agentleFS
Bhala-SrinivashBhala-Srinivash/nse-trading-skills/nse-trading-toolkit/SKILL.md

nse-trading-toolkit

Skill36 starsChanged 8 months agoMITView on GitHub

Master orchestrator for Indian NSE/BSE equity trading analysis via Groww broker. Routes to specialized framework skills: technical analysis, position sizing, stop-loss, trailing stops, risk-reward, multi-timeframe, RSI divergence, and Fibonacci trading.

  • Installs packages

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    All skills work standalone with zero dependencies — they're prompt-based frameworks that Claude applies during analysis.

    line 21
  2. Distinctive:

    Follow this sequence for a full analysis.

    line 51
  3. Distinctive:

    When presenting a full analysis, use this structure:

    line 84
  4. Distinctive:

    Use BSE symbol if NSE not available

    line 117

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

NSE Trading Toolkit — Orchestrator

This is the master workflow that coordinates 8 specialized trading framework skills for Indian NSE/BSE equities.

Prerequisites

All skills work standalone with zero dependencies — they're prompt-based frameworks that Claude applies during analysis. Connecting data sources makes them more powerful:

Data SourceRequired?What It AddsSetup
Groww MCPOptionalLive quotes, portfolio, technical indicators, candle data, order placementAdd to .mcp.json (see README)
yfinanceOptionalHistorical OHLCV (>6 months), backtestingpip install yfinance
TradingView MCPOptionalCrypto screening, volume scannersSee tradingview-mcp

Without any data source: You provide prices manually, Claude applies the frameworks. With Groww MCP: Claude pulls live data automatically. Use search_stock_and_others_symbol first to resolve the trading symbol.

Groww MCP Tool Reference

ToolUse For
search_stock_and_others_symbolFind correct trading symbol
get_quotes_and_depthLive price, volume, bid/ask depth
get_historical_technical_indicatorsRSI, MACD, SMA, EMA, Bollinger, ADX, ATR
fetch_historical_candle_dataOHLCV candles (1m to 1w intervals)
get_equity_portfolio_holdingsYour current holdings and P&L
get_ltpQuick last traded price

yfinance Quick Reference

import yfinance as yf
data = yf.download("RELIANCE.NS", period="2y", interval="1d")  # NSE: .NS, BSE: .BO

Master Workflow

Follow this sequence for a full analysis. Skip steps not relevant to the user's question.

1. CONTEXT    → What does the user hold? What's their goal?
2. DATA       → Pull live quotes + historical candles + indicators
3. STRUCTURE  → Multi-timeframe analysis (→ use multi-timeframe-analysis skill)
4. TECHNICALS → Chart reading, indicators (→ use technical-analysis skill)
                 RSI divergences (→ use rsi-divergence skill)
                 Fibonacci levels (→ use fibonacci-trading skill)
5. DECISION   → Buy / Sell / Hold with specific triggers
6. SIZING     → How many shares, at what risk (→ use position-sizing skill)
7. STOPS      → Initial stop-loss (→ use stop-loss-strategies skill)
                 Trailing plan (→ use trailing-stops skill)
8. TARGETS    → R:R ratio check (→ use risk-reward-ratio skill)
                 Fibonacci extensions (→ use fibonacci-trading skill)
9. PLAN       → Concrete action plan with prices and triggers

When to Use Which Skill

User's QuestionPrimary SkillSupporting Skills
"Analyze BBTC"This orchestratorAll 8 as needed
"Position size for RELIANCE"position-sizingstop-loss-strategies, risk-reward-ratio
"Where to set stop-loss?"stop-loss-strategiestechnical-analysis (for S/R levels)
"RSI divergence on TATAMOTORS?"rsi-divergencetechnical-analysis, fibonacci-trading
"Fib levels for INFY"fibonacci-tradingtechnical-analysis
"Should I trail my stop?"trailing-stops—
"Is this trade worth taking?"risk-reward-ratioposition-sizing
"Weekly vs daily trend?"multi-timeframe-analysistechnical-analysis

Output Format

When presenting a full analysis, use this structure:

# [STOCK] Analysis — [Date]

## Quick Take
[1-2 sentence summary: bullish/bearish/neutral + key level to watch]

## Position (if held)
[Current holdings, avg price, P&L]

## Technical Setup
[Trend, key levels, indicator readings]

## Scenarios
[Bullish / Bearish / Sideways with probabilities]

## Action Plan
| Action | Trigger | Price | Size | Stop | Target | R:R |
|--------|---------|-------|------|------|--------|-----|

## Risk Summary
- Max risk: Rs.XXX (X% of capital)
- Stop-loss: Rs.XXX
- Trailing plan: [method]

Indian Market Notes

  • NSE trading hours: 9:15 AM - 3:30 PM IST
  • Pre-open session: 9:00 - 9:15 AM
  • T+1 settlement
  • Circuit limits: 5%, 10%, 20% (varies by stock)
  • STT, brokerage, GST affect actual P&L — factor ~0.1% for delivery trades
  • Use BSE symbol if NSE not available

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.