From odh-ai-helpers
Guides agent to write unit tests strictly conforming to project's existing testing structure, patterns, and style by first analyzing 2-3 similar tests. Use for new functions, refactors, or coverage additions.
npx claudepluginhub opendatahub-io/ai-helpers --plugin odh-ai-helpersThis skill uses the workspace's default tool permissions.
This skill ensures the agent does **not invent test structure** and instead learns how the project already tests similar code, then writes the new test in the same style, location, and pattern.
Generates unit tests matching project patterns and frameworks like Jest/Vitest (JS/TS), pytest (Python), Go testing, JUnit (Java), RSpec (Ruby).
Creates and manages unit and integration tests by analyzing the codebase, auto-detecting test frameworks, and generating tests that follow project conventions.
Provides test design patterns, coverage strategies (80-100% targets), types (unit/integration/E2E), organization, and best practices for comprehensive test suites. Use for new suites, coverage improvement, or test design.
Share bugs, ideas, or general feedback.
This skill ensures the agent does not invent test structure and instead learns how the project already tests similar code, then writes the new test in the same style, location, and pattern.
The goal is for the new test to be indistinguishable from existing tests.
Before writing any test:
You must examine at least 2–3 similar tests before proceeding.
From the discovered tests, learn:
You are learning the project’s testing contract.
Follow existing structure exactly:
Do not create a new test file unless similar tests do.
Mirror the project’s style for:
Do not introduce new libraries, helpers, or patterns.
If similar methods:
Then you must follow the same pattern.
Do not create standalone unit tests if the project does not.
Match the project’s expectations:
Do not over-test compared to existing patterns.
Search for and reuse:
Do not recreate logic that already exists.
Only after completing all discovery steps should you write the test.
The result should look like it was written by the same author as the surrounding tests.
Before finishing, confirm:
Use the ask questions tool if you need to clarify requirements with the user.