Kraken Liquidation Guard logo

Kraken Liquidation Guard

Organization
krakenfx
kraken-liquidation-guard

Prevent futures liquidation through margin monitoring and emergency procedures.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-liquidation-guard
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 Liquidation Guard 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-liquidation-guard
  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-liquidation-guard .claude/skills/kraken-liquidation-guard
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Liquidation Guard 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 Liquidation Guard 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 Liquidation Guard 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-liquidation-guard

Use this skill for:

  • monitoring margin ratio to detect liquidation risk
  • automated position reduction when thresholds are breached
  • emergency flatten procedures
  • proactive margin top-up patterns

Margin Health Check

bash
kraken futures accounts -o json 2>/dev/null

Key fields:

  • equity: total account value
  • initialMargin: margin held for positions
  • maintenanceMargin: minimum margin before liquidation
  • availableFunds: free margin for new positions

Margin ratio = maintenanceMargin / equity. Liquidation approaches as this ratio nears 1.0.

Alert Thresholds

RatioStatusAction
< 0.3HealthyNormal operation
0.3 - 0.5CautionReduce position or add margin
0.5 - 0.7WarningReduce position immediately
> 0.7CriticalEmergency flatten

Monitoring Loop

bash
kraken futures ws balances -o json 2>/dev/null | while read -r line; do
  # Parse equity and maintenanceMargin
  # Calculate ratio
  # Alert or act when threshold is breached
done

Or poll periodically:

bash
kraken futures accounts -o json 2>/dev/null

Unwind Queue Check

If a position enters the unwind queue, liquidation is imminent:

bash
kraken futures unwind-queue -o json 2>/dev/null

Any result here requires immediate action.

Emergency Flatten

Cancel all open orders, then close all positions:

bash
# Cancel all orders to free held margin
kraken futures cancel-all --yes -o json 2>/dev/null

# Close each position with reduce-only market orders
kraken futures positions -o json 2>/dev/null
# For each position:
kraken futures order sell PF_XBTUSD <SIZE> --reduce-only -o json 2>/dev/null

Margin Top-Up

Transfer funds from spot wallet to futures to increase margin:

bash
kraken futures transfer 5000 USD -o json 2>/dev/null

Or from main account:

bash
kraken wallet-transfer USD 5000 --from <SPOT_IIBAN> --to <FUTURES_IIBAN> -o json 2>/dev/null

Leverage Reduction

Lower leverage to reduce margin requirements:

bash
kraken futures set-leverage PF_XBTUSD 2 -o json 2>/dev/null

Dead Man's Switch

Always run a dead man's switch during futures sessions:

bash
kraken futures cancel-after 600 -o json 2>/dev/null

If the agent crashes, orders auto-cancel, preventing further margin consumption.

Hard Rules

  • Monitor margin ratio continuously during any futures session.
  • Alert at 0.5 ratio; act at 0.7. Do not wait for the exchange to liquidate.
  • Emergency flatten requires human approval unless the agent operates at autonomy level 4+.
  • Never increase position size when margin ratio is above 0.3.
  • futures set-leverage is flagged dangerous: it changes the margin requirement on open positions, so de-risking with it needs the same human approval as flattening.
  • 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 Liquidation Guard AI skill do?

Prevent futures liquidation through margin monitoring and emergency procedures.

Why use Kraken Liquidation Guard on TypingMind?

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

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

Which AI models can use Kraken Liquidation Guard?

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 Liquidation Guard?

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

Is the Kraken Liquidation Guard 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 👇