Coin Families Contract logo

Coin Families Contract

Organization
LedgerHQ
coin-families-contract

Coin-specific families logic must live in families/. Generic UI uses the families contract only (no if (family === "evm") in shared code). Use this guidance for work in "**/families/**", "**/mvvm/**", "**/renderer/**" and "**/screens/**".

Overview

PublisherLedgerHQ
Repositoryledger-live
Skill namecoin-families-contract
Stars
622
Forks
491
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 LedgerHQ on GitHub. Read the source before you install it.

Installation

Install the Coin Families Contract 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/LedgerHQ/ledger-live/tree/develop/.agents/skills/coin-families-contract
  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/LedgerHQ/ledger-live.git /tmp/ledger-live
mkdir -p .claude/skills
cp -r /tmp/ledger-live/.agents/skills/coin-families-contract .claude/skills/coin-families-contract
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Coin Families Contract 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 Coin Families Contract 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 Coin Families Contract 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.

Coin families contract (Desktop & Mobile UI)

Principle: Coin-specific UI and behavior must live in families/. Generic screens, hooks, and components must not branch on family === "evm" (or any family name). They must use the families contract: optional slots defined in the family type, implemented per family, and consumed via a single lookup (e.g. getLLDCoinFamily(currency.family).SlotName). This keeps generic code family-agnostic and supports modularisation and lazy loading.

Do not do (anti-patterns)

  • Generic code (outside families/<family>/):
    • if (currency.family === "evm") / if (transaction.family === "solana") to render or behave differently.
    • Coin-specific hooks or logic in shared ViewModels / screens (e.g. Canton onboarding branch inside a generic Scan Device VM).
    • Importing a specific coin module (e.g. @ledgerhq/coin-canton) in generic UI to branch on that coin.
  • Exception: Type-narrowing inside a family folder (e.g. invariant(transaction.family === "bitcoin", "...") in families/bitcoin/) is acceptable; the rule applies to generic (shared) code only.

Do (correct pattern)

  1. Define a slot on the contract

    • Desktop: Add an optional property to LLDCoinFamily in apps/ledger-live-desktop/src/renderer/families/types.ts (e.g. NoAssociatedAccounts?: React.ComponentType<...>).
    • Mobile: Use the same idea: a typed contract (or generated map like noAssociatedAccountsByFamily) that families can optionally fill.
  2. Implement only in the family

    • Put the component or logic in families/<family>/ (e.g. families/hedera/NoAssociatedAccounts.tsx) and export it from the family index (Desktop: in the object passed to generated; Mobile: in the generated aggregation if applicable).
  3. Use the contract in generic code

    • Generic code looks up by family and uses the slot if present, with no if (family === "hedera"):
    • Desktop: getLLDCoinFamily(currency.family).NoAssociatedAccounts → use it when defined.
    • Mobile: e.g. getCustomNoAssociatedAccounts(currency) returning a component from a family map, then pass it to the screen (e.g. as CustomNoAssociatedAccounts in route params).

Reference example: Scan Device "no associated accounts"

  • Contract (Desktop):
    apps/ledger-live-desktop/src/renderer/families/types.ts — NoAssociatedAccounts?: React.ComponentType<AddAccountsStepProps> on LLDCoinFamily.
  • Family implementation:
    apps/ledger-live-desktop/src/renderer/families/hedera/NoAssociatedAccounts.tsx and hedera/index.ts exporting it in the family object.
  • Generic usage (Desktop):
    StepImport.tsx / useScanAccounts.ts: getLLDCoinFamily(mainCurrency.family).NoAssociatedAccounts — no Hedera-specific branch.
  • Generic usage (Mobile):
    useScanDeviceAccountsViewModel.ts: getCustomNoAssociatedAccounts(currency) from ~/generated/NoAssociatedAccounts; result passed as CustomNoAssociatedAccounts to the NoAssociatedAccounts screen. No if (family === "hedera") in the VM.

When you need new coin-specific behavior in a generic flow (e.g. post-add-account navigation, custom empty state): extend the contract (add a new optional slot and document it), implement it in the relevant family folder, and have the generic code only read from the contract. Do not add new if (family === "…") branches in shared UI.

Paths

  • Desktop: apps/ledger-live-desktop/src/renderer/families/ — contract in types.ts, implementations per family, aggregation in generated.ts; generic code under renderer/, mvvm/.
  • Mobile: apps/ledger-live-mobile/src/families/ — family-specific UI and flows; generic code under mvvm/, screens/. Use generated maps or a small helper (e.g. getCustomNoAssociatedAccounts) so generic code never branches on family name.

Frequently asked questions

What does the Coin Families Contract AI skill do?

Coin-specific families logic must live in families/. Generic UI uses the families contract only (no if (family === "evm") in shared code). Use this guidance for work in "**/families/**", "**/mvvm/**", "**/renderer/**" and "**/screens/**".

Why use Coin Families Contract on TypingMind?

Because you install it once and use it with any model. Coin Families Contract 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 Coin Families Contract in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/LedgerHQ/ledger-live/tree/develop/.agents/skills/coin-families-contract. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Coin Families Contract?

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 Coin Families Contract?

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

Is the Coin Families Contract AI skill free?

Yes. It is published on GitHub by LedgerHQ 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 👇