Test Coverage logo

Test Coverage

Organization
LedgerHQ
test-coverage

Increase test coverage to 90% on a target zone with iterative writing and refactoring

Overview

PublisherLedgerHQ
Repositoryledger-live
Skill nametest-coverage
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 Test Coverage 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/test-coverage
  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/test-coverage .claude/skills/test-coverage
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Test Coverage 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 Test Coverage 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 Test Coverage 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.

Test Coverage

Increase test coverage to 90% on a target zone with iterative writing and refactoring.

Prompt Variables

$TARGET_ZONE

Directory path or Jira ticket URL for the zone to cover (e.g., src/mvvm/features/Accounts/ or https://ledgerhq.atlassian.net/browse/LIVE-1234)

Instructions

Follow all conventions from the testing skill (.agents/skills/testing/SKILL.md). Delegate test execution to the test-runner subagent throughout.

Step 1: Scope and Analyze

  1. If $TARGET_ZONE is a Jira URL, fetch the ticket via Atlassian MCP and extract affected files.
  2. Use code-explorer subagent to analyze the zone: trace execution paths, map dependencies, and identify branching logic worth testing.
  3. Measure current coverage:
    bash
    pnpm <mobile|desktop> test:jest --coverage \
      --collectCoverageFrom='<zone-glob>' \
      --coverageReporters=text-summary
  4. From the code-explorer analysis, build the list of files to test. Skip type definitions, barrel re-exports, and thin wrappers with no branching.
  5. For each remaining file, ask:
    • Does it contain branching logic, state transitions, or side effects?
    • Would a regression break user-facing behavior?
    • Is it already covered indirectly by a parent test? If all answers are no, skip.

Step 2: Write Tests

Order: pure utils -> hooks -> viewModels -> components with side effects.

For each file:

  1. Search existing mocks/fixtures/factories before creating new ones (see testing skill).
  2. Write tests following all testing skill conventions.
  3. Run tests via test-runner. Fix failures before moving to the next file.

Loop until coverage >= 90%.

Step 3: Refactoring Loop

Three sequential passes. After each pass, run tests via test-runner -- they must still pass before the next pass.

Pass 1 -- Audit mocks

  • For every mock (jest.mock, jest.fn, mockReturnValue, jest.spyOn): is it asserted directly or does it enable a code path whose output is asserted?
  • Remove any mock that satisfies neither. Simplify over-specified mocks.

Pass 2 -- Deduplicate

  • Scan all test files in the zone for repeated factories, inline fixtures, or mock setup blocks.
  • Duplicated within one file -> extract a local helper.
  • Duplicated across 2+ files -> move to nearest __tests__/shared.ts.
  • Used in one file only -> keep local.

Pass 3 -- Prune redundant tests

  • Two it blocks testing the same branch with trivially different inputs -> merge or remove.
  • Tests that only assert a mock was called without verifying output or state -> strengthen or remove.
  • Tests on logic-free getters (direct property access) -> remove.

Step 4: Summary Report

Output a report covering:

  • Coverage: before/after percentages
  • Tests written: for each file, what behaviors were tested and why they are relevant
  • Remaining gaps: files still below 90% and why

Frequently asked questions

What does the Test Coverage AI skill do?

Increase test coverage to 90% on a target zone with iterative writing and refactoring

Why use Test Coverage on TypingMind?

Because you install it once and use it with any model. Test Coverage 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 Test Coverage in TypingMind?

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

Which AI models can use Test Coverage?

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 Test Coverage?

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

Is the Test Coverage 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 👇