“ava-expert” is a ready-made agent for Testing and quality, built for Claude Code, Codex, Cursor. Download the file, or use “Make a custom version” to add your project details so the AI works exactly for your project.
The agent reads this file only when a related task comes up; so keeping it in the project costs nothing.
Start each test file with clear setup and teardown
Use descriptive names for test cases
Ensure tests are independent and isolated
Take advantage of Ava's concurrent execution by default
Apply before and after hooks wisely to manage resources
Use only the necessary assertions in each test
Keep tests small and focused on a single behavior
Avoid stateful tests to prevent side effects
Refactor common setup code among tests
Embrace Ava's minimal syntax for clarity
Quality Checklist
Tests are clean and adhere to Ava's syntax
Each test case verifies a single unit of behavior
Utilize Ava's power-assert for detailed assertions
Async code is handled using async/await correctly
Global variables are avoided within tests
Execution times of test suites are optimized
Errors and warnings in console are addressed
DRY principle applied across test files
Constant test suite runtime across environments
Comprehensive code coverage with Ava's built-in support
Output
Well-documented test files with clear intentions
Efficient test execution leveraging Ava's concurrency
Error messages with detailed and actionable information
Consistent and reproducible test results
Codebase with >85% test coverage
Collection of tests that are quick to execute and diagnose
Report of potential performance bottlenecks in tests
Setup for continuous integration with Ava
Test automation scripts using Ava CLI
Guidance on best practices and test strategies using Ava
Build a custom version for your project
Write your project details; to the end of Agent is added, and you get a file that is given to the AI without extra explanation. Everything is built in your browser and no data goes to the server.
Preview of the final file
Where do I put the file?
Claude Code.claude/skills/ava-expert/SKILL.md
Codex.agents/skills/ava-expert/SKILL.md
GitHub Copilot.github/skills/ava-expert/SKILL.md
Cursor.cursor/skills/ava-expert/SKILL.md
Gemini CLI.gemini/skills/ava-expert/SKILL.md
Team projects: commit the file to the repository so every agent on the team follows the same rules. With Build a bundle Get several skills together, with the correct structure.
Frequently asked questions
Agent “ava-expert” — where do I put it?
for Claude Code in .claude/skills/ava-expert/SKILL.md, for Codex in .agents/skills, for Copilot in .github/skills and for Cursor in .cursor/skills or .cursor/rules. Use the “Build a bundle” button to get a zip with the correct structure.
Can I modify it for my own project?
Yes. The license MIT allows modification and commercial use. With “Build a custom version” your project's details are added to the file, and you can edit the text afterward.
This Agent Which tools does it work with?
With Claude Code, Codex, Cursor, Gemini CLI. Standard Agent Skills are read by all modern coding agents.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Capture screenshots of web apps during development using Playwright and PIL. Supports full-page captures, interactive states, and an iterate-on-crop workflow that avoids slow re-screenshots.
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
Run a read-only audit for missing, weak, stale, or mis-scoped test coverage. If the user does not name a scope, audit the full repository and identify important code paths, routes,…
