test-writer

SkillAI & models

Write unit tests for any function — happy path, edge cases, and error cases. Use when the user asks for tests, wants to add test coverage, or is practicing TDD.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the test-writer skill

What this skill tells your AI

The instructions your AI receives, as published by hamzafarooq/multi-agent-course in .claude/skills/test-writer/SKILL.md and read by ahel’s review.

Ask the user to share the function or code they want tests for.

Then write tests covering:

Tests for [functionName]

Testing framework: [detect from package.json — Jest, Vitest, pytest, etc. Ask if unclear]


Happy path

Test the expected behavior with valid inputs. One test per meaningful variation.

test('returns [expected] when given [input]', () => {
  // arrange
  // act
  // assert
})

Edge cases

Tests for boundary conditions and unusual but valid inputs:

  • Empty input (empty string, empty array, 0)
  • Single item
  • Maximum size or value
  • Special characters (if string input)

Error cases

Tests that verify the function fails correctly:

  • Invalid input types
  • Null/undefined inputs
  • Inputs that should trigger error handling

Mock requirements

List any external dependencies (API calls, database queries, file system) that need mocking, with example mock setup.


Coverage target: Aim for all branches, not just lines. Flag any branch that is difficult to test and explain why.

Write tests that read like documentation — the test name should be a sentence explaining what the function does in that scenario.

Signals

GitHub stars
84
Forks
70
Last commit
Sep 2026

ahel recommends instead

Advanced
Catalog kind
skill
Gateway key
test-writer-2
Source
github.com/hamzafarooq/multi-agent-course