This repository is a collection of resources (prompts, instructions, and chat modes) for using GitHub Copilot to enhance test automation and quality engineering workflows.
It is designed to help testers, developers, and quality engineers leverage AI to improve their testing practices, automate repetitive tasks, and enhance the overall quality of software products.
Tip
This project is heavily inspired by Awesome GitHub Copilot - a curated list of resources for using GitHub Copilot effectively. We have adapted the structure and content to focus specifically on testing and quality engineering, providing tailored resources for this domain.
Table of Contents
Important
Check out our free YouTube video to learn more about GitHub Copilot Chat Modes:
GitHub Copilot provides three main ways to customize AI responses and tailor assistance to your specific workflows, team guidelines, and project requirements:
- Custom Instructions: Define how Copilot should behave, what to prioritize, and how to communicate.
- Chat Modes: Create specialized chat modes for different roles or tasks, each with its own set of tools and instructions. With version 1.106 of VS Code, Chat Modes were renamed to Custom Agents.
- Custom Agents: Advanced chat modes that can utilize multiple instructions and tools to perform complex tasks.
- Prompt Templates: Predefined templates for common tasks or questions, allowing for quick and consistent responses.
Tip
More You can learn about these features in the official documentation and:
- VS Code Copilot Customization Documentation - Official Microsoft documentation
- Custom Instructions - Tailor Copilot's behavior
- Custom Chat Modes - Advanced chat configuration
- Custom Instructions - Customize Copilot's behavior
- Prompt Files - Using prompt templates
- Custom Agents - Advanced agent configuration
- Agent Skills - Extend agent capabilities with skills
- Hooks - Customize agent behavior with hooks
- Using agents in Visual Studio Code - Overview of agents and orchestration
- Subagents in Visual Studio Code - Using subagents for specialized tasks
Tip
Do you want to learn more about effective use of AI and GitHub Copilot for Testers?
Check our AI_Testers Program - a comprehensive Program for mastering AI in test automation!
Tip
Usage:
- copy these instructions to your
.github/copilot-instructions.mdfile or - create task-specific
.github/.instructions.mdfiles in your workspace's.github/instructionsfolder - use
Chat: Attach Instructionscommand from the command palette to apply them in the current chat
| Title | Description | Install |
|---|---|---|
| 🤖 Copilot Instructions – Best Practices Guide | Guide specific coding standards and best practices |   |
| API test rules (Playwright + TypeScript) | This file describes the API test rules for Playwright + TypeScript tests. | |
| Playwright E2E rules | This file describes the Playwright E2E test rules for Playwright + TypeScript tests. | |
| Page Objects / App Actions rules (Playwright + TS) | This file describes the Page Object / App Action rules for Playwright + TypeScript tests. | |
| Playwright TypeScript Test Generation Instructions | Playwright test generation instructions with best practices and patterns. | |
| TypeScript style rules | This file describes the TypeScript code style for the project. | |
Tip
Usage:
- copy these prompts to your
.github/copilot-prompts/folder - use
/prompt-namein VS Code chat, - run
Chat: Run Promptcommand from the command palette
| Title | Description | Install |
|---|---|---|
| Accessibility audit — deep dive | Run a deeper accessibility audit for a page, sampled set of pages, or user flow with WCAG 2.2 mapping, manual verification guidance, and technical or stakeholder-ready output. | |
| A11Y Webpage Audit (Single URL) | Analyze one webpage for accessibility with WCAG 2.1/2.2 mapping and actionable fixes. | |
| API Test Plan & Test Generator | Create a risk-based API test plan and generate example automated tests from API definitions (OpenAPI/Postman/custom docs). | |
| Create a bug report | Turn rough tester notes, screenshots, logs, or observed behavior into a professional bug report with severity, reproducibility, and evidence guidance. | |
| Create Skill | Create a new skill (SKILL.md) for VS Code Copilot. Analyzes existing skills for patterns, guides through design decisions, creates the skill file with supporting resources, and validates against best practices. | |
| Analyze and explain code | Analysis of the code you provide, select, or open | |
| Fix failing tests | Fix failing tests in the codebase | |
| Generate test data | Design realistic and edge-covering test data packs from requirements, constraints, or existing test plans for manual and automated testing. | |
| Generate manual test cases | Turn a feature description, acceptance criteria, exploratory notes, or a test plan into detailed manual test cases with risk tags, expected results, and automation hints. | |
| Performance & Reliability Test Planner | Design a performance and reliability test strategy and propose concrete load/soak tests for critical user flows. | |
| Explore a website and gather network requests using Playwright MCP | Website exploration and network request gathering using Playwright MCP | |
| Explore a website and propose test cases | Website exploration using Playwright MCP | |
| Generate tests based on a scenario using Playwright MCP | Generate a Playwright test based on a scenario using Playwright MCP | |
| QA Strategy — Edge Cases, Security & Attack Scenarios | For any feature, user story, or API spec: instantly generate a structured scenario matrix covering edge cases, boundary values, OWASP Top 10 security attacks, and adversarial sequences. Use the qa-strategist agent mode for best results. | |
| Analyze regression scope | Turn a diff, PR summary, changed files, or hotfix description into a prioritized regression scope with a minimal confidence suite and retest guidance. | |
| Tech Debt Audit — Test Automation Code Review | Ruthlessly audit automated test code for anti-patterns: fragile selectors, hardcoded waits, missing assertions, test interdependencies, credential leaks, and more. Produces a severity-ranked debt report with line-level citations and concrete fixes. Use the tech-debt-auditor agent mode for best results. | |
| Generate tests based on test plan | Generate tests based on test plan for a website | |
| Generate a Basic Test Plan | Generate a basic Test Plan | |
| Generate a comprehensive Test Plan | Collects environment details and produces a prioritized test plan with web and API scenarios using the Test Planner Chat Mode. |
|
| Verify acceptance criteria | Compare implementation evidence against acceptance criteria and show what is met, partial, missing, or still untestable. | |
Tip
Usage (in VS Code prior to version 1.106):
- create new chat modes:
- using the command
Chat: Configure Chat Modes...or - from set mode menu
Agent -> Configure Modes,
- using the command
- then switch your chat mode in the Chat input from set mode menu
Agent -> Configure Modes
Warning
With version 1.106 of VS Code, Chat Modes were renamed to Custom Agents.
They contain .agent.md suffix and should be stored in the .github/agents/
| Title | Description | Install |
|---|---|---|
| Accessibility Expert mode | A specialized chat mode focused on ensuring all code adheres to WCAG 2.1 accessibility standards. | |
| Playwright Automation Engineer (TypeScript) mode (detailed) | Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Prioritize maintainability, speed, reliability, and business value of the test suite. Very detailed operating manual. | |
| Playwright Automation Engineer (TypeScript) mode | Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Prioritize maintainability, speed, reliability, and business value of the test suite. | |
| QA Strategist — Edge Cases, Security & Attacks | Kills happy-path thinking. For every feature, spec, or user story the agent immediately surfaces edge cases, boundary values, security attacks (OWASP Top 10), and adversarial scenarios before a single line of test code is written. | |
| Tech Debt Auditor — Test Automation Code Reviewer | A ruthless, opinionated code reviewer for automated test suites. Hunts down anti-patterns, tech debt, and bad practices — from fragile selectors and hardcoded waits to test interdependencies, weak assertions, and credential leaks. | |
| Test Automation Architect | Help engineers craft robust, fast, and maintainable automated tests that deliver actionable feedback and integrate seamlessly into modern SDLC pipelines. | |
| Test plan from expert Senior Quality Assurance Engineer | This chat mode is designed to assist in creating comprehensive test plans tailored for web applications. | |
Tip
Usage:
- create new agents:
- using the command
Chat: Configure Custom Agents...or - from set mode menu
Agent -> Configure Custom Agents,
- using the command
- then switch your agent in the Chat input from set mode menu
Agent -> <Custom Agent Name>
| Title | Description | Install |
|---|---|---|
| Accessibility Expert mode | A specialized Agent focused on ensuring all code adheres to WCAG 2.1 accessibility standards. | |
| API Test Automation (from OpenAPI spec) | description: Generate REST API tests from an OpenAPI spec (language/framework provided by the user). | |
| Agent mission | Generates and maintains automated tests from an OpenAPI schema and supports testers as a test automation expert (best practices, patterns, project tooling). | |
| Playwright Automation Engineer (TypeScript) mode (detailed) | Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Prioritize maintainability, speed, reliability, and business value of the test suite. Very detailed operating manual. | |
| Playwright Automation Engineer (TypeScript) mode | Provide expert guidance, code, and troubleshooting help for end-to-end and component-level test automation using Playwright with TypeScript. Prioritize maintainability, speed, reliability, and business value of the test suite. | |
| QA Strategist — Edge Cases, Security & Attacks | Kills happy-path thinking. For every feature, spec, or user story the agent immediately surfaces edge cases, boundary values, security attacks (OWASP Top 10), and adversarial scenarios before a single line of test code is written. | |
| 🦆 Rubber Duck 2.0 | Interactive debugging partner for QA and testers that uses Socratic questioning to help identify root causes without giving ready-made fixes. | |
| Tech Debt Auditor | Audits the repo for technical debt, quantifies impact/risk, and produces a prioritized remediation plan with small, safe PR-sized recommendations. | |
| Test Automation Architect | Help engineers craft robust, fast, and maintainable automated tests that deliver actionable feedback and integrate seamlessly into modern SDLC pipelines. | |
| Test plan from expert Senior Quality Assurance Engineer | This chat mode is designed to assist in creating comprehensive test plans tailored for web applications. | |
| Ui Test Automation | This custom agent creates and maintains Playwright tests for UI automation. Used in courses from AI_Testers (courses about test automation for UI and REST API with AI). | |
Tip
Usage: Just pick an agent set and install the agents you want to orchestrate together, then switch to main agent from the set and start chatting. The agents will automatically trigger each other based on the defined orchestration flow.
Docs:
Contains 4 agents.
| Title | Description | Install |
|---|---|---|
| Analyst | Analyst: pattern analysis, risk assessment, and insight generation | |
| Explorer | Explorer: fast read-only codebase mapping and pattern discovery | |
| Orchestrator | Orchestrator: multi-agent conductor with explicit stop gates | |
| Planner | Planner: research-driven phased plan with test strategy and risks | |
Contains 10 agents.
| Title | Description | Install |
|---|---|---|
| Architect Subagent | Architect: ADR-ready trade-offs, NFR impacts, threat models, and test implications | |
| Code Review Subagent | Code review: correctness, risks, security, tests, and regressions (no fixes) | |
| Docs Writer Subagent | Docs: README updates, usage examples, API docs, and release notes – copy-paste ready | |
| Explorer Subagent | Explorer: fast read-only map of files, usages, patterns, and entry points | |
| Implementer Subagent | Implementer: TDD-first phase delivery with minimal diffs and quality gates | |
| Orchestrator Agent | Orchestrator: multi-agent lifecycle with explicit stop gates | |
| Planner Agent | Planner: research-driven phased plan with tests and NFRs | |
| QA Strategy Subagent | QA strategy: test pyramid, coverage goals, quality gates, and flakiness mitigation | |
| Researcher Subagent | Researcher: extract conventions, key files, patterns, and examples at scale | |
| Security Auditor Subagent | Security audit: threat model, risk scan, OWASP mapping, and concrete mitigations | |
Contains 8 agents.
| Title | Description | Install |
|---|---|---|
| OpenAPI Explorer | Analyze OpenAPI/Swagger spec and produce an API inventory + test matrix. | |
| BE Test Implementer | Implement backend/API tests from the OpenAPI-driven matrix. | |
| FE Explorer (Playwright MCP) | Explore the frontend via Playwright MCP, map flows, suggest robust locator strategy and test targets. | |
| FE Test Implementer | Implement Playwright frontend tests following the provided plan and repo conventions. | |
| QA Orchestrator | Orchestrate subagents to design, implement, review and verify FE/BE tests (OpenAPI + Playwright MCP). | |
| Solution Reviewer | Review FE/BE tests for correctness, maintainability, flakiness, and alignment with the plan. | |
| Test Planner | Combine OpenAPI + FE exploration into a prioritized test plan with architecture and tasks. | |
| Test Runner & Verifier | Run test suites, diagnose failures, and verify the final solution end-to-end. | |
Contains 5 agents. Used in courses from AI_Testers (courses about test automation for UI and REST API with AI).
| Title | Description | Install |
|---|---|---|
| Test Coder Agent | A minimal agent that implements tests based on a provided test plan. It focuses on following best practices for test implementation. | |
| Explorer Agent | A minimal agent that explores the application and gathers information for test planning. It focuses on following best practices for exploration and data collection. | |
| Test Planner | Combine exploration into a prioritized test plan with architecture and tasks. | |
| QA Orchestrator | Orchestrate subagents to design, implement, review and verify FE/BE tests (OpenAPI + Playwright MCP). | |
| Test Framework Starter Agent | A minimal agent that sets up a test framework. | |
Once you've installed the agents, here are some example prompts to get started:
Example 1: Analyze a Feature for Tech Debt (Minimal Example)
@Orchestrator Analyze this codebase for technical debt and maintainability issues.
The Orchestrator will:
- Clarify your scope and constraints
- Invoke Explorer and Analyst in parallel to research the codebase
- Present findings and recommendations for your approval
Example 2: Plan an Implementation (Full Example)
@Orchestrator Plan implementing: Add real-time notifications to our API.
Constraints: Must be backward compatible, no database schema changes.
The Orchestrator will:
- Invoke Planner to create a phased implementation strategy
- Planner will invoke Explorer to map the codebase and Architect for trade-offs
- Present a complete plan with test strategy and risk mitigation
Example 3: Security Assessment
@Orchestrator Assess the security posture of our authentication system.
The Orchestrator will:
- Invoke Explorer to find all auth-related files
- Invoke Security-Auditor to analyze patterns and identify vulnerabilities
- Synthesize findings into actionable recommendations
Tip
For more detailed workflows and best practices, see the Minimal Agent Orchestration Example README
Custom sets are combinations of custom instructions, prompt templates, and chat modes (or custom agents) designed for specific use cases.
Tip
Set elements work together to provide a tailored experience for specific testing scenarios. But you can also use them separately as needed.
Warning
Concept of Sets is not natively supported in VS Code Copilot.
Contains 1 prompt, 1 agent
| Title | Type | Description | Install |
|---|---|---|---|
| Edge Case Scenario Generator (BDD) | Prompt | Generates a complete, risk-based set of BDD test scenarios, focusing on edge cases, state validation, and boundary conditions. | |
| AI Test Architect: Beyond Codegen 2.0 Strategy | Agent | Designs and oversees the implementation of the strategic, two-stage Beyond Codegen 2.0 test generation architecture. | |
Agent Skills are folders of instructions, scripts, and resources that GitHub Copilot can load when relevant to perform specialized tasks. Agent Skills is an open standard that works across multiple AI agents, including GitHub Copilot in VS Code, GitHub Copilot CLI, and GitHub Copilot coding agent.
Tip
Usage:
- copy these skills to your
.github/skills/or.claude/skills/folder
The correct folder structure is:
.github/
└── skills/
└── <my-skill>/
├── SKILL.md
└── resources/
└── example.txt
where <my-skill> is the name of your skill. You have to name it according to the task it performs, e.g. api-playwright-test-developer or prd-generator. The SKILL.md file contains the main instructions and logic for the skill, while the resources/ folder can contain any additional files needed for the skill's operation (e.g. templates, examples, reference materials).
Agents will automatically detect and load these skills if the agent finds them relevant to the current chat context (based on the skill's name and description).
Warning
Agent Skills are currently in preview and may require enabling experimental features in VS Code settings.
| Title | Description | Install |
|---|---|---|
| analyzing-regression-scope | Analyzes diffs, changed files, hotfixes, and release candidates to identify where regression risk spreads and what must be retested first. Use when scoping retest after a change, reviewing QA impact for a pull request, or building a minimal confidence suite for release validation. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| api-playwright-test-developer | Writes and reviews API automation tests with Playwright. Use when creating backend API tests, contract checks, data-driven assertions, or API+UI hybrid workflows in Playwright Test. Focus on robust, maintainable test design with clear setup/teardown, single responsibility per test, and best practices for assertions and data management. | manual |
| auditing-accessibility | Performs webpage and user-flow accessibility audits with WCAG 2.2 guidance, manual verification checklists, prioritized remediation output, and stakeholder-ready summaries. Use when auditing accessibility on a URL, triaging suspected a11y issues, or producing technical findings with practical next steps. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| code-review-advanced | Performs evidence-driven code review for pull requests, legacy modules, and quality-critical changes. Use when reviewing code, test automation changes, architectural refactors, or hot paths that need analysis of correctness, maintainability, security, performance, test quality, and operability risks. Provides structured feedback with severity-ranked findings, actionable recommendations, and clear rationale. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| code-review | Assists users with code review, providing feedback on code quality, best practices, and potential improvements. Use always when user asks for code review or when there are code changes to review, providing feedback on code quality, structure, readability, maintainability, and adherence to coding standards. This skill provides information on best practices for code review, including how to identify issues, suggest improvements, and communicate feedback effectively. | manual |
| creating-custom-agents | Creates GitHub Copilot custom agents (.agent.md) for VS Code. Use when defining a specialized agent role, selecting a minimal toolset, referencing supporting skills, or shipping install-ready agent examples with clear boundaries and collaboration rules. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| creating-hooks | Creates GitHub Copilot hooks for VS Code using hooks.json, supporting scripts, and companion docs. Use when automating deterministic checks, pre/post tool policies, or reusable hook packs that need safe defaults, observability, and clear installation guidance. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| creating-instructions | Creates GitHub Copilot instruction files for VS Code, including repository guidance and scoped .instructions.md rules. Use when encoding project conventions, choosing applyTo patterns, or shipping install-ready instruction examples with rationale and guardrails. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| creating-prompts | Creates GitHub Copilot prompt files (.prompt.md) for VS Code. Use when building reusable workflow starters that route work to the right agent, collect the right inputs, and ship with install-ready templates, examples, and validation guidance. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| creating-skills | Creates GitHub Copilot skills with reusable workflows, companion resources, and validation gates. Use when packaging repeatable expertise into a SKILL.md folder, deciding what belongs in the skill body versus resources, or producing install-ready skill examples for a team or collection. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| designing-functional-tests | Designs risk-based functional test plans, manual test cases, regression slices, and automation handoff packs from requirements, URLs, or exploratory notes. Use when preparing manual QA coverage before automation, turning feature descriptions into scenario catalogs, or converting exploratory findings into structured test assets. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| designing-test-data | Designs realistic, boundary-heavy, and role-aware test data packs for manual and automated testing. Use when a feature needs deliberate inputs and fixtures before execution, when edge-case values keep being improvised, or when automation needs stable example data with setup notes. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| prd-generator | Generate production-ready Product Requirements Documents (PRDs) for software systems and AI-powered features. The skill ensures clear problem framing, measurable outcomes, scoped functionality, testable requirements, technical feasibility, risk awareness, and stakeholder alignment. | manual |
| reporting-bugs | Transforms rough tester notes, screenshots, console output, or observed behavior into reproducible defect reports with severity, evidence, and follow-up guidance. Use when logging bugs, triaging intermittent issues, or rewriting vague defect notes into developer-ready reports. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| requirements-test-coverage-mapper | Map requirements (PRD/user stories/AC) to comprehensive test coverage using a traceability matrix (RTM). Outputs coverage gaps, risks, test levels, prioritization, automation candidates, and change-impact notes. Designed for QA/Test Architect workflows. | manual |
| static-code-analysis-typescript | Use for create, review, or modernize static code analysis for node.js and typescript repositories. Use when you or the user needs to set up or audit eslint flat config, typescript-eslint, tsconfig, prettier, import sorting, husky, lint-staged, package.json quality scripts, and github actions quality gates. | manual |
| tech-debt-analysis | Analyzes technical debt in codebases, test suites, architecture, dependencies, and delivery workflows using observable signals. Use when auditing repository health, explaining slow delivery or flaky tests, prioritizing refactoring, or building an evidence-based remediation roadmap with risk, effort, and ROI. Use when user asks for technical debt analysis, repository audit, or refactor planning. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
| verifying-acceptance-criteria | Compares implementation evidence against acceptance criteria and shows what is met, partial, missing, or untestable. Use when checking feature readiness, preparing QA sign-off, or turning criteria into a concrete verification matrix without inventing missing behavior. 💡 Includes additional bundled resources in resources that should also be copied/used. See skill folder. |
manual |
Hooks enable you to execute custom shell commands at key lifecycle points during agent sessions. Use hooks to automate workflows, enforce security policies, validate operations, and integrate with external tools. Hooks run deterministically and can control agent behavior, including blocking tool execution or injecting context into the conversation.
Tip
Usage:
- copy these hooks to your
.github/hooks/folder or.claude/settings.json
Warning
Hooks are currently in preview and may require enabling experimental features in VS Code settings.
| Title | Description | Install |
|---|---|---|
| Print Tool Info Hook | Manual setup required |
- VS Code Copilot Customization Documentation - Official Microsoft documentation
- GitHub Copilot Chat Documentation - Complete chat feature guide
- Custom Chat Modes - Advanced chat configuration
- Custom Instructions - Customize Copilot's behavior
- Prompt Files - Using prompt templates
- Custom Agents - Advanced agent configuration
- Agent Orchestration - Coordinating multiple agents for complex workflows
- Agent Skills - Extend agent capabilities with custom skills
- Hooks - Automate actions based on chat events
- VS Code Settings - General VS Code configuration guide
- Using agents in Visual Studio Code - Overview of agents and orchestration
- Subagents in Visual Studio Code - Using subagents for specialized tasks
- Agent Skills - open standard - Specification and documentation for Agent Skills
Are you interested in contributing to this project?
We welcome your contributions! Whether it's adding new instructions, prompts, or chat modes, your input is valuable.
Just follow the Contributing Guidelines to get started!
Feel free to reach out to us:
- 🌐 Website: jaktestowac.pl
- 💼 LinkedIn: jaktestowac.pl
- 💬 Discord: Polish Playwright Community
- 📧 Support: Check our website for contact details
We have gathered a collection of resources to help you learn and master Playwright, both in Polish and English. Whether you're a beginner or an advanced user, these resources will help you enhance your skills and knowledge.
- 💡 FREE Playwright Resources - Comprehensive and Free Polish learning materials
- JavaScript and TypeScript for Testers - Comprehensive (13h+) course on JavaScript and TypeScript for testers, with practical examples and exercises
- Professional Test Automation with Playwright - Comprehensive (100h+) course on Playwright, test automation, CI/CD and test architecture
- Back-end Test Automation - Comprehensive (45h+) course on Back-end Test Automation with Postman, Mocha, Chai, and Supertest
- Playwright Basics - YouTube series (Polish)
- Playwright Elements - Advanced concepts (Polish)
- Playwright MCP - MCP course (Polish)
- Discord Community - First Polish Playwright community!
- Playwright Info - first and only Polish Playwright blog
Gain an edge by combining AI knowledge with the most popular tools in the IT market.
We'll show you how to accelerate with AI and build a professional test automation framework. 😉
- AI_Testers - Main page about AI_Testers Program
- AI_Testers LinkedIn - Follow us on LinkedIn
- VS Code Extensions - Our free Playwright plugins
- Playwright Documentation - Official documentation
- Playwright GitHub - Source code and issues
PS. For more resources and updates, follow us on our website and GitHub.
Happy testing and automation! 🚀
jaktestowac.pl Team ❤️💚
Built with ❤️💚 for the Playwright and test automation community