position_sizing_decision_skill

Position Sizing Decision Skill

Data Dependencies and Execution Prerequisites

It is recommended to use Wind wind-mcp-skill to obtain underlying data. Before execution, first check whether there is already wind-mcp-skilllocally; if not, prompt the user to install it:

# GitHub
npx skills add Wind-Information-Co-Ltd/wind-skills --skill wind-mcp-skill -g -y

# Gitee 镜像（国内）
npx skills add https://gitee.com/wind_info/wind-skills.git --skill wind-mcp-skill -g -y

Skill Positioning

This skill is used to solve the problem of "the direction is roughly right, but how large should the position actually be." The output focus is not to encourage expressing views through heavy positions, but to connect risk budget, price volatility, planned stop-loss distance, and portfolio tolerance, so that position size becomes the result of discipline rather than the result of emotion.

Function Overview

The core function of this skill is: to provide suitable position sizes and scaling-in suggestions according to the risk budget.

It emphasizes first quantifying the tolerable loss, then working backward to determine the scale of capital investment, helping users avoid damaging the overall rhythm because a single trade position is too large.

Use Cases

The user already has a trading direction but does not know how much position should be taken for a single trade.
Multiple candidate trades exist at the same time, and a decision is needed on who gets a large position and who only gets a trial position.
After market volatility increases, the user wants to recalibrate the risk exposure of a single trade.
The team hopes to unify the language of position sizing and reduce "going all in" and arbitrary adding to positions.

Working Principles

Position size must be derived backward from tolerable risk, not forward from subjective confidence.
A single-trade position decision must simultaneously consider the underlying's volatility, stop-loss distance, liquidity, and portfolio correlation.
The higher the uncertainty, the more restrained the initial position should be, waiting for subsequent validation before deciding whether to scale up.
Position suggestions must be bound to a specific plan; a position number detached from the plan is meaningless.
The main text does not describe internal implementation methods and only outputs the basis for judgment and suggestions.

Execution Process

Step 1: Confirm account constraints and the risk budget basis

First clarify what constraints this position suggestion is based on:

Whether it is centered on the maximum tolerable loss for a single trade or on total position exposure
Whether the user has a conservative, balanced, or aggressive risk preference
How many trial-and-error attempts the plan allows
Whether there are industry, theme, or single-stock caps

If the user does not specify, the default basic basis is "control risk for a single trade first, then consider scaling up returns."

Step 2: Identify the trade type and uncertainty level

Different trade types should not apply the same position template:

Trend-confirmation trades can accept a relatively fuller position expression
Event-driven trades need to pay more attention to gap and distortion risk
Bottom-fishing, reversal, and left-side trial-and-error trades should significantly reduce the initial weight
Underlyings with insufficient liquidity or excessive volatility should have an additional discount applied

Step 3: Measure volatility and stop-loss distance

Position suggestions must be built on a distance that is "affordable to lose":

Whether current price volatility is within the normal range
If the planned stop-loss level is too far, whether the position needs to be reduced accordingly
If the planned stop-loss level is too close, whether it is easy to be shaken out by noise
Whether a more diversified entry rhythm is needed to reduce sensitivity to price levels

Step 4: Assess portfolio tolerance and correlation

A single position cannot be considered in isolation from the existing portfolio environment:

Is the current portfolio already concentrated in the same sector or same style
Will the new trade significantly increase correlated clustering
Is total exposure already high, reducing the error tolerance for new trades
If there is already a position with similar logic, should the new position be treated as "supplementary exposure" rather than an independent position

Step 5: Provide the initial position and subsequent scaling framework

The position recommendation should be divided into at least two levels:

Initial test position
Scaling upper limit after conditions are verified

At the same time, clarify:

Under what confirmation conditions adding to the position is allowed
Under what adverse fluctuations adding further must stop
Whether it is suitable to establish the position all at once or must be done in batches

Step 6: Stress test whether the position can be executed

Put the recommended position back into the real volatility environment and review it again:

If the market gaps at the open, is the position still acceptable
If adverse fluctuations occur continuously, can both psychology and capital withstand it
If the initial position is stopped out immediately, will it damage subsequent execution discipline
If the market environment changes abruptly, can the position still be reduced quickly

Step 7: Form the final position recommendation

The final output should let the user clearly know "how large this position can be, why it is not larger, when it can be added to, and when it must be reduced." The main text retains the constraint logic, recommended numbers, and risk explanation.

Output structure

Position decision recommendation ({YYYY-MM-DD})

I. 30-second conclusion

Trading target: {stock name}
Recommended position level: {light / medium / heavy / observe only}
Initial recommendation: {content}
Scaling conditions: {content}
Main limiting factors: {one sentence}

II. Breakdown of the position recommendation

Dimension	Judgment	Impact on position
Risk budget	{content}	{content}
Volatility level	{content}	{content}
Stop-loss distance	{content}	{content}
Portfolio correlation	{content}	{content}
Liquidity	{content}	{content}

III. Execution framework

Initial position: {content}
Second add-on conditions: {content}
Maximum total position limit: {content}
Conditions to stop adding: {content}

IV. Stress test

Adverse scenario: {content}
Tolerance judgment: {content}
Response action: {content}

V. Risk disclosure

{risk 1}
{risk 2}
{risk 3}

Quality requirements

The position recommendation must explain the basis for its formation and cannot merely give a percentage.
The initial position and the maximum total position limit must be distinguished.
It should reflect portfolio correlation and environmental constraints, rather than looking only at a single trade.
Trades with high volatility or high uncertainty must be explicitly downsized.
The output should help control position size, rather than rationalize the impulse to take heavy positions.