Kraken Rebalancing logo

Kraken Rebalancing

Organization
krakenfx
kraken-rebalancing

Portfolio rebalancing to maintain target allocations across assets.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-rebalancing
Stars
754
Forks
104
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 krakenfx on GitHub. Read the source before you install it.

Installation

Install the Kraken Rebalancing 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/krakenfx/kraken-cli/tree/main/skills/kraken-rebalancing
  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/krakenfx/kraken-cli.git /tmp/kraken-cli
mkdir -p .claude/skills
cp -r /tmp/kraken-cli/skills/kraken-rebalancing .claude/skills/kraken-rebalancing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Rebalancing 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 Kraken Rebalancing 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 Kraken Rebalancing 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.

kraken-rebalancing

Use this skill for:

  • checking current portfolio allocation vs target weights
  • calculating rebalance trades
  • executing rebalance orders with minimum trade thresholds
  • scheduling periodic rebalance checks

Define Target Allocation

Example target: 50% BTC, 30% ETH, 20% SOL (by USD value).

The agent maintains these weights and compares against current holdings.

Read Current Portfolio

  1. Get balances:
    bash
    kraken balance -o json 2>/dev/null
  2. Get current prices for all held assets:
    bash
    kraken ticker BTCUSD ETHUSD SOLUSD -o json 2>/dev/null
  3. Calculate USD value of each holding and total portfolio value.
  4. Compute current weights: asset_value / total_value for each.

Calculate Rebalance Trades

For each asset:

  • Target value = total_portfolio * target_weight
  • Current value = holdings * current_price
  • Delta = target_value - current_value
  • If delta > threshold: buy (delta / price) units
  • If delta < -threshold: sell (|delta| / price) units

Set a minimum trade threshold (e.g., $50) to avoid placing tiny orders that waste fees.

Paper Rebalance Test

bash
kraken workspace create sandbox --capital 10000 --mode paper -o json 2>/dev/null
export KRAKEN_WORKSPACE=sandbox

# Initial buys to establish positions
kraken paper buy BTCUSD 0.05 -o json 2>/dev/null
kraken paper buy ETHUSD 1.0 -o json 2>/dev/null
kraken paper buy SOLUSD 10 -o json 2>/dev/null

kraken workspace status -o json 2>/dev/null

# After price drift, rebalance
# Sell overweight asset, buy underweight asset
kraken paper sell BTCUSD 0.005 -o json 2>/dev/null
kraken paper buy SOLUSD 2 -o json 2>/dev/null

kraken workspace status -o json 2>/dev/null

Live Rebalance Execution

  1. Calculate all required trades.
  2. Present the rebalance plan to the user:
    • Current allocation vs target
    • Proposed trades with estimated fees
  3. Validate each order:
    bash
    kraken order sell BTCUSD 0.005 --type market --validate -o json 2>/dev/null
    kraken order buy SOLUSD 2 --type market --validate -o json 2>/dev/null
  4. Execute sells first (to free capital), then buys (requires human approval):
    bash
    kraken order sell BTCUSD 0.005 --type market -o json 2>/dev/null
    kraken order buy SOLUSD 2 --type market -o json 2>/dev/null
  5. Verify final state:
    bash
    kraken balance -o json 2>/dev/null

Drift Detection

Periodically compare current weights to targets. Trigger rebalance when any asset drifts beyond a threshold (e.g., 5% absolute drift):

bash
# Agent checks balance and prices on a schedule
# If |current_weight - target_weight| > 0.05 for any asset → rebalance

Rebalance with Limit Orders

For lower fees, use limit orders instead of market:

bash
PRICE=$(kraken ticker SOLUSD -o json 2>/dev/null | jq -r '.[].ask_price')
kraken order buy SOLUSD 2 --type limit --price $PRICE -o json 2>/dev/null

Check fills before declaring rebalance complete:

bash
kraken open-orders -o json 2>/dev/null

Hard Rules

  • Never execute rebalance trades without explicit human approval.
  • Always present the full rebalance plan (sells and buys) before execution.
  • Execute sells before buys to ensure sufficient quote currency.
  • Respect minimum order sizes for each pair (check pair info with kraken pairs).
  • Apply a minimum trade threshold to skip negligible adjustments.
  • If you hit a mismatch between what you are trying to do and the CLI's interface or responses — including a mismatch between this skill and the installed CLI version's contract — feel free to submit feedback with kraken feedback.

Frequently asked questions

What does the Kraken Rebalancing AI skill do?

Portfolio rebalancing to maintain target allocations across assets.

Why use Kraken Rebalancing on TypingMind?

Because you install it once and use it with any model. Kraken Rebalancing 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 Kraken Rebalancing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/krakenfx/kraken-cli/tree/main/skills/kraken-rebalancing. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Kraken Rebalancing?

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 Kraken Rebalancing?

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

Is the Kraken Rebalancing AI skill free?

Yes. It is published on GitHub by krakenfx 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 👇