Trader Rebalance logo

Trader Rebalance

Community
Jakeschincariol
trader-rebalance

Rebalancer. Brings the portfolio back to its target weights when it drifts: values every holding at current prices, works out each stock's drift from its target in percentage points, trades only the stocks outside a band (default 5 points), keeps the cash buffer and the per-stock cap, skips tiny trades, lists sells before buys, and writes the trades to trader/orders.json as proposals. Use when the user says "rebalance", "my portfolio drifted", "bring it back to the targets", "I added money", "the new 13F changed the weights", "am I overweight", or on a schedule (monthly or quarterly) after /trader-copycat updates the targets.

Overview

PublisherJakeschincariol
Repositorytrader-skill
Skill nametrader-rebalance
Stars
406
Forks
67
Bundled files
1
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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Jakeschincariol on GitHub. Read the source before you install it.

Installation

Install the Trader Rebalance 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/Jakeschincariol/trader-skill/tree/main/trader-rebalance
  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/Jakeschincariol/trader-skill.git /tmp/trader-skill
mkdir -p .claude/skills
cp -r /tmp/trader-skill/trader-rebalance .claude/skills/trader-rebalance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Trader Rebalance 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 Trader Rebalance 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 Trader Rebalance 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.

trader-rebalance

The Rebalancer keeps the portfolio looking like the plan. Prices move, new money arrives and a new 13F changes the weights; this skill finds the stocks that drifted too far and proposes the trades that bring them back. It writes proposals only: trader-risk checks them and trader-broker asks the user yes or no for each one.

${CLAUDE_SKILL_DIR} below is this skill's folder (where this SKILL.md lives).

bash
python3 "${CLAUDE_SKILL_DIR}/rebalance.py"                    # the drift table, no files written
python3 "${CLAUDE_SKILL_DIR}/rebalance.py" --band 5 --write   # proposals -> trader/orders.json
python3 "${CLAUDE_SKILL_DIR}/rebalance.py" --sell-untracked   # also sell holdings not in the targets
python3 "${CLAUDE_SKILL_DIR}/rebalance.py" --json

What it reads and writes

filewhat
trader/portfolio.jsoncash and positions (shares); same shape as trader-tax's portfolio.example.json
trader/prices.jsona price for every holding and every target (trader-alerts writes it)
trader/targets.jsonthe target weights (trader-copycat writes it)
trader/config.jsoncash buffer, cap, min and max order, rebalance_band_pct
trader/orders.jsonthe proposals it writes with --write, sells first

How it decides

  • Account value = cash + every holding at its price.
  • Targets: the weights renormalised over the stock sleeve (account minus the cash buffer), with no stock above max_position_pct of the account. The excess is shared out, the same way trader-budget does it, so a capped stock is not bought back over the cap every month.
  • Drift = current percent of the account minus target percent.
  • Band: only stocks drifting MORE than the band trade (default 5 points). A trade takes the stock all the way back to its target. A small band means more trades; a wide band means fewer.
  • Sells first, then buys. Buys only spend cash above the buffer; if there is not enough, all buys are scaled down by the same share.
  • Trades under min_order_usd are skipped. A trade over max_order_usd is cut to the max with a note to run again after it fills.
  • Untracked holdings (not in the targets) are left alone and listed, unless the user asks to sell them with --sell-untracked.

Steps

  1. Refresh prices: trader-alerts alerts.py quote --holdings --write.
  2. Run rebalance.py and show the drift table in plain words: which stocks are over or under, by how many points, and what it would trade.
  3. Before any sell, run trader-tax (lots.py sell TICKER SHARES) and show what the sale would realize. Selling a winner can mean a tax bill.
  4. If the user wants the trades: rebalance.py --write, then /trader-risk, then /trader-broker, one yes per order.

Example: the reel's portfolio

The copy portfolio bought on 2026-10-13 (AAPL $1,250 capped, AXP $1,119, GOOGL $823, KO $708, BAC $600, $500 cash), valued at that day's closes, sits on its targets: every drift is under 0.1 point, so rebalance.py says "Nothing is outside the band" and exits 1. If the user adds $2,000 of cash, the account is $7,000 and the cap becomes $1,750. AAPL is now 7.1 points under its target and AXP 6.4, both outside the 5-point band, so it proposes buying $499 of AAPL and $446 of AXP. GOOGL, KO and BAC are under target too, but inside the band, so they wait. Add $5,000 instead and all five are outside the band: five buys that leave the $1,000 buffer in cash.

What it never does

It never places an order, never trades inside the band to chase small differences, never sells holdings outside the targets unless asked, and never says a rebalance will improve returns.

Safety

  • Education and tooling, not financial advice. A rebalance follows the user's own targets, not a forecast.
  • Paper trading by default ("paper": true). Going live is the user's own decision, in their own config.
  • Nothing in this pack places an order except trader-broker, and only when all three hold: trader-risk passed that exact order today, the user typed an explicit yes for that one order in the chat, and the user clicked Allow once on Claude's own card because the order tool is set to "Needs approval" (Customize > Connectors > tool permissions). Never set an order tool to "Always allow".
  • No options, margin, short selling or leverage unless the config allows it and the user confirms.
  • Broker keys live in environment variables or the Claude Desktop config, never in the chat.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Trader Rebalance AI skill do?

Rebalancer. Brings the portfolio back to its target weights when it drifts: values every holding at current prices, works out each stock's drift from its target in percentage points, trades only the stocks outside a band (default 5 points), keeps the cash buffer and the per-stock cap, skips tiny trades, lists sells before buys, and writes the trades to trader/orders.json as proposals. Use when the user says "rebalance", "my portfolio drifted", "bring it back to the targets", "I added money", "the new 13F changed the weights", "am I overweight", or on a schedule (monthly or quarterly) after...

Why use Trader Rebalance on TypingMind?

Because you install it once and use it with any model. Trader Rebalance 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 Trader Rebalance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Jakeschincariol/trader-skill/tree/main/trader-rebalance. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Trader Rebalance?

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 Trader Rebalance?

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

Is the Trader Rebalance AI skill free?

Yes. It is published on GitHub by Jakeschincariol 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 👇