# write-tests

Systematically add test coverage for all local code changes using specialized review and development agents.

* Purpose - Ensure comprehensive test coverage for new or modified code
* Output - New test files covering all critical business logic

```bash
/write-tests ["focus area or modules"]
```

## Arguments

Optional focus area specification. Defaults to all uncommitted changes. If everything is committed, covers the latest commit.

## How It Works

1. **Preparation Phase**
   * Discovers test infrastructure (test commands, coverage tools)
   * Runs full test suite to establish baseline
   * Reads project conventions and patterns
2. **Analysis Phase** (parallel)
   * Verifies single test execution capability
   * Analyzes local changes via `git status` or latest commit
   * Filters non-code files and identifies logic changes
   * Assesses complexity to determine workflow path
3. **Test Writing Phase**
   * **Simple changes** (single file, straightforward logic): Writes tests directly
   * **Complex changes** (multiple files or complex logic): Orchestrates specialized agents
     * Coverage reviewer agents analyze each file for test needs
     * Developer agents write comprehensive tests in parallel
     * Verification agents confirm coverage completeness
4. **Verification Phase**
   * Runs full test suite
   * Generates coverage report if available
   * Iterates on gaps until all critical logic is covered

**Complexity Decision:**

* 1 simple file: Write tests directly
* 2+ files or complex logic: Orchestrate parallel agents

## Usage Examples

```bash
# Cover all uncommitted changes
> /write-tests

# Focus on specific module
> /write-tests Focus on payment processing edge cases

# Cover authentication changes
> /write-tests authentication module

# Focus on error handling
> /write-tests Focus on error paths and validations
```

## Best practices

* **Run before committing** - Ensure all changes have test coverage before commit
* **Be specific** - Provide focus areas for more targeted test generation
* **Review generated tests** - Verify tests actually test behavior, not implementation
* **Iterate on gaps** - Re-run if coverage reviewer identifies missing cases
* **Prioritize critical logic** - Not every line needs 100% coverage, focus on business logic


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://cek.neolab.finance/plugins/tdd/write-tests.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.