Kraken Twap Execution logo

Kraken Twap Execution

Organization
krakenfx
kraken-twap-execution

Execute large orders as time-weighted slices to reduce market impact.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-twap-execution
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 Twap Execution 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-twap-execution
  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-twap-execution .claude/skills/kraken-twap-execution
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Twap Execution 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 Twap Execution 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 Twap Execution 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-twap-execution

Use this skill for:

  • breaking a large order into smaller time-spaced slices
  • reducing market impact and slippage on size
  • executing over minutes, hours, or days
  • tracking average fill price across slices

Core Concept

Time-Weighted Average Price (TWAP) splits a large order into N equal slices executed at regular intervals. The goal is to achieve an average price close to the time-weighted market average, reducing the impact a single large order would have on the book.

Parameters

  • Total volume: the full amount to buy or sell
  • Slices: number of child orders (e.g., 10)
  • Interval: time between slices (e.g., 60s, 300s)
  • Slice volume: total volume / slices

Paper TWAP Test

bash
kraken workspace create sandbox --capital 50000 --mode paper -o json 2>/dev/null
export KRAKEN_WORKSPACE=sandbox

# Simulate 5 slices of 0.01 BTC each, 60s apart
kraken paper buy BTCUSD 0.01 -o json 2>/dev/null
# wait 60s
kraken paper buy BTCUSD 0.01 -o json 2>/dev/null
# wait 60s
kraken paper buy BTCUSD 0.01 -o json 2>/dev/null
# repeat...

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

Live TWAP Loop

The agent runs this loop externally (the CLI does not have a built-in scheduler):

bash
TOTAL_VOLUME=0.05
SLICES=5
SLICE_VOL=$(echo "scale=8; $TOTAL_VOLUME / $SLICES" | bc)
INTERVAL=60

for i in $(seq 1 $SLICES); do
  kraken order buy BTCUSD $SLICE_VOL --type market -o json 2>/dev/null
  [ $i -lt $SLICES ] && sleep $INTERVAL
done

Limit-Order TWAP Variant

Use limit orders at the current best bid/ask for potentially better fills:

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

Check fill status before the next slice. Cancel unfilled orders and adjust:

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

Tracking Average Fill

After all slices, compute the volume-weighted average price from trade history:

bash
kraken trades-history --consolidate-taker -o json 2>/dev/null

Sum (price * volume) for each fill, divide by total volume filled.

Rate Limit Awareness

The CLI does not pre-throttle requests. If a slice submission hits a rate limit, the error includes a suggestion field with tier-specific limits and a docs_url pointing to Kraken's documentation. On rate_limit error, pause the loop, read the suggestion, and adjust the interval before resuming. A 60-second interval between slices is well within budget for all tiers. For shorter intervals, consult the kraken-rate-limits skill for per-tier counter costs and decay rates.

Hard Rules

  • Each live slice requires human approval unless operating at autonomy level 4+.
  • Track cumulative fill volume and stop if total exceeds target (handle partial fills).
  • On error, pause the loop rather than skipping the slice; resume after recovery.
  • Log every slice for post-execution analysis.
  • 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 Twap Execution AI skill do?

Execute large orders as time-weighted slices to reduce market impact.

Why use Kraken Twap Execution on TypingMind?

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

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

Which AI models can use Kraken Twap Execution?

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 Twap Execution?

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

Is the Kraken Twap Execution 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 👇