, Warren Buffett, Charlie Munger, Peter Lynch, Benjamin Graham, and Howard Marks.

Agentic AI architecture — deciding whether to build an agent at all, then designing it. Branches: design a single- or multi-agent system, decide agent vs. workflow, design tools/MCP integration, design agent memory, design planning/orchestration, debug a looping or failing agent, or add human-in-the-loop safety gating. This is an architecture/design skill — use `fastapi-genai` for implementation and `prompt-engineering` for the actual prompt templates.

FastAPI implementation for generative AI services — the code/Python layer beneath `production-rag` and `agentic-ai`. Fires regardless of which LLM provider is involved (OpenAI, Anthropic, a self-hosted model, or any other) — the FastAPI/Python patterns are the same either way. Branches: build or serve a model-calling endpoint, stream a response token-by-token (SSE/WebSocket), define a type-safe request/response contract, persist conversation or usage data, add auth or AI-specific security (rate limiting, prompt-injection guardrails), cache or batch for cost/latency, test a non-deterministic endpoint, or containerize and deploy the service.

Retrieval-Augmented Generation (RAG) architecture — designing, scaling, or hardening a RAG pipeline for production. Branches: architect a new RAG pipeline, choose a vector database, decide a chunking strategy, evaluate retrieval/generation quality, decide RAG vs. fine-tuning vs. long-context, pick an advanced pattern (agentic/graph/multimodal RAG), or debug a RAG system that's hallucinating or retrieving the wrong thing. This is an architecture/design skill — use `fastapi-genai` to implement it.

Prompt engineering — designing, debugging, evaluating, or chaining a prompt, grounded in the Five Principles of Prompting and first-principles reasoning when the task is ambiguous. Branches: write or design a new prompt, debug a prompt that's failing, evaluate or optimize an existing prompt, apply a named technique (few-shot, chain-of-thought, ReAct, tool-use), produce a structured/RAG output format, or build a multi-step prompt chain.