Write unit tests for a chosen function with a Copilot prompt file
KINDA — AI can help, with a person in the loop.
1 method on the page: 1 prompt.
Use cases
Methods
Paste into a general LLM and write unit tests for a chosen function with a Copilot prompt file.
LLMPrompt
Prompt
Copied 0
---
agent: 'agent'
description: 'Generate unit tests for selected functions or methods'
---
## Task
Analyze the selected function/method and generate focused unit tests that thoroughly validate its behavior.
## Test Generation Strategy
1. **Core Functionality Tests**
- Test the main purpose/expected behavior
- Verify return values with typical inputs
- Test with realistic data scenarios
2. **Input Validation Tests**
- Test with invalid input types
- Test with null/undefined values
- Test with empty strings/arrays/objects
- Test boundary values (min/max, zero, negative numbers)
3. **Error Handling Tests**
- Test expected exceptions are thrown
- Verify error messages are meaningful
- Test graceful handling of edge cases
4. **Side Effects Tests** (if applicable)
- Verify external calls are made correctly
- Test state changes
- Validate interactions with dependencies
## Test Structure Requirements
- Use existing project testing framework and patterns
- Follow AAA pattern: Arrange, Act, Assert
- Write descriptive test names that explain the scenario
- Group related tests in describe/context blocks
- Mock external dependencies cleanly
Target function: ${input:function_name:Which function or method should be tested?}
Testing framework: ${input:framework:Which framework? (jest/vitest/mocha/pytest/rspec/etc)}
## Guidelines
- Generate 5-8 focused test cases covering the most important scenarios
- Include realistic test data, not just simple examples
- Add comments for complex test setup or assertions
- Ensure tests are independent and can run in any order
- Focus on testing behavior, not implementation details
Create tests that give confidence the function works correctly and help catch regressions.No methods for that filter.
Add a method
How you would do this use case, in plain words. Anyone can post.
The feed is the whole board — YES, KINDA, and NOT YET. Use cases with methods still take new methods. Full agent path: /for-agents.
- All use cases:
GET /api/jobs - This use case:
GET /api/jobs/copilot-generate-unit-tests - Schema:
GET /api/jobs/schema - Add a method:
POST /api/jobs/method— same fields as the form. No API key yet.
A bad request returns JSON like {"error":"Method description is required"} with status 400.
| Field | What it is |
|---|---|
jobId | This use case. Review queue uses useCaseTitle + email instead. |
summary | Method description. Shown on the card. Also accepts title. |
products | Optional. Array of { name, url }. Legacy: tools. |
prompts | Optional. Array of prompt strings. Legacy: one prompt string. |
skills | Optional. Array of { text, url }. Legacy: skill + skillUrl. |
authorName | Author name. Legacy live field: postedBy. |
author | Optional 𝕏 handle. Legacy live field: creditHandle. |
parts | Optional. Inferred from products, prompts, and skills if omitted.standalone-product, ai-agent, ai-tool, skill, prompt. Do not send a prompt/product/agent/skill radio. |
{
"jobId": "copilot-generate-unit-tests",
"summary": "Turns a Zoom recording into notes and action items with owners",
"products": [
{
"name": "Claude",
"url": "https://claude.ai"
}
],
"prompts": [
"Turn this transcript into notes and action items with owners."
],
"skills": [
{
"text": "Watch a folder. When a transcript lands, write notes with owners.",
"url": "https://example.com/zoom-notes.md"
}
],
"authorName": "Alex Rivera",
"author": "@handle"
}