Kraken Shared logo

Kraken Shared

Organization
krakenfx
kraken-shared

Shared runtime contract for kraken-cli: auth, invocation, parsing, and safety.

Overview

Publisherkrakenfx
Repositorykraken-cli
Skill namekraken-shared
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 Shared 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-shared
  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-shared .claude/skills/kraken-shared
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Kraken Shared 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 Shared 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 Shared 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-shared

This tool is experimental. Commands execute real financial transactions on the Kraken exchange. Test with kraken paper before using real funds. See DISCLAIMER.md for full terms.

Invocation Contract

Always call:

bash
kraken <command> [args...] -o json 2>/dev/null

Rules:

  • Parse stdout only.
  • Treat stderr as diagnostics.
  • Exit code 0 means success.
  • Non-zero exit means failure with JSON envelope in stdout.
  • Streaming commands (session start, record, ws, streamd) emit JSONL: match lines by their "type" field (e.g. scan for "type":"session_started" to get the session handle) — never assume a line position, because live market frames interleave on stdout.
  • Probe capability, not version, at the start of a loop: kraken session --help >/dev/null 2>&1 exits 0 on a build that speaks this contract and 2 on an older one — kraken --version cannot tell them apart across a vocabulary change.
  • Market-data field names are readable (last_price, not c[0]). Only ticker still keys on Kraken's INTERNAL pair name (XXBTZUSD, not BTCUSD) — reach its fields with .[] or to_entries, never a hardcoded key. ohlc/trades/spreads reshape to {pair, …}: fold the named row array (.candles/.trades/.spreads) directly, never the whole object — ohlc keeps a sibling last cursor that poisons naive iteration. orderbook drops the wrapper to top-level .asks/.bids.
  • Validate every number a READ produces before it gates an order or lands in a reason. On an empty or failed read, record kraken session note --kind alert --reason "READ failed: ..." and end the step — never interpolate a failed read into a reason, or the decision log fills with plausible-looking false evidence.

Authentication

bash
export KRAKEN_API_KEY="your-key"
export KRAKEN_API_SECRET="your-secret"

Optional futures credentials:

bash
export KRAKEN_FUTURES_API_KEY="your-futures-key"
export KRAKEN_FUTURES_API_SECRET="your-futures-secret"

Public market data and paper trading require no credentials.

Error Routing

Route on .error:

  • auth: re-authenticate
  • rate_limit: read suggestion and docs_url fields, adapt strategy
  • network: retry with exponential backoff
  • validation: fix inputs, do not retry unchanged request
  • api: inspect request parameters

Safety

The catalog marks 41 commands as dangerous: true. Always check the dangerous field in agents/tool-catalog.json before executing a command.

Require explicit human approval before:

  • live buy or sell orders (spot and futures)
  • order amendments, edits, and batch operations
  • cancel and cancel-all operations
  • withdrawals and wallet transfers
  • earn allocate/deallocate
  • subaccount transfers
  • WebSocket order mutations

Use paper trading for dry runs:

bash
kraken workspace create sandbox --capital 10000 --mode paper -o json
export KRAKEN_WORKSPACE=sandbox

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 Shared AI skill do?

Shared runtime contract for kraken-cli: auth, invocation, parsing, and safety.

Why use Kraken Shared on TypingMind?

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

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

Which AI models can use Kraken Shared?

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 Shared?

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

Is the Kraken Shared 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 👇