Position Sizing logo

Position Sizing

Community
Bhala-Srinivash
position-sizing

Calculate optimal position sizes for NSE/BSE equity trades using fixed fractional, ATR-based, and Kelly criterion methods. Includes portfolio constraints and leverage adjustments. Use when the user asks: "how many shares to buy", "position size for [stock]", "how much to invest in [stock]", "calculate lot size", "risk per trade", or any question about how much capital to allocate to a trade. Also triggers on portfolio allocation and leverage sizing questions.

Overview

PublisherBhala-Srinivash
Repositorynse-trading-skills
Skill nameposition-sizing
Stars
59
Forks
25
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Bhala-Srinivash on GitHub. Read the source before you install it.

Installation

Install the Position Sizing AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/Bhala-Srinivash/nse-trading-skills/tree/master/position-sizing
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/Bhala-Srinivash/nse-trading-skills.git /tmp/nse-trading-skills
mkdir -p .claude/skills
cp -r /tmp/nse-trading-skills/position-sizing .claude/skills/position-sizing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Position Sizing in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Position Sizing on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Position Sizing is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Position Sizing

Position sizing is how you survive. The goal: risk a small, consistent percentage of capital per trade so that no single loss can cripple your account.

Prerequisites

No dependencies required. Works with manually provided prices. Enhanced with Groww MCP (live price, ATR, portfolio) or yfinance (pip install yfinance).

Data Needed

  1. Account size: Total trading capital (ask user if not known)
  2. Current price: get_quotes_and_depth from Groww, or user-provided
  3. ATR(14): get_historical_technical_indicators from Groww, or calculate from candle data
  4. Existing positions: get_equity_portfolio_holdings to check concentration (optional)

Method 1: Fixed Fractional (Default)

This is the go-to method. Simple, robust, works for everyone.

Risk per trade = Account size × Risk%
Shares = Risk per trade ÷ (Entry price - Stop-loss price)
Capital required = Shares × Entry price

Risk% guidelines:

SituationRisk%
Normal (no leverage)1-2%
With 2x leverage0.5-1%
With 3-4x leverage0.25-0.5%
High conviction tradeUp to 3% (rare)
New/uncertain setup0.5%

Example

Account: Rs.10,00,000
Risk: 2% = Rs.20,000
Entry: Rs.1,800
Stop: Rs.1,700 (Rs.100 risk per share)
Shares: 20,000 ÷ 100 = 200 shares
Capital: 200 × 1,800 = Rs.3,60,000 (36% of account)

Method 2: ATR-Based Sizing

Uses volatility to set the stop distance, then sizes accordingly.

Stop distance = ATR(14) × multiplier
Shares = Risk amount ÷ Stop distance
Market ConditionATR Multiplier
Low volatility (ADX < 20)1.5× ATR
Normal volatility2.0× ATR
High volatility (ADX > 30)2.5× ATR

This naturally sizes you smaller in volatile stocks and larger in calm ones.

Method 3: Kelly Criterion (Advanced)

For traders with a track record of at least 30 trades:

Kelly% = W - (1 - W) / R
W = historical win rate
R = average win / average loss

Use Half-Kelly (Kelly% ÷ 2) for real trading — full Kelly is too aggressive.
Win RateAvg W/L RatioKelly%Half-Kelly
40%2.010%5%
50%1.517%8%
60%1.227%13%

Portfolio Constraints

These are hard limits — never exceed them regardless of sizing method:

ConstraintLimit
Single stockMax 20% of portfolio
Single sectorMax 35% of portfolio
Total open riskMax 6% of portfolio (sum of all position risks)
Correlated positionsMax 3 stocks in same sector simultaneously

If a position would breach a constraint, reduce size until it fits.

Leverage Adjustment

When using margin/leverage, the math changes because losses are amplified:

Effective risk% = Risk% × Leverage
So: reduce your base risk% by dividing by leverage

At 3.74x leverage:
  Normal risk: 2%
  Adjusted risk: 2% ÷ 3.74 ≈ 0.5%
  This keeps your effective risk at ~2%

Output

Present position sizing as:

Position Size: XXX shares
Capital Required: Rs.X,XX,XXX
Risk Amount: Rs.X,XXX (X.X% of account)
Stop-Loss: Rs.XXX (X.X% below entry)
Portfolio Allocation: XX% of total capital

Frequently asked questions

What does the Position Sizing AI skill do?

Calculate optimal position sizes for NSE/BSE equity trades using fixed fractional, ATR-based, and Kelly criterion methods. Includes portfolio constraints and leverage adjustments. Use when the user asks: "how many shares to buy", "position size for [stock]", "how much to invest in [stock]", "calculate lot size", "risk per trade", or any question about how much capital to allocate to a trade. Also triggers on portfolio allocation and leverage sizing questions.

Why use Position Sizing on TypingMind?

Because you install it once and use it with any model. Position Sizing is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Position Sizing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Bhala-Srinivash/nse-trading-skills/tree/master/position-sizing. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Position Sizing?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Position Sizing?

As many as you like. As long as a model supports skills, you can use Position Sizing with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Position Sizing AI skill free?

Yes. It is published on GitHub by Bhala-Srinivash under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇